Загрузка видео...

Не удалось загрузить видео

Возникла проблема при загрузке этого видео. Это может быть связано с временными проблемами сети или видео может быть недоступно.

На главную

Codex tip: once GPT-6.1 Sol runs your main session, stop paying Sol prices for the grunt work hand the reading to Luna and put Astra on call Sol keeps writing the code Luna agents read the repo and pull the docs, fast and cheap Astra only gets spawned at... three moments: → before a plan: is this the right approach? → when the same error comes back: am I digging in the wrong place? → before "done": what did I miss? Sol ships. Luna reads. Astra checks jev engineering is the same move one layer down: the forks that need no thinker (which file, which tool, retry or stop) go to jev in under half a second, and the big models only see the ones that split - the full tree > GPT-6.1 Sol on high runs the main session > explorer reads the code on Luna > researcher pulls the docs on Luna > worker edits and runs tests on Sol > Astra on call as the architect > auto_review watches every approval paste the tree and this prompt into Codex ↓ "Rebuild my Codex setup around this tree: 1. Check ~/.codex/agents and .codex/agents for agents that already fit explorer, researcher and worker. > Draft new TOML files only for missing roles > explorer and researcher on gpt-6-luna, worker on gpt-6.1-sol, all with model_reasoning_effort medium > Add an architect agent on gpt-6-astra, model_reasoning_effort high, that only reviews plans, repeated errors and finished work > List any that pin a different model before changing them 2. In ~/.codex/config.toml set model to gpt-6.1-sol, model_reasoning_effort to high and approvals_reviewer to auto_review 3. Find anything that would override this (active profiles, flags in my shell aliases, agents.default_subagent_model). Report it, change nothing 4. Add one rule to AGENTS.md: spawn the architect before a large plan, when an error repeats, and before calling a long task done Show me every change as a diff first. No edits until I say go." ↳show more

Hanako

19,508 subscribers

29,559 просмотров • 7 дней назад •via X (Twitter)

Anya Rossi• Live Now

Private livecam show

Комментарии: 10

Фото профиля Sahibzada Allahyar

Sahibzada Allahyar6 дней назад

I’d replace Jev with GLiDE for those tool and retry decisions. It scores 83.5 in Decision Index tools vs Jev’s 75.1, and 64.81 vs 57.91 overall. You still get a bounded choice, with extra reasoning when needed.

Фото профиля slash1s

slash1s7 дней назад

huh that’s terminal looks hige

Фото профиля Hussain Hashim | Building SundayBack

Hussain Hashim | Building SundayBack6 дней назад

@hanakoxbt sometimes Luna misses context on complex docs. I offloaded some of the parsing to Notion for clarity before it hits Astra.

Фото профиля motyka_9

motyka_97 дней назад

Love how this mirrors the jev routing pattern one layer up too, cheap models handling reads and writes while the expensive one only gets pulled in at the three moments that actually need judgment, same principle applied at every layer of the stack

Фото профиля Brjan | AI Builder

Brjan | AI Builder7 дней назад

that workflow sounds efficient, but managing multiple agents can get tricky

Фото профиля noel

noel7 дней назад

Escalating on triggers (same error returns, before "done") beats "use the big model when it feels hard". Curious whether Astra sees the full session at "before done", since that probably decides whether it catches anything.

Фото профиля Alison Jungles

Alison Jungles6 дней назад

Looks perfect how can get some visualization?

Фото профиля it's Sofia

it's Sofia6 дней назад

sol keeps writing the code until luna reads something wrong and astra gets spawned at 3am

Фото профиля Ahmed Hossam

Ahmed Hossam6 дней назад

how do you create these moving real time diagrams?

Фото профиля catman

catman7 дней назад

It’s like a workshop: readers scout for parts, workers build, and the architect checks the plan before you call it finished.

Похожие видео

Codex tip: once GPT-6.1 Sol is your main model, stop running Astra on every turn put Astra on call as an architect agent GPT-6.1 Sol keeps writing the code Astra only gets spawned at three points: → before a plan: is this the right approach? → when the same error comes back: am I digging in the wrong place? → before "done": what did I miss? Astra reviews. Sol ships Jev engineering is the same move one layer down: the forks that need no thinker (which file, which tool, retry or stop) go to Jev in under half a second, and the big models only see the ones that split - the full tree > GPT-6.1 Sol on high runs the main session > explorer reads the code on Luna > worker edits and runs tests on Sol > researcher pulls the docs on Luna > all three on medium > Astra on call as the architect > auto_review checks every approval paste the tree and this prompt into Codex ↓ "Rebuild my Codex setup around this tree: 1. Check ~/.codex/agents and .codex/agents for agents that already fit explorer, worker and researcher. > Draft new TOML files only for missing roles > explorer and researcher on gpt-6-luna, worker on gpt-6.1-sol, all with model_reasoning_effort medium > Add an architect agent on gpt-6-astra, model_reasoning_effort high, whose only job is reviewing plans, repeated errors and finished work > Skip any that pin a different model and list them 2. In ~/.codex/config.toml set model to gpt-6.1-sol, model_reasoning_effort to high and approvals_reviewer to auto_review 3. Find anything that would override this (active profiles, flags in my shell aliases, agents.default_subagent_model). Report it, change nothing 4. Add one rule to AGENTS.md: spawn the architect before a large plan, when an error repeats, and before calling a long task done Show me every change as a diff first. No edits until I say go." ↳

Codex tip: once GPT-6.1 Sol is your main model, stop running Astra on every turn put Astra on call as an architect agent GPT-6.1 Sol keeps writing the code Astra only gets spawned at three points: → before a plan: is this the right approach? → when the same error comes back: am I digging in the wrong place? → before "done": what did I miss? Astra reviews. Sol ships Jev engineering is the same move one layer down: the forks that need no thinker (which file, which tool, retry or stop) go to Jev in under half a second, and the big models only see the ones that split - the full tree > GPT-6.1 Sol on high runs the main session > explorer reads the code on Luna > worker edits and runs tests on Sol > researcher pulls the docs on Luna > all three on medium > Astra on call as the architect > auto_review checks every approval paste the tree and this prompt into Codex ↓ "Rebuild my Codex setup around this tree: 1. Check ~/.codex/agents and .codex/agents for agents that already fit explorer, worker and researcher. > Draft new TOML files only for missing roles > explorer and researcher on gpt-6-luna, worker on gpt-6.1-sol, all with model_reasoning_effort medium > Add an architect agent on gpt-6-astra, model_reasoning_effort high, whose only job is reviewing plans, repeated errors and finished work > Skip any that pin a different model and list them 2. In ~/.codex/config.toml set model to gpt-6.1-sol, model_reasoning_effort to high and approvals_reviewer to auto_review 3. Find anything that would override this (active profiles, flags in my shell aliases, agents.default_subagent_model). Report it, change nothing 4. Add one rule to AGENTS.md: spawn the architect before a large plan, when an error repeats, and before calling a long task done Show me every change as a diff first. No edits until I say go." ↳

delost

1,052,930 просмотров • 8 дней назад

Claude Code tip: once Opus 5.5 runs your main session, stop leaving Fable 5.1 on the bench put it on call with /advisor run /advisor fable Opus 5.5 keeps writing the code Fable 5.1 reads the whole session, every tool call included, and only speaks up at three moments: → before a plan: is this the right approach? → when the same error comes back: am I digging in the wrong place? → before "done": what did I miss? Fable 5.1 reviews. Opus 5.5 ships jev engineering is the same move one layer down: the forks that need no thinker (which file, which tool, retry or stop) go to jev in under half a second, and the big model only sees the ones that split - the full tree > Opus 5.5 on high runs the main session > explorer reads the code > worker edits and runs tests > researcher pulls the docs > all three on medium > Fable 5.1 on call as the advisor paste the tree and this prompt into Claude Code ↓ "Rebuild my Claude Code setup around this tree: 1. Check ~/.claude/agents and .claude/agents for subagents that already fit explorer, worker and researcher. > Draft new ones only for missing roles > Give each model: opus, effort: medium > Skip any that pin a different model and list them 2. Set the main session to high via effortLevel in ~/.claude/settings.json, and set advisorModel to fable 3. Find anything that keeps the advisor off (CLAUDE_CODE_DISABLE_ADVISOR_TOOL, DISABLE_TELEMETRY, any variable that stops feature-flag fetching) plus CLAUDE_CODE_EFFORT_LEVEL, which overrides subagent effort. Report them, change nothing 4. Add one rule to ~/.claude/CLAUDE.md: consult the advisor before a large plan, when an error repeats, and before calling a long task done Show me every change as a diff first. No edits until I say go." ↳

Claude Code tip: once Opus 5.5 runs your main session, stop leaving Fable 5.1 on the bench put it on call with /advisor run /advisor fable Opus 5.5 keeps writing the code Fable 5.1 reads the whole session, every tool call included, and only speaks up at three moments: → before a plan: is this the right approach? → when the same error comes back: am I digging in the wrong place? → before "done": what did I miss? Fable 5.1 reviews. Opus 5.5 ships jev engineering is the same move one layer down: the forks that need no thinker (which file, which tool, retry or stop) go to jev in under half a second, and the big model only sees the ones that split - the full tree > Opus 5.5 on high runs the main session > explorer reads the code > worker edits and runs tests > researcher pulls the docs > all three on medium > Fable 5.1 on call as the advisor paste the tree and this prompt into Claude Code ↓ "Rebuild my Claude Code setup around this tree: 1. Check ~/.claude/agents and .claude/agents for subagents that already fit explorer, worker and researcher. > Draft new ones only for missing roles > Give each model: opus, effort: medium > Skip any that pin a different model and list them 2. Set the main session to high via effortLevel in ~/.claude/settings.json, and set advisorModel to fable 3. Find anything that keeps the advisor off (CLAUDE_CODE_DISABLE_ADVISOR_TOOL, DISABLE_TELEMETRY, any variable that stops feature-flag fetching) plus CLAUDE_CODE_EFFORT_LEVEL, which overrides subagent effort. Report them, change nothing 4. Add one rule to ~/.claude/CLAUDE.md: consult the advisor before a large plan, when an error repeats, and before calling a long task done Show me every change as a diff first. No edits until I say go." ↳

Hanako

52,065 просмотров • 8 дней назад

Claude Code tip: once Opus 5.5 is your main model, stop leaving Fable 5.1 sitting idle put it on call with /advisor run /advisor fable Opus 5.5 keeps writing the code Fable 5.1 reads the full session, every tool call included, and only speaks up at three points: → before a plan: is this the right approach? → when the same error comes back: am I digging in the wrong place? → before "done": what did I miss? Fable 5.1 reviews. Opus 5.5 ships Jev engineering is the same move one layer down: the forks that need no thinker (which file, which tool, retry or stop) go to Jev in under half a second, and the big model only sees the ones that split - the full tree > Opus 5.5 on high runs the main session > explorer reads the code > worker edits and runs tests > researcher pulls the docs > all three on medium > Fable 5.1 on call as the advisor paste the tree and this prompt into Claude Code ↓ "Rebuild my Claude Code setup around this tree: 1. Check ~/.claude/agents and .claude/agents for subagents that already fit explorer, worker and researcher. > Draft new ones only for missing roles > Give each model: opus, effort: medium > Skip any that pin a different model and list them 2. Set the main session to high via effortLevel in ~/.claude/settings.json, and set advisorModel to fable 3. Find anything that keeps the advisor off (CLAUDE_CODE_DISABLE_ADVISOR_TOOL, DISABLE_TELEMETRY, any variable that stops feature-flag fetching) plus CLAUDE_CODE_EFFORT_LEVEL, which overrides subagent effort. Report them, change nothing 4. Add one rule to ~/.claude/CLAUDE.md: consult the advisor before a large plan, when an error repeats, and before calling a long task done Show me every change as a diff first. No edits until I say go." ↳

Claude Code tip: once Opus 5.5 is your main model, stop leaving Fable 5.1 sitting idle put it on call with /advisor run /advisor fable Opus 5.5 keeps writing the code Fable 5.1 reads the full session, every tool call included, and only speaks up at three points: → before a plan: is this the right approach? → when the same error comes back: am I digging in the wrong place? → before "done": what did I miss? Fable 5.1 reviews. Opus 5.5 ships Jev engineering is the same move one layer down: the forks that need no thinker (which file, which tool, retry or stop) go to Jev in under half a second, and the big model only sees the ones that split - the full tree > Opus 5.5 on high runs the main session > explorer reads the code > worker edits and runs tests > researcher pulls the docs > all three on medium > Fable 5.1 on call as the advisor paste the tree and this prompt into Claude Code ↓ "Rebuild my Claude Code setup around this tree: 1. Check ~/.claude/agents and .claude/agents for subagents that already fit explorer, worker and researcher. > Draft new ones only for missing roles > Give each model: opus, effort: medium > Skip any that pin a different model and list them 2. Set the main session to high via effortLevel in ~/.claude/settings.json, and set advisorModel to fable 3. Find anything that keeps the advisor off (CLAUDE_CODE_DISABLE_ADVISOR_TOOL, DISABLE_TELEMETRY, any variable that stops feature-flag fetching) plus CLAUDE_CODE_EFFORT_LEVEL, which overrides subagent effort. Report them, change nothing 4. Add one rule to ~/.claude/CLAUDE.md: consult the advisor before a large plan, when an error repeats, and before calling a long task done Show me every change as a diff first. No edits until I say go." ↳

delost

693,243 просмотров • 10 дней назад

Official Anthropic tip for Claude Code: stop burning Opus 5.5 on work Sonnet 5.5 can do, while Fable 5.1 sits idle hand the grunt work to Sonnet 5.5 subagents and put Fable 5.1 on call run /advisor fable Opus 5.5 plans and merges Sonnet 5.5 subagents read, edit and run the tests Fable 5.1 reads the full session and only speaks up at three points: → before a plan: is this the right approach? → when the same error comes back: am I digging in the wrong place? → before "done": what did I miss? Sonnet 5.5 builds. Fable 5.1 reviews. Opus 5.5 ships Jev engineering is the same move one layer down: the forks that need no thinker (which file, which tool, retry or stop) go to Jev in under half a second, and the big models only see the ones that split - the full tree > Opus 5.5 on high runs the main session > explorer reads the code on Sonnet 5.5 > worker edits and runs tests on Sonnet 5.5 > researcher pulls the docs on Sonnet 5.5 > all three on medium > Fable 5.1 on call for main and every subagent paste the tree and this prompt into Claude Code ↓ "Rebuild my Claude Code setup around this tree: 1. Check ~/.claude/agents and .claude/agents for subagents that already fit explorer, worker and researcher. > Draft new ones only for missing roles > Give each model: sonnet, effort: medium > Skip any that pin a different model and list them 2. Set the main session to high via effortLevel in ~/.claude/settings.json, and set advisorModel to fable 3. Find anything that keeps the advisor off (CLAUDE_CODE_DISABLE_ADVISOR_TOOL, DISABLE_TELEMETRY) plus CLAUDE_CODE_EFFORT_LEVEL, which overrides subagent effort. Report them, change nothing 4. Add one rule to ~/.claude/CLAUDE.md: consult the advisor before a large plan, when an error repeats, and before calling a long task done Show me every change as a diff first. No edits until I say go." ↳

Official Anthropic tip for Claude Code: stop burning Opus 5.5 on work Sonnet 5.5 can do, while Fable 5.1 sits idle hand the grunt work to Sonnet 5.5 subagents and put Fable 5.1 on call run /advisor fable Opus 5.5 plans and merges Sonnet 5.5 subagents read, edit and run the tests Fable 5.1 reads the full session and only speaks up at three points: → before a plan: is this the right approach? → when the same error comes back: am I digging in the wrong place? → before "done": what did I miss? Sonnet 5.5 builds. Fable 5.1 reviews. Opus 5.5 ships Jev engineering is the same move one layer down: the forks that need no thinker (which file, which tool, retry or stop) go to Jev in under half a second, and the big models only see the ones that split - the full tree > Opus 5.5 on high runs the main session > explorer reads the code on Sonnet 5.5 > worker edits and runs tests on Sonnet 5.5 > researcher pulls the docs on Sonnet 5.5 > all three on medium > Fable 5.1 on call for main and every subagent paste the tree and this prompt into Claude Code ↓ "Rebuild my Claude Code setup around this tree: 1. Check ~/.claude/agents and .claude/agents for subagents that already fit explorer, worker and researcher. > Draft new ones only for missing roles > Give each model: sonnet, effort: medium > Skip any that pin a different model and list them 2. Set the main session to high via effortLevel in ~/.claude/settings.json, and set advisorModel to fable 3. Find anything that keeps the advisor off (CLAUDE_CODE_DISABLE_ADVISOR_TOOL, DISABLE_TELEMETRY) plus CLAUDE_CODE_EFFORT_LEVEL, which overrides subagent effort. Report them, change nothing 4. Add one rule to ~/.claude/CLAUDE.md: consult the advisor before a large plan, when an error repeats, and before calling a long task done Show me every change as a diff first. No edits until I say go." ↳

delost

43,704 просмотров • 6 дней назад

Claude Code tip, and it's absolute free f*cking gold: run Opus 5.5, Sonnet 5.5 and Fable 5.1 as one team and stop burning Opus tokens on routine work the setup in one line: plan on high, delegate on medium, keep Fable on call • who does what > Opus 5.5 on high - plans and ships the code > Sonnet 5.5 on medium - explorer reads code, worker edits and runs tests, researcher pulls docs > Fable 5.1 via /advisor fable - reads the whole session and speaks up only when it matters • when Fable 5.1 steps in -> before a plan: is this the right approach? -> when an error repeats: am I digging in the wrong place? -> before "done": what did I miss? Jev engineering takes it one layer lower: which file, which tool, retry or stop all go to Jev in under half a second, so the big models only see the real forks paste this into Claude Code ↓ "Rebuild my Claude Code setup: 1. Find subagents in ~/.claude/agents and .claude/agents that fit explorer, worker and researcher. Draft only the missing ones. Set each to model: sonnet, effort: medium. List any that pin a different model and leave them 2. In ~/.claude/settings.json set effortLevel to high and advisorModel to fable. 3. Report anything that disables the advisor (CLAUDE_CODE_DISABLE_ADVISOR_TOOL, DISABLE_TELEMETRY, flag-fetching blockers) and CLAUDE_CODE_EFFORT_LEVEL. Change nothing. 4. Add to ~/.claude/CLAUDE.md: consult the advisor before a large plan, when an error repeats, and before calling a long task done. Show every change as a diff. No edits until I say go." ↳

Claude Code tip, and it's absolute free f*cking gold: run Opus 5.5, Sonnet 5.5 and Fable 5.1 as one team and stop burning Opus tokens on routine work the setup in one line: plan on high, delegate on medium, keep Fable on call • who does what > Opus 5.5 on high - plans and ships the code > Sonnet 5.5 on medium - explorer reads code, worker edits and runs tests, researcher pulls docs > Fable 5.1 via /advisor fable - reads the whole session and speaks up only when it matters • when Fable 5.1 steps in -> before a plan: is this the right approach? -> when an error repeats: am I digging in the wrong place? -> before "done": what did I miss? Jev engineering takes it one layer lower: which file, which tool, retry or stop all go to Jev in under half a second, so the big models only see the real forks paste this into Claude Code ↓ "Rebuild my Claude Code setup: 1. Find subagents in ~/.claude/agents and .claude/agents that fit explorer, worker and researcher. Draft only the missing ones. Set each to model: sonnet, effort: medium. List any that pin a different model and leave them 2. In ~/.claude/settings.json set effortLevel to high and advisorModel to fable. 3. Report anything that disables the advisor (CLAUDE_CODE_DISABLE_ADVISOR_TOOL, DISABLE_TELEMETRY, flag-fetching blockers) and CLAUDE_CODE_EFFORT_LEVEL. Change nothing. 4. Add to ~/.claude/CLAUDE.md: consult the advisor before a large plan, when an error repeats, and before calling a long task done. Show every change as a diff. No edits until I say go." ↳

Mr. Buzzoni

142,491 просмотров • 8 дней назад

this is straight f*cking gold for anyone on Claude Code you already pay for Fable 5.1, and while Opus 5.5 does all the work it just sits there one command puts it on your session as a senior reviewer: /advisor fable Opus 5.5 keeps writing the code Fable 5.1 reads the whole session, every tool call included, and speaks up at three moments only: > before a plan: is this the right approach? > when the same error comes back: am I digging in the wrong place? > before "done": what did I miss? Fable 5.1 reviews. Opus 5.5 ships Jev engineering does the same thing one layer down: forks that need no thinker (which file, which tool, retry or stop) go to Jev in under half a second, and the big model only sees the ones that actually split • the full tree > Opus 5.5 on high runs the main session > explorer reads the code > worker edits and runs tests > researcher pulls the docs > all three on medium > Fable 5.1 on call as the advisor paste the tree and this prompt into Claude Code ↓ "Rebuild my Claude Code setup around this tree: 1. Check ~/.claude/agents and .claude/agents for subagents that already fit explorer, worker and researcher. Draft new ones only for missing roles. Give each model: opus, effort: medium. Skip any that pin a different model and list them. 2. Set the main session to high via effortLevel in ~/.claude/settings.json, and set advisorModel to fable. 3. Find anything that keeps the advisor off (CLAUDE_CODE_DISABLE_ADVISOR_TOOL, DISABLE_TELEMETRY, any variable that stops feature-flag fetching) plus CLAUDE_CODE_EFFORT_LEVEL, which overrides subagent effort. Report them, change nothing. 4. Add one rule to ~/.claude/CLAUDE.md: consult the advisor before a large plan, when an error repeats, and before calling a long task done. Show me every change as a diff first. No edits until I say go" ↳

this is straight f*cking gold for anyone on Claude Code you already pay for Fable 5.1, and while Opus 5.5 does all the work it just sits there one command puts it on your session as a senior reviewer: /advisor fable Opus 5.5 keeps writing the code Fable 5.1 reads the whole session, every tool call included, and speaks up at three moments only: > before a plan: is this the right approach? > when the same error comes back: am I digging in the wrong place? > before "done": what did I miss? Fable 5.1 reviews. Opus 5.5 ships Jev engineering does the same thing one layer down: forks that need no thinker (which file, which tool, retry or stop) go to Jev in under half a second, and the big model only sees the ones that actually split • the full tree > Opus 5.5 on high runs the main session > explorer reads the code > worker edits and runs tests > researcher pulls the docs > all three on medium > Fable 5.1 on call as the advisor paste the tree and this prompt into Claude Code ↓ "Rebuild my Claude Code setup around this tree: 1. Check ~/.claude/agents and .claude/agents for subagents that already fit explorer, worker and researcher. Draft new ones only for missing roles. Give each model: opus, effort: medium. Skip any that pin a different model and list them. 2. Set the main session to high via effortLevel in ~/.claude/settings.json, and set advisorModel to fable. 3. Find anything that keeps the advisor off (CLAUDE_CODE_DISABLE_ADVISOR_TOOL, DISABLE_TELEMETRY, any variable that stops feature-flag fetching) plus CLAUDE_CODE_EFFORT_LEVEL, which overrides subagent effort. Report them, change nothing. 4. Add one rule to ~/.claude/CLAUDE.md: consult the advisor before a large plan, when an error repeats, and before calling a long task done. Show me every change as a diff first. No edits until I say go" ↳

Annatar.md

74,132 просмотров • 9 дней назад

Claude Code tip: keep Opus 5.5 as your main model, but stop paying Opus prices for your subagents move them to Sonnet 5.5 Opus 5.5 plans and decides Sonnet 5.5 subagents do the heavy reading, editing and testing at half the price ($2 / $10 vs $4 / $20 per 1M tokens) Fable 5.1 stays on call with /advisor and only speaks up at three points: → before a plan: is this the right approach? → when the same error comes back: am I digging in the wrong place? → before "done": what did I miss? Opus thinks. Sonnet does. Fable checks Jev engineering is the same move one layer down: the forks that need no thinker (which file, which tool, retry or stop) go to Jev in under half a second, and the big models only see the ones that split - the full tree > Opus 5.5 on high runs the main session > explorer reads the code > worker edits and runs tests > researcher pulls the docs > all three on Sonnet 5.5, medium > Fable 5.1 on call as the advisor paste the tree and this prompt into Claude Code ↓ "Rebuild my Claude Code setup around this tree: 1. Check ~/.claude/agents and .claude/agents for subagents that already fit explorer, worker and researcher. > Draft new ones only for missing roles > Give each model: claude-sonnet-5-5, effort: medium > List any that pin a different model before changing them 2. Keep the main session on Opus, set effortLevel to high in ~/.claude/settings.json and advisorModel to fable 3. Find anything that keeps the advisor off (CLAUDE_CODE_DISABLE_ADVISOR_TOOL, DISABLE_TELEMETRY, any variable that stops feature-flag fetching) plus CLAUDE_CODE_EFFORT_LEVEL, which overrides subagent effort. Report them, change nothing 4. Add one rule to ~/.claude/CLAUDE.md: consult the advisor before a large plan, when an error repeats, and before calling a long task done Show me every change as a diff first. No edits until I say go." ↳

Claude Code tip: keep Opus 5.5 as your main model, but stop paying Opus prices for your subagents move them to Sonnet 5.5 Opus 5.5 plans and decides Sonnet 5.5 subagents do the heavy reading, editing and testing at half the price ($2 / $10 vs $4 / $20 per 1M tokens) Fable 5.1 stays on call with /advisor and only speaks up at three points: → before a plan: is this the right approach? → when the same error comes back: am I digging in the wrong place? → before "done": what did I miss? Opus thinks. Sonnet does. Fable checks Jev engineering is the same move one layer down: the forks that need no thinker (which file, which tool, retry or stop) go to Jev in under half a second, and the big models only see the ones that split - the full tree > Opus 5.5 on high runs the main session > explorer reads the code > worker edits and runs tests > researcher pulls the docs > all three on Sonnet 5.5, medium > Fable 5.1 on call as the advisor paste the tree and this prompt into Claude Code ↓ "Rebuild my Claude Code setup around this tree: 1. Check ~/.claude/agents and .claude/agents for subagents that already fit explorer, worker and researcher. > Draft new ones only for missing roles > Give each model: claude-sonnet-5-5, effort: medium > List any that pin a different model before changing them 2. Keep the main session on Opus, set effortLevel to high in ~/.claude/settings.json and advisorModel to fable 3. Find anything that keeps the advisor off (CLAUDE_CODE_DISABLE_ADVISOR_TOOL, DISABLE_TELEMETRY, any variable that stops feature-flag fetching) plus CLAUDE_CODE_EFFORT_LEVEL, which overrides subagent effort. Report them, change nothing 4. Add one rule to ~/.claude/CLAUDE.md: consult the advisor before a large plan, when an error repeats, and before calling a long task done Show me every change as a diff first. No edits until I say go." ↳

delost

27,459 просмотров • 7 дней назад

Let's keep benchmarking with the Night train this time, with GPT-6 Sol and GPT-6 Luna, so here are all four! 🚀 I gave each model the exact same prompt: “Build a Night train.” •Opus 5.5 • GPT-6 Astra • GPT-6 Sol • GPT-6 Luna Something that really surprised me: GPT-6 Sol produced almost the exact same rocket launch as Opus 5.5! The colors are slightly different, but the overall result is remarkably similar. For this prompt, I’d even put Sol ahead of Astra. I’m seriously impressed by Sol, especially at half the API price of Opus 5.5! 🤯 I’m starting to use this approach in my own workflow. I kept one Codex subscription so I can run a bunch of Sol sub-agents while keeping my main agent on Astra. Sol is so cheap for what it can do! Knowing when to switch models based on the task, the quality you need, and the cost is becoming an essential skill in this new AI era.

Let's keep benchmarking with the Night train this time, with GPT-6 Sol and GPT-6 Luna, so here are all four! 🚀 I gave each model the exact same prompt: “Build a Night train.” •Opus 5.5 • GPT-6 Astra • GPT-6 Sol • GPT-6 Luna Something that really surprised me: GPT-6 Sol produced almost the exact same rocket launch as Opus 5.5! The colors are slightly different, but the overall result is remarkably similar. For this prompt, I’d even put Sol ahead of Astra. I’m seriously impressed by Sol, especially at half the API price of Opus 5.5! 🤯 I’m starting to use this approach in my own workflow. I kept one Codex subscription so I can run a bunch of Sol sub-agents while keeping my main agent on Astra. Sol is so cheap for what it can do! Knowing when to switch models based on the task, the quality you need, and the cost is becoming an essential skill in this new AI era.

Tony

112,633 просмотров • 14 дней назад

Claude Code tip: once Opus 5.5 is your main model, stop letting your Fable 5.1 quota go to waste put it on call with /advisor run /advisor fable Opus 5.5 keeps doing the work Fable 5.1 sits on the sidelines, reads the whole session, and steps in at three moments: → before a plan: is this right? → when the same error comes back: am I going the wrong way? → before "done": did I miss anything? Fable 5.1 advises. Opus 5.5 writes the code the same idea sits under Jev engineering: the expensive model stops weighing in on every step and only gets called at the moments that change the outcome • the full setup > Opus 5.5 on high runs the main session > subagent one reads code > subagent two edits and runs tests > subagent three looks up docs > all three on medium > Fable 5.1 on call hand the tree and this prompt to Claude Code 👇 "Set up my Claude Code to match this tree: 1. Reuse fitting subagents from ~/.claude/agents and .claude/agents. > Propose new ones only for missing roles > Set each to model: opus, effort: medium > Leave any that set a different model alone and list them 2. Set main session effort to high via effortLevel in ~/.claude/settings.json 3. Check for env vars that disable the advisor (CLAUDE_CODE_DISABLE_ADVISOR_TOOL, DISABLE_TELEMETRY, anything that stops flag fetching) and CLAUDE_CODE_EFFORT_LEVEL, which overrides subagent effort. Report them, don't change them 4. Add a rule to ~/.claude/CLAUDE.md: ask the advisor before a big plan, when an error repeats, and before calling a long task done Show me the changes first. Don't edit files yet." ↳

Claude Code tip: once Opus 5.5 is your main model, stop letting your Fable 5.1 quota go to waste put it on call with /advisor run /advisor fable Opus 5.5 keeps doing the work Fable 5.1 sits on the sidelines, reads the whole session, and steps in at three moments: → before a plan: is this right? → when the same error comes back: am I going the wrong way? → before "done": did I miss anything? Fable 5.1 advises. Opus 5.5 writes the code the same idea sits under Jev engineering: the expensive model stops weighing in on every step and only gets called at the moments that change the outcome • the full setup > Opus 5.5 on high runs the main session > subagent one reads code > subagent two edits and runs tests > subagent three looks up docs > all three on medium > Fable 5.1 on call hand the tree and this prompt to Claude Code 👇 "Set up my Claude Code to match this tree: 1. Reuse fitting subagents from ~/.claude/agents and .claude/agents. > Propose new ones only for missing roles > Set each to model: opus, effort: medium > Leave any that set a different model alone and list them 2. Set main session effort to high via effortLevel in ~/.claude/settings.json 3. Check for env vars that disable the advisor (CLAUDE_CODE_DISABLE_ADVISOR_TOOL, DISABLE_TELEMETRY, anything that stops flag fetching) and CLAUDE_CODE_EFFORT_LEVEL, which overrides subagent effort. Report them, don't change them 4. Add a rule to ~/.claude/CLAUDE.md: ask the advisor before a big plan, when an error repeats, and before calling a long task done Show me the changes first. Don't edit files yet." ↳

Mr. Buzzoni

324,448 просмотров • 10 дней назад

i recreated this with GPT 5.6 Sol & it costed me ~$5 only & 2 prompts >GPT 5.6 Sol Ultra as the main agent, admin & orchestrator >GPT 5.6 Luna Max as sub-agents >used the Codex app >used about 20% of my weekly limit on $100 plan ($100/4 * 20%) some bugs, and improvements would take another prompt but pretty good for $5!

i recreated this with GPT 5.6 Sol & it costed me ~$5 only & 2 prompts >GPT 5.6 Sol Ultra as the main agent, admin & orchestrator >GPT 5.6 Luna Max as sub-agents >used the Codex app >used about 20% of my weekly limit on $100 plan ($100/4 * 20%) some bugs, and improvements would take another prompt but pretty good for $5!

anul agarwal

16,535 просмотров • 2 месяцев назад

This is f*cking insane. This tip saved me thousands of dollars. run Opus 5.5, Sonnet 5.5, and Fable 5.1 together, and stop burning Opus on work it was never needed for. the whole idea in one line: the strong model plans, the mid-tier model executes, Fable stays quiet until it's actually needed. roles, broken down: Opus 5.5, high effort, owns the plan and ships the final code Sonnet 5.5, medium effort, splits into explorer (reads the codebase), worker (edits files, runs tests), researcher (pulls docs) Fable 5.1, called through /advisor fable, reads everything happening in the session but stays silent unless something's actually wrong three moments where Fable speaks: → a plan goes out: is this actually the right call? → the same failure shows up again: is the search going nowhere? → the task gets marked finished: did something get skipped? Jev engineering does the same thing one level down. the forks that don't need real thought, which file, which tool, keep going or stop, go straight to Jev and come back in under half a second. the big models only ever see the forks that genuinely need a decision. anyone still running one model for everything is paying Opus prices to decide whether a file exists. drop this into Claude Code: "Rebuild my Claude Code setup around this structure: Look through ~/.claude/agents and .claude/agents for subagents already covering explorer, worker, and researcher. Only create new ones for roles that are missing. Set model: sonnet, effort: medium on each. If an existing subagent is locked to a different model, leave it as is and just list it. In ~/.claude/settings.json, set effortLevel to high and advisorModel to fable. Check for anything disabling the advisor, CLAUDE_CODE_DISABLE_ADVISOR_TOOL, DISABLE_TELEMETRY, or anything blocking feature-flag fetches, plus CLAUDE_CODE_EFFORT_LEVEL, which can override subagent effort settings. Report what you find. Don't change any of it yet. Add one line to ~/.claude/CLAUDE.md: check in with the advisor before a big plan, when the same error shows up twice, and before marking a long task done. Show every change as a diff first. Wait for my go-ahead before touching anything."

This is f*cking insane. This tip saved me thousands of dollars. run Opus 5.5, Sonnet 5.5, and Fable 5.1 together, and stop burning Opus on work it was never needed for. the whole idea in one line: the strong model plans, the mid-tier model executes, Fable stays quiet until it's actually needed. roles, broken down: Opus 5.5, high effort, owns the plan and ships the final code Sonnet 5.5, medium effort, splits into explorer (reads the codebase), worker (edits files, runs tests), researcher (pulls docs) Fable 5.1, called through /advisor fable, reads everything happening in the session but stays silent unless something's actually wrong three moments where Fable speaks: → a plan goes out: is this actually the right call? → the same failure shows up again: is the search going nowhere? → the task gets marked finished: did something get skipped? Jev engineering does the same thing one level down. the forks that don't need real thought, which file, which tool, keep going or stop, go straight to Jev and come back in under half a second. the big models only ever see the forks that genuinely need a decision. anyone still running one model for everything is paying Opus prices to decide whether a file exists. drop this into Claude Code: "Rebuild my Claude Code setup around this structure: Look through ~/.claude/agents and .claude/agents for subagents already covering explorer, worker, and researcher. Only create new ones for roles that are missing. Set model: sonnet, effort: medium on each. If an existing subagent is locked to a different model, leave it as is and just list it. In ~/.claude/settings.json, set effortLevel to high and advisorModel to fable. Check for anything disabling the advisor, CLAUDE_CODE_DISABLE_ADVISOR_TOOL, DISABLE_TELEMETRY, or anything blocking feature-flag fetches, plus CLAUDE_CODE_EFFORT_LEVEL, which can override subagent effort settings. Report what you find. Don't change any of it yet. Add one line to ~/.claude/CLAUDE.md: check in with the advisor before a big plan, when the same error shows up twice, and before marking a long task done. Show every change as a diff first. Wait for my go-ahead before touching anything."

rvaniaaa

250,263 просмотров • 6 дней назад

This workflow will save you thousands with Claude. Run Opus 5.5, Sonnet 5.5, Haiku 5.5, and Fable 5.1 together, and stop spending Opus tokens on work that doesn't need Opus. The entire idea in one line: Opus plans, Sonnet edits, Haiku reads, Fable reviews at decision points. Roles, broken down: - Opus 5.5, high effort, owns the plan and reviews the final code - Sonnet 5.5, medium effort, is the worker: edits files, runs tests - Haiku 5.5, low effort, splits into explorer (searches and reads the codebase) and researcher (pulls docs). it's the first Haiku with an effort setting - Fable 5.1, set with /advisor fable. Opus calls it at decision points, and it gets the full transcript each time Three moments Opus tends to call it: → before committing to a plan: is this the right approach? → the same error shows up again: is this going nowhere? → before marking the task done: did something get skipped? Why Haiku only reads: Anthropic's launch post says Sonnet 5.5 and Opus 5.5 are still the better choice for complex agentic coding (Terminal-Bench 4.0: 39.2% for Haiku 5.5, 70.6% for Sonnet 5.5) and that Haiku 5.5 fits narrowly scoped subagent work. so it gets the lookups, not the edits. Anyone still running one model for everything is paying $4 per million input tokens to check whether a file exists. Haiku 5.5 does it for $0.10. Drop this into Claude Code 👇 "Rebuild my Claude Code setup around this structure: Confirm Claude Code is v2.1.293 or later, so the haiku alias resolves to Haiku 5.5. If it isn't, stop and tell me to run claude update. Look through ~/.claude/agents and .claude/agents for subagents already covering explorer, worker, and researcher. Only create new ones for roles that are missing. Set model: haiku, effort: low on explorer and researcher, with no Edit or Write tools. Set model: sonnet, effort: medium on worker. If an existing subagent is locked to a different model, leave it as is and just list it. Name the explorer subagent Explore so it overrides the built-in one, which otherwise runs on my main model. In ~/.claude/settings.json, set advisorModel to fable, and set effortLevel to high for claude-opus-5-5 under modelSettings. A top-level effortLevel in user settings doesn't apply to Opus 5.5. Check for anything disabling the advisor: CLAUDE_CODE_DISABLE_ADVISOR_TOOL, DISABLE_TELEMETRY, or anything blocking feature-flag fetches. Also check CLAUDE_CODE_EFFORT_LEVEL, which overrides subagent effort settings, and CLAUDE_CODE_SUBAGENT_MODEL_FORCE, which makes Claude Code ignore subagent model fields. Report what you find. Don't change any of it yet. Add one line to ~/.claude/CLAUDE.md: consult the advisor before a big plan, when the same error shows up twice, and before marking a long task done. Show every change as a diff first. Wait for my go-ahead before touching anything."

This workflow will save you thousands with Claude. Run Opus 5.5, Sonnet 5.5, Haiku 5.5, and Fable 5.1 together, and stop spending Opus tokens on work that doesn't need Opus. The entire idea in one line: Opus plans, Sonnet edits, Haiku reads, Fable reviews at decision points. Roles, broken down: - Opus 5.5, high effort, owns the plan and reviews the final code - Sonnet 5.5, medium effort, is the worker: edits files, runs tests - Haiku 5.5, low effort, splits into explorer (searches and reads the codebase) and researcher (pulls docs). it's the first Haiku with an effort setting - Fable 5.1, set with /advisor fable. Opus calls it at decision points, and it gets the full transcript each time Three moments Opus tends to call it: → before committing to a plan: is this the right approach? → the same error shows up again: is this going nowhere? → before marking the task done: did something get skipped? Why Haiku only reads: Anthropic's launch post says Sonnet 5.5 and Opus 5.5 are still the better choice for complex agentic coding (Terminal-Bench 4.0: 39.2% for Haiku 5.5, 70.6% for Sonnet 5.5) and that Haiku 5.5 fits narrowly scoped subagent work. so it gets the lookups, not the edits. Anyone still running one model for everything is paying $4 per million input tokens to check whether a file exists. Haiku 5.5 does it for $0.10. Drop this into Claude Code 👇 "Rebuild my Claude Code setup around this structure: Confirm Claude Code is v2.1.293 or later, so the haiku alias resolves to Haiku 5.5. If it isn't, stop and tell me to run claude update. Look through ~/.claude/agents and .claude/agents for subagents already covering explorer, worker, and researcher. Only create new ones for roles that are missing. Set model: haiku, effort: low on explorer and researcher, with no Edit or Write tools. Set model: sonnet, effort: medium on worker. If an existing subagent is locked to a different model, leave it as is and just list it. Name the explorer subagent Explore so it overrides the built-in one, which otherwise runs on my main model. In ~/.claude/settings.json, set advisorModel to fable, and set effortLevel to high for claude-opus-5-5 under modelSettings. A top-level effortLevel in user settings doesn't apply to Opus 5.5. Check for anything disabling the advisor: CLAUDE_CODE_DISABLE_ADVISOR_TOOL, DISABLE_TELEMETRY, or anything blocking feature-flag fetches. Also check CLAUDE_CODE_EFFORT_LEVEL, which overrides subagent effort settings, and CLAUDE_CODE_SUBAGENT_MODEL_FORCE, which makes Claude Code ignore subagent model fields. Report what you find. Don't change any of it yet. Add one line to ~/.claude/CLAUDE.md: consult the advisor before a big plan, when the same error shows up twice, and before marking a long task done. Show every change as a diff first. Wait for my go-ahead before touching anything."

Alvaro Cintas

51,598 просмотров • 1 день назад

I don't understand why everyone isn't doing this yet. Anthropic's own Claude Code docs show how to run a whole team of Claudes, while Opus 5.5 only touches the plan and the merge the whole idea: agent teams in Claude Code one lead, separate teammates in their own context windows, one shared task list, and they message each other directly the lead: Opus 5.5 on high, splits the work, writes the tasks, merges at the end the builders: Sonnet 5.5, one owns client/, one owns api/, never the same file the adversary: Fable 5.1, never writes code, only shows up at three points: → before an interface locks: do both sides agree on the contract? → when a test fails twice: is it fixed or just hidden? → before a task is marked done: what breaks it? Sonnet 5.5 builds. Fable 5.1 attacks. Opus 5.5 merges Jev engineering is the same move one layer down: the forks that need no thinker (which file, which tool, retry or stop) go to Jev in under half a second, and the team only argues about the ones that split turn it on, then start the team in plain English: "Spawn three teammates: ux and backend on Sonnet, an adversary on Fable" - the full team > Opus 5.5 on high leads the session > ux on Sonnet 5.5, owns client/ > backend on Sonnet 5.5, owns api/ > adversary on Fable 5.1, owns nothing, reviews everything > shared task list with file locking, direct messages, no lead in the middle paste the team and this prompt into Claude Code ↓ "Set up agent teams for this repo: 1. In ~/.claude/settings.json add CLAUDE_CODE_EXPERIMENTAL_AGENT_TEAMS=1 under env and set effortLevel to high 2. In ~/.claude/agents, draft three subagent definitions for the teammates > ux and backend with model: sonnet, each limited to its own folder > adversary with model: fable and read-only tools, whose only job is attacking contracts, repeated test failures and done claims > Skip any that already exist and list them 3. Add a TaskCompleted hook that blocks completion until the adversary signs off, and one rule to CLAUDE.md: no two teammates edit the same file 4. Find anything that would override this (CLAUDE_CODE_SUBAGENT_MODEL, CLAUDE_CODE_SUBAGENT_MODEL_FORCE, CLAUDE_CODE_EFFORT_LEVEL). Report it, change nothing Show me every change as a diff first. No edits until I say go." ↳

I don't understand why everyone isn't doing this yet. Anthropic's own Claude Code docs show how to run a whole team of Claudes, while Opus 5.5 only touches the plan and the merge the whole idea: agent teams in Claude Code one lead, separate teammates in their own context windows, one shared task list, and they message each other directly the lead: Opus 5.5 on high, splits the work, writes the tasks, merges at the end the builders: Sonnet 5.5, one owns client/, one owns api/, never the same file the adversary: Fable 5.1, never writes code, only shows up at three points: → before an interface locks: do both sides agree on the contract? → when a test fails twice: is it fixed or just hidden? → before a task is marked done: what breaks it? Sonnet 5.5 builds. Fable 5.1 attacks. Opus 5.5 merges Jev engineering is the same move one layer down: the forks that need no thinker (which file, which tool, retry or stop) go to Jev in under half a second, and the team only argues about the ones that split turn it on, then start the team in plain English: "Spawn three teammates: ux and backend on Sonnet, an adversary on Fable" - the full team > Opus 5.5 on high leads the session > ux on Sonnet 5.5, owns client/ > backend on Sonnet 5.5, owns api/ > adversary on Fable 5.1, owns nothing, reviews everything > shared task list with file locking, direct messages, no lead in the middle paste the team and this prompt into Claude Code ↓ "Set up agent teams for this repo: 1. In ~/.claude/settings.json add CLAUDE_CODE_EXPERIMENTAL_AGENT_TEAMS=1 under env and set effortLevel to high 2. In ~/.claude/agents, draft three subagent definitions for the teammates > ux and backend with model: sonnet, each limited to its own folder > adversary with model: fable and read-only tools, whose only job is attacking contracts, repeated test failures and done claims > Skip any that already exist and list them 3. Add a TaskCompleted hook that blocks completion until the adversary signs off, and one rule to CLAUDE.md: no two teammates edit the same file 4. Find anything that would override this (CLAUDE_CODE_SUBAGENT_MODEL, CLAUDE_CODE_SUBAGENT_MODEL_FORCE, CLAUDE_CODE_EFFORT_LEVEL). Report it, change nothing Show me every change as a diff first. No edits until I say go." ↳

delost

69,178 просмотров • 4 дней назад

wow... GPT 5.6 Sol Passed the Replit Benchmark. In one prompt 5.6 on Codex created a full Replit clone with DB, Sandboxes, and an agent that builds and edits full web apps. Only Fable and GPT 5.6 have passed this benchmark. 5.6 is much better at designing iOS apps than 5.5 as well.

wow... GPT 5.6 Sol Passed the Replit Benchmark. In one prompt 5.6 on Codex created a full Replit clone with DB, Sandboxes, and an agent that builds and edits full web apps. Only Fable and GPT 5.6 have passed this benchmark. 5.6 is much better at designing iOS apps than 5.5 as well.

Riley Brown

123,642 просмотров • 3 месяцев назад

Codex CLI will have MULTI-AGENT support in 0.123.0 Here's how it will work: → 1. Add `multi_agent=true` in ~/codex/config.toml under [features] → 2. Toggle with `/experimental` → 3. Three built-in agents (default, explorer, worker) → 4. Define your own agents ``` [agents.researcher] description = "Research-focused role." config_file = "~/.codex/agents/researcher.toml" model = "gpt-5.3-codex" model_reasoning_effort = "high" web_search = "live" sandbox_mode = "read-only" developer_instructions = """ You are the researcher agent. - Gather evidence from primary sources. - Return links, findings, and uncertainty. - Do not edit files. """ ``` → 5. Run more agent threads per session (default: 6) ``` [agents] max_threads = 6 Notes: → OAI released 0.122.0 - but rolled it back! → I built it from source (so you don't have)

Codex CLI will have MULTI-AGENT support in 0.123.0 Here's how it will work: → 1. Add `multi_agent=true` in ~/codex/config.toml under [features] → 2. Toggle with `/experimental` → 3. Three built-in agents (default, explorer, worker) → 4. Define your own agents ``` [agents.researcher] description = "Research-focused role." config_file = "~/.codex/agents/researcher.toml" model = "gpt-5.3-codex" model_reasoning_effort = "high" web_search = "live" sandbox_mode = "read-only" developer_instructions = """ You are the researcher agent. - Gather evidence from primary sources. - Return links, findings, and uncertainty. - Do not edit files. """ ``` → 5. Run more agent threads per session (default: 6) ``` [agents] max_threads = 6 Notes: → OAI released 0.122.0 - but rolled it back! → I built it from source (so you don't have)

Chong-U

36,205 просмотров • 7 месяцев назад

OpenAI just shipped the biggest release in their history. I got in before launch. GPT-5.6 family : Sol, Terra, Luna. A new super app that merges @ChatGPTapp and Codex. Three modes: Chat, Work, Code. I sat down with Wulfie Bain from OpenAI and we built a full startup on camera. Pitch deck, working web app, computer-use agents finding and fixing bugs live, and an autonomous 16-hour overnight run. The idea that changes everything: stop writing prompts. Start writing loops. Give the agent a goal and a way to check its own work. That's how a model runs overnight and comes back finished. We also answer the real questions what you build that OpenAI won't kill, tokens vs engineers, and why India wins in this era. Coder or not watch this one.

OpenAI just shipped the biggest release in their history. I got in before launch. GPT-5.6 family : Sol, Terra, Luna. A new super app that merges @ChatGPTapp and Codex. Three modes: Chat, Work, Code. I sat down with Wulfie Bain from OpenAI and we built a full startup on camera. Pitch deck, working web app, computer-use agents finding and fixing bugs live, and an autonomous 16-hour overnight run. The idea that changes everything: stop writing prompts. Start writing loops. Give the agent a goal and a way to check its own work. That's how a model runs overnight and comes back finished. We also answer the real questions what you build that OpenAI won't kill, tokens vs engineers, and why India wins in this era. Coder or not watch this one.

Vaibhav Sisinty

11,713 просмотров • 3 месяцев назад

OpenAI. said. this. publicly. their own engineers just proved one idea on themselves, in writing: stop telling AI what's wrong. hand it the whole broken thing and let it find out they gave GPT-6 Astra a slow test build of their own coding tool. one cause found, a memory bottleneck, one allocator swapped, every turn 25× faster this is GPT-6 Astra, the layer that fixes the cause instead of the symptom, $0 on top of the ChatGPT plan you already pay for: - open ChatGPT or Codex, pick GPT-6 Astra, hand it the whole thing: the folder, the file that takes a minute to open. it works in apps with no API and reads your screen - type one sentence: find the one cause, prove it, fix it, do not patch around it - leave the room. it asks without stopping, keeps working on what does not need your answer, waits only where the answer changes the outcome - keep it in one Codex session with the experimental notes setting on: it remembers across context windows why an earlier fix failed - expect the first pass to land: handed a program with no source, it worked out how it runs 88% of the time first try, 99.2% within four you never find out what was broken. it gets fixed anyway the catch is on the same page. roughly 30% more memory for that speed, and the safety checks can pause a long job until you approve the next step describing the problem was the expensive half of fixing it. that half just ended every hour you spend explaining the symptom to a chat window, someone else has handed theirs over whole bookmark this before the next thing breaks, the playbook for handing a whole job to an AI worker is in the piece below ↓

OpenAI. said. this. publicly. their own engineers just proved one idea on themselves, in writing: stop telling AI what's wrong. hand it the whole broken thing and let it find out they gave GPT-6 Astra a slow test build of their own coding tool. one cause found, a memory bottleneck, one allocator swapped, every turn 25× faster this is GPT-6 Astra, the layer that fixes the cause instead of the symptom, $0 on top of the ChatGPT plan you already pay for: - open ChatGPT or Codex, pick GPT-6 Astra, hand it the whole thing: the folder, the file that takes a minute to open. it works in apps with no API and reads your screen - type one sentence: find the one cause, prove it, fix it, do not patch around it - leave the room. it asks without stopping, keeps working on what does not need your answer, waits only where the answer changes the outcome - keep it in one Codex session with the experimental notes setting on: it remembers across context windows why an earlier fix failed - expect the first pass to land: handed a program with no source, it worked out how it runs 88% of the time first try, 99.2% within four you never find out what was broken. it gets fixed anyway the catch is on the same page. roughly 30% more memory for that speed, and the safety checks can pause a long job until you approve the next step describing the problem was the expensive half of fixing it. that half just ended every hour you spend explaining the symptom to a chat window, someone else has handed theirs over whole bookmark this before the next thing breaks, the playbook for handing a whole job to an AI worker is in the piece below ↓

Argona

109,831 просмотров • 28 дней назад

Claude Code tip: stop burning Opus 5.5 context on tasks Sonnet 5.5 can swarm, while Fable 5.1 sits idle spin up an autonomous team with --agent claude --agent architect Opus 5.5 acts as the lead architect, scoping the work and validating every worktree before it merges Sonnet 5.5 teammates take isolated git worktrees and hammer out implementations at medium effort Fable 5.1 sits on the team as a dedicated adversary, only stepping in at three critical moments: → before a contract locks: does the frontend payload match the backend schema? → when a test breaks twice: are we patching the bug or just hiding the symptom? → before the merge: what attack surface or edge case did everyone overlook? Sonnet 5.5 builds. Fable 5.1 challenges. Opus 5.5 merges and ships Jev engineering runs the identical pattern one layer down: mechanical decisions that need no reasoning (which file to open, which tool to invoke, retry or abort) execute in 16ms, so the frontier models only wake up when execution paths actually diverge Plan on high. Delegate on medium. Keep the adversary on peer-to-peer call. - the full team setup > architect runs the main session on Opus 5.5 at high effort > teammate-ux builds client state inside its own git worktree > teammate-back writes endpoints and migrations inside a separate worktree > teammate-adv runs on Fable 5.1, read-only, and attacks every diff > teammates message each other by name without routing through the lead > tools: Agent(ux, backend, adversary) locks the architect to spawning only its own team paste the setup and this prompt into Claude Code below: "Configure my Claude Code workspace for an autonomous agent team: 1. Audit ~/.claude/agents and .claude/agents for definitions fitting architect, ux, backend and adversary > Generate definitions only for missing roles > Pin model: sonnet, effort: medium, isolation: worktree for ux and backend, and model: fable with read-only tools for adversary > Give architect model: opus, effort: high and tools: Agent(ux, backend, adversary) 2. Check ~/.claude/settings.json and my env: > Report CLAUDE_CODE_EXPERIMENTAL_AGENT_TEAMS if it's set, since it turns named subagents into teammates without worktrees > Report CLAUDE_CODE_SUBAGENT_MODEL_FORCE and CLAUDE_CODE_EFFORT_LEVEL, which can override the pinned models and effort 3. Write each role's prompt so ux and backend own separate folders, message each other by name when a contract changes, and hand every diff to adversary before reporting back 4. Add a team rule to ~/.claude/CLAUDE.md: no worktree merges until adversary has reviewed it Show every configuration diff first. Do not apply edits until confirmed" save it

Claude Code tip: stop burning Opus 5.5 context on tasks Sonnet 5.5 can swarm, while Fable 5.1 sits idle spin up an autonomous team with --agent claude --agent architect Opus 5.5 acts as the lead architect, scoping the work and validating every worktree before it merges Sonnet 5.5 teammates take isolated git worktrees and hammer out implementations at medium effort Fable 5.1 sits on the team as a dedicated adversary, only stepping in at three critical moments: → before a contract locks: does the frontend payload match the backend schema? → when a test breaks twice: are we patching the bug or just hiding the symptom? → before the merge: what attack surface or edge case did everyone overlook? Sonnet 5.5 builds. Fable 5.1 challenges. Opus 5.5 merges and ships Jev engineering runs the identical pattern one layer down: mechanical decisions that need no reasoning (which file to open, which tool to invoke, retry or abort) execute in 16ms, so the frontier models only wake up when execution paths actually diverge Plan on high. Delegate on medium. Keep the adversary on peer-to-peer call. - the full team setup > architect runs the main session on Opus 5.5 at high effort > teammate-ux builds client state inside its own git worktree > teammate-back writes endpoints and migrations inside a separate worktree > teammate-adv runs on Fable 5.1, read-only, and attacks every diff > teammates message each other by name without routing through the lead > tools: Agent(ux, backend, adversary) locks the architect to spawning only its own team paste the setup and this prompt into Claude Code below: "Configure my Claude Code workspace for an autonomous agent team: 1. Audit ~/.claude/agents and .claude/agents for definitions fitting architect, ux, backend and adversary > Generate definitions only for missing roles > Pin model: sonnet, effort: medium, isolation: worktree for ux and backend, and model: fable with read-only tools for adversary > Give architect model: opus, effort: high and tools: Agent(ux, backend, adversary) 2. Check ~/.claude/settings.json and my env: > Report CLAUDE_CODE_EXPERIMENTAL_AGENT_TEAMS if it's set, since it turns named subagents into teammates without worktrees > Report CLAUDE_CODE_SUBAGENT_MODEL_FORCE and CLAUDE_CODE_EFFORT_LEVEL, which can override the pinned models and effort 3. Write each role's prompt so ux and backend own separate folders, message each other by name when a contract changes, and hand every diff to adversary before reporting back 4. Add a team rule to ~/.claude/CLAUDE.md: no worktree merges until adversary has reviewed it Show every configuration diff first. Do not apply edits until confirmed" save it

Khairallah AL-Awady

32,018 просмотров • 2 дней назад

Most agent comparisons end up comparing models. We wanted to test the other half: the harness. That's the environment that decides whether a search actually runs, a source gets checked, and a file gets delivered. So we gave Minara, OpenClaw, Hermes and Claude Code the same tasks on the same base model: charts, research, code, and a prompt-injection test. Same model. Different outcomes. In the video, one AppLovin research note, GPT-5.6 Luna on both sides. Minara Harness delivered it in 1:51. Codex was still working when the recording ended. (5x speed) Full case studies 👇

Most agent comparisons end up comparing models. We wanted to test the other half: the harness. That's the environment that decides whether a search actually runs, a source gets checked, and a file gets delivered. So we gave Minara, OpenClaw, Hermes and Claude Code the same tasks on the same base model: charts, research, code, and a prompt-injection test. Same model. Different outcomes. In the video, one AppLovin research note, GPT-5.6 Luna on both sides. Minara Harness delivered it in 1:51. Codex was still working when the recording ended. (5x speed) Full case studies 👇

Minara AI

27,006 просмотров • 8 дней назад

Three skills I use every day in Claude Code and Codex to solve my hardest problems: 1️⃣ /agent-watchdog When I have one agent like Codex working on a task and I don't fully trust it's going to do everything right, I'll open up another one like Claude Code and tell it to watchdog the Codex thread. You can copy the Codex deep link into Claude Code and it'll look at the prompt you sent, watch the Codex thread until it's done, then compare the Codex solution to how it was planning to solve it and automatically fix anything that Codex missed. It can also test the work of the other agent end-to-end. Similar to the idea of OpenRouter's new Fusion feature, I've definitely found that two models thinking through a problem and checking each other's work can be wildly more impactful than just one. 2️⃣ /plan-arbiter Similar ideas as /agent-watchdog - but with this one you have both make plans, compare plans, negotiate the differences, and make a final plan to execute. I find Claude Code is better at writing plans, but Codex is faster and cheaper to execute on them. Then I usually have Claude Code watchdog the Codex work and fix anything that was missed. 3️⃣ /read-the-damn-docs One thing that drives me crazy with coding agents is they're so reluctant to look up docs. They'll just guess and guess and guess at the right API surface for things, or the right solution to an integration of two things. Once I explicitly tell it to look up the docs, it says "Oh, I see the answer," and it fixes the problem. So I made the /read-the-damn-docs skill. Add it and your agents will know when and how to do efficient web searches to look up docs for the types of problems you really should look up docs for. All of these are totally open source over on my GitHub. If you try them, let me know your feedback. Will link to them below:

Three skills I use every day in Claude Code and Codex to solve my hardest problems: 1️⃣ /agent-watchdog When I have one agent like Codex working on a task and I don't fully trust it's going to do everything right, I'll open up another one like Claude Code and tell it to watchdog the Codex thread. You can copy the Codex deep link into Claude Code and it'll look at the prompt you sent, watch the Codex thread until it's done, then compare the Codex solution to how it was planning to solve it and automatically fix anything that Codex missed. It can also test the work of the other agent end-to-end. Similar to the idea of OpenRouter's new Fusion feature, I've definitely found that two models thinking through a problem and checking each other's work can be wildly more impactful than just one. 2️⃣ /plan-arbiter Similar ideas as /agent-watchdog - but with this one you have both make plans, compare plans, negotiate the differences, and make a final plan to execute. I find Claude Code is better at writing plans, but Codex is faster and cheaper to execute on them. Then I usually have Claude Code watchdog the Codex work and fix anything that was missed. 3️⃣ /read-the-damn-docs One thing that drives me crazy with coding agents is they're so reluctant to look up docs. They'll just guess and guess and guess at the right API surface for things, or the right solution to an integration of two things. Once I explicitly tell it to look up the docs, it says "Oh, I see the answer," and it fixes the problem. So I made the /read-the-damn-docs skill. Add it and your agents will know when and how to do efficient web searches to look up docs for the types of problems you really should look up docs for. All of these are totally open source over on my GitHub. If you try them, let me know your feedback. Will link to them below:

Steve (Builder.io)

43,089 просмотров • 3 месяцев назад