正在加载视频...

视频加载失败

加载此视频时出现问题。这可能是由于临时网络问题，或视频可能不可用。

I am genuinely baffled why everyone is sleeping on this feature: Claude Code can review your CLAUDE.md configuration and weed out outdated legacy rules meant for older iterations 1. Upgrade your Claude Code utility to version v2.1.283 (or newer) via: claude update 2. Navigate into your project workspace and... execute: /doctor prompt-audit 3. The tool scans CLAUDE.md, AGENTS.md, custom rules, skills, and command definitions located in .claude/ and ~/.claude/ 4. It flags prompts and guidelines tailored specifically for previous-gen models 5. It spots broken references pointing to missing files or non-existent commands 6. It catches conflicting instructions across your configuration files 7. You get a comprehensive breakdown of suggested fixes, and nothing gets modified until you explicitly tell Claude to apply them Targeting a single directory: /doctor prompt-audit .claude/ skills/deploy Anthropic guidelines state: keep individual CLAUDE.md files under 200 lines. If rules clash with one another, Claude might end up picking one at random Check out the full CLAUDE.md template and directory layout in the linked article belowshow more

Bober_smart

21,902 subscribers

15,022 次观看 • 11 天前 •via X (Twitter)

科学技术教育

Anya Rossi• Live Now

Private livecam show

55 条评论

MAX 的头像

MAX11 天前

This feature deserves way more attention. Keeping instructions clean matters.

Bober_smart 的头像

Bober_smart11 天前

I agree; everyone who uses this agent should be aware of this

Tetriss 的头像

Tetriss11 天前

Old instructions are easy to forget about. Reviewing them once in a while makes sense

Bober_smart 的头像

Bober_smart11 天前

Exactly, that’s why it’s an excellent solution

boan 的头像

boan11 天前

finally, a proper cleanup tool for claude configs

Bober_smart 的头像

Bober_smart11 天前

I hope I’ve been helpful

Kinder 的头像

Kinder11 天前

prompt audit is huge for cleaning out bloat from legacy rules

Bober_smart 的头像

Bober_smart11 天前

You’re 100% right

Dipen Vaja 的头像

Dipen Vaja11 天前

Prompts rot faster than code does. Every rule written to babysit an old model becomes a tax on the new one, so a prompt audit belongs in the routine right next to dependency updates.

Moysha 的头像

Moysha11 天前

Especially useful that you can review changes before applying them

Bober_smart 的头像

Bober_smart11 天前

Yes, this is complete control over the work

Rohan 的头像

Rohan11 天前

Does it show a diff of the rules it wants to remove before applying anything?

Bober_smart 的头像

Bober_smart11 天前

Yeah, sure, buddy

Prompt Goblin 的头像

Prompt Goblin11 天前

my CLAUDE.md is just the word "snacks" in all caps and nobody has ever called it outdated

Bober_smart 的头像

Bober_smart11 天前

An update certainly wouldn't go amiss

Lemberg 的头像

Lemberg11 天前

Useful tip for keeping Claude Code setups clean.

Bober_smart 的头像

Bober_smart11 天前

Thank you, I really appreciated this

Korens 的头像

Korens11 天前

I should probably audit my configurations more often

Bober_smart 的头像

Bober_smart11 天前

This is undoubtedly the right decision

John Rood 的头像

John Rood11 天前

the audit catches contradictions. the harder question is which rule is still load-bearing, and the evidence for that lives in the sessions where the rule fired, which compaction already ate. keeping that trail is exactly why I built memoryrouter.

Bober_smart 的头像

Bober_smart11 天前

An excellent choice, you really did everything right

Gipp 🦅 的头像

Gipp 🦅11 天前

audit config first, apply fixes last for real safety

Bober_smart 的头像

Bober_smart11 天前

Yes, the sequence of actions is absolutely correct

Ridark 的头像

Ridark11 天前

Beautiful terminal, one of the best I’ve seen lately

Bober_smart 的头像

Bober_smart11 天前

Thank you, your words mean a great deal to me

EagleVision 的头像

EagleVision11 天前

really useful, especially for projects with lots of instructions

Bober_smart 的头像

Bober_smart11 天前

For them, this is a real alpha

shmidt 的头像

shmidt11 天前

second brain need to everyone

Bober_smart 的头像

Bober_smart11 天前

In the modern world, absolutely yes

kiosa 的头像

kiosa11 天前

They gotta be woke

Bober_smart 的头像

Bober_smart11 天前

Thank you, my great friend

Vlad Web3 的头像

Vlad Web311 天前

Love that it audits the rules first and waits before changing anything

Bober_smart 的头像

Bober_smart11 天前

This is the perfect job

me_cool_off 的头像

me_cool_off11 天前

i’ll do it today, ty

Bober_smart 的头像

Bober_smart11 天前

Bro 🤝

EugBass 的头像

EugBass11 天前

certainly, why?

Bober_smart 的头像

Bober_smart11 天前

This is something everyone should familiarize themselves with

EugBass 的头像

EugBass11 天前

definitely

Bubo 的头像

Bubo11 天前

the report first part is what makes it safe to run on a messy repo

Bober_smart 的头像

Bober_smart11 天前

Yes, that is the most important part of this process

tenzo 的头像

tenzo11 天前

catching conflicting rules is especially useful

Bober_smart 的头像

Bober_smart11 天前

This is exactly what I like most about this place

Dekos 的头像

Dekos11 天前

such opportunities cannot be missed

Bober_smart 的头像

Bober_smart11 天前

Plus, the setup takes 10 minutes

(Parody) Mike Bouchard 的头像

(Parody) Mike Bouchard11 天前

Those graphics are to adults using AI tools what colorful cereal packages are to kids passing through cereal isles, and yet, you all post them without any shame.

Utkarsh Jha | building Piperoom 的头像

Utkarsh Jha | building Piperoom11 天前

Worth running whenever several agents share one CLAUDE.md: one stale rule spreads to every session at once. Does the audit also check rules against what your hooks actually enforce?

Ahmad 的头像

Ahmad11 天前

does it catch rules that contradict each other

Nitesh 的头像

Nitesh11 天前

this is the kind of feature that deserves way more attention

车友圈里的小桃子的头像

车友圈里的小桃子10 天前

the bass hit so hard my ribs are still buzzing

Ani 的头像

Ani11 天前

I have all this automated. It runs on its own throw my Claw setup.

Ashish Khandelwal 的头像

Ashish Khandelwal11 天前

Ok I'm out of excuses for not cleaning up my CLAUDE.md lol

Isagii 的头像

Isagii11 天前

Oh cool

Insomnia 的头像

Insomnia11 天前

you making it like magic

阿琳的头像

阿琳11 天前

stage sweat and analog cymbals, proper double gig levels when unclosed

magsimich 的头像

magsimich10 天前

This looks good to me

相关视频

Your Claude setup might be full of broken instructions Run /doctor prompt-audit to catch dead paths, outdated commands, and conflicting instruction files before they hurt Opus 5.5.

Your Claude setup might be full of broken instructions Run /doctor prompt-audit to catch dead paths, outdated commands, and conflicting instruction files before they hurt Opus 5.5.

0xMarioNawfal

52,707 次观看 • 1 个月前

It is becoming f*cking dangerous: when Anthropic shipped CLAUDE.md, they didn't even realize they were opening a Pandora's box 1. Make an empty folder on your computer, call it SECOND BRAIN 2. Open Claude Code inside it 3. Add subfolders: MEMORY/, notes/, people/, projects/ 4. Drop a CLAUDE.md in the root with one rule: save every key fact to MEMORY, one topic per file 5. Add @-links in CLAUDE.md so key files load into context every session 6. Run claude mcp add to connect Playwright MCP, now Claude controls a real browser 7. Build a skill in .claude/skills/ so one command runs the entire routine Folder setup: about 5 minutes Your Claude becomes a second brain: it keeps every key fact between sessions, loads your main files by itself and drives a real browser Full guide in the article below

It is becoming f*cking dangerous: when Anthropic shipped CLAUDE.md, they didn't even realize they were opening a Pandora's box 1. Make an empty folder on your computer, call it SECOND BRAIN 2. Open Claude Code inside it 3. Add subfolders: MEMORY/, notes/, people/, projects/ 4. Drop a CLAUDE.md in the root with one rule: save every key fact to MEMORY, one topic per file 5. Add @-links in CLAUDE.md so key files load into context every session 6. Run claude mcp add to connect Playwright MCP, now Claude controls a real browser 7. Build a skill in .claude/skills/ so one command runs the entire routine Folder setup: about 5 minutes Your Claude becomes a second brain: it keeps every key fact between sessions, loads your main files by itself and drives a real browser Full guide in the article below

plusxbt

69,401 次观看 • 17 天前

Boris Cherny gave Claude Code a memory that has no database, no indexing, no setup, and 80% of Anthropic runs on it a CLAUDE.md "gets automatically read into context at the start of every session" 12:48 - CLAUDE.md loads into memory every session 13:15 - Keep memory short or it burns your context 15:48 - Memory stacks from you to your whole company 17:30 - The memory command shows what Claude remembers 19:33 - Hit pound and Claude remembers it forever the whole memory layer is files → drop a CLAUDE.md in your repo and Claude reads it in on every session → nest more in subfolders and it pulls them only where it works → stack them personal to project to enterprise so one config serves the whole team → hit the pound key mid task and Claude writes the new fact into memory itself the best coding agent's memory was never a database, it was markdown you can open and edit

Boris Cherny gave Claude Code a memory that has no database, no indexing, no setup, and 80% of Anthropic runs on it a CLAUDE.md "gets automatically read into context at the start of every session" 12:48 - CLAUDE.md loads into memory every session 13:15 - Keep memory short or it burns your context 15:48 - Memory stacks from you to your whole company 17:30 - The memory command shows what Claude remembers 19:33 - Hit pound and Claude remembers it forever the whole memory layer is files → drop a CLAUDE.md in your repo and Claude reads it in on every session → nest more in subfolders and it pulls them only where it works → stack them personal to project to enterprise so one config serves the whole team → hit the pound key mid task and Claude writes the new fact into memory itself the best coding agent's memory was never a database, it was markdown you can open and edit

NO1ennn

13,015 次观看 • 3 个月前

I deleted 80% of my CLAUDE.md last night. My CLAUDE.md was 400 lines. It's now 60. Claude works better. It's all because of this video. Two Anthropic engineers. 50 minutes. The Claude team's best practices. Anthropic deleted 80% of the Claude Code system prompt. The output got better. Most people will keep adding rules and wondering why it keeps getting worse. Watch it today, then read the guide below.

I deleted 80% of my CLAUDE.md last night. My CLAUDE.md was 400 lines. It's now 60. Claude works better. It's all because of this video. Two Anthropic engineers. 50 minutes. The Claude team's best practices. Anthropic deleted 80% of the Claude Code system prompt. The output got better. Most people will keep adding rules and wondering why it keeps getting worse. Watch it today, then read the guide below.

Raytar

127,789 次观看 • 3 个月前

THIS IS A PURE F*CKING GOLDMINE Anthropic just documented how Claude Code actually remembers your entire codebase across sessions The idea: stop dumping 500 lines into CLAUDE.md and let the new Haiku 5.5 manage an auto-indexing memory tree while Opus 5.5 audits your rules Zero context bloat, path-scoped rules that load only when touched, and persistent learnings that survive across Git worktrees You just inspect and steer it in Claude Code like this: /memory here's how it splits: → Opus 5.5 audits rule integrity: runs /doctor prompt-audit to catch stale instructions, contradictions, and obsolete configs → Sonnet 5.5 writes path-scoped rules: drafts modular .claude/rules/ with frontmatter globs so rules only load for matching files → Haiku 5.5 maintains auto-memory: indexes MEMORY.md at 340 tok/s and moves deep context into dedicated topic files → you stop burning Opus context on static prompt bloat and keep your session token count razor thin The memory architecture runs through three proven layers: → path-scoped rules: .claude/rules/*.md load strictly when touched files match, saving up to 80% context → auto-memory index: MEMORY.md caps at 200 lines / 25KB, keeping startup instant across all worktrees → on-demand topic files: detailed architectural notes live in ~/.claude/projects/ /memory/ without polluting the turn Opus audits, Haiku indexes, Sonnet scopes JEV engineering is the same move one layer down: the forks that need no thinker (which rule file matches, auto-memory threshold, stale timestamp drop) resolve in code in 15ms, and the frontier models only see the ones that split the full tree > Opus 5.5 audits rule consistency and runs /doctor prompt-audit > Haiku 5.5 prunes and indexes MEMORY.md at 340 tok/s (1M context) > Sonnet 5.5 writes path-scoped rules in .claude/rules/ with frontmatter globs > on-demand topic files capture edge cases without burning startup tokens > ~/.claude/projects/ /memory/ shares learnings across all Git worktrees > Opus 5.5 enforces zero-regression architecture standards > JEV routes path matching in milliseconds paste the tree and this prompt into Claude Code ↓ "Reconfigure my Claude Code memory architecture around this tree: 1. Audit my current CLAUDE.md with /doctor prompt-audit and strip out stale or conflicting rules 2. Move file-specific instructions into .claude/rules/*.md with YAML frontmatter path globs 3. Delegate MEMORY.md indexing and 200-line threshold management to Haiku 5.5 at 340 tok/s 4. Route detailed architectural learnings and edge cases to Sonnet 5.5 as on-demand topic files 5. Reserve Opus 5.5 for high-level rule consistency and cross-worktree memory verification Show me every change as a diff first. No edits until I say go" ↳ save it, it'll come in handy

THIS IS A PURE FCKING GOLDMINE Anthropic just documented how Claude Code actually remembers your entire codebase across sessions The idea: stop dumping 500 lines into CLAUDE.md and let the new Haiku 5.5 manage an auto-indexing memory tree while Opus 5.5 audits your rules Zero context bloat, path-scoped rules that load only when touched, and persistent learnings that survive across Git worktrees You just inspect and steer it in Claude Code like this: /memory here's how it splits: → Opus 5.5 audits rule integrity: runs /doctor prompt-audit to catch stale instructions, contradictions, and obsolete configs → Sonnet 5.5 writes path-scoped rules: drafts modular .claude/rules/ with frontmatter globs so rules only load for matching files → Haiku 5.5 maintains auto-memory: indexes MEMORY.md at 340 tok/s and moves deep context into dedicated topic files → you stop burning Opus context on static prompt bloat and keep your session token count razor thin The memory architecture runs through three proven layers: → path-scoped rules: .claude/rules/.md load strictly when touched files match, saving up to 80% context → auto-memory index: MEMORY.md caps at 200 lines / 25KB, keeping startup instant across all worktrees → on-demand topic files: detailed architectural notes live in ~/.claude/projects/ /memory/ without polluting the turn Opus audits, Haiku indexes, Sonnet scopes JEV engineering is the same move one layer down: the forks that need no thinker (which rule file matches, auto-memory threshold, stale timestamp drop) resolve in code in 15ms, and the frontier models only see the ones that split the full tree > Opus 5.5 audits rule consistency and runs /doctor prompt-audit > Haiku 5.5 prunes and indexes MEMORY.md at 340 tok/s (1M context) > Sonnet 5.5 writes path-scoped rules in .claude/rules/ with frontmatter globs > on-demand topic files capture edge cases without burning startup tokens > ~/.claude/projects/ /memory/ shares learnings across all Git worktrees > Opus 5.5 enforces zero-regression architecture standards > JEV routes path matching in milliseconds paste the tree and this prompt into Claude Code ↓ "Reconfigure my Claude Code memory architecture around this tree: 1. Audit my current CLAUDE.md with /doctor prompt-audit and strip out stale or conflicting rules 2. Move file-specific instructions into .claude/rules/*.md with YAML frontmatter path globs 3. Delegate MEMORY.md indexing and 200-line threshold management to Haiku 5.5 at 340 tok/s 4. Route detailed architectural learnings and edge cases to Sonnet 5.5 as on-demand topic files 5. Reserve Opus 5.5 for high-level rule consistency and cross-worktree memory verification Show me every change as a diff first. No edits until I say go" ↳ save it, it'll come in handy

mirku

30,878 次观看 • 20 天前

Cat Wu, head of product for Claude Code at Anthropic: "you can build almost anything with Claude from a single prompt now" one prompt gets you a working screen, not YOUR product Claude Code has never seen your design system, so it guesses the look fresh every time. how to hand Claude Code that system is in the article. better than the $300 design course in your tabs, and this one's free.

Cat Wu, head of product for Claude Code at Anthropic: "you can build almost anything with Claude from a single prompt now" one prompt gets you a working screen, not YOUR product Claude Code has never seen your design system, so it guesses the look fresh every time. how to hand Claude Code that system is in the article. better than the $300 design course in your tabs, and this one's free.

Mnimiy

114,229 次观看 • 5 个月前

Opus 5.5 is out! excellent at coding, great at writing, reduced pricing. run '/claude-api migrate' in the latest Claude Code to update your application code. run '/claude-api prompt-audit' to ensure your skills + prompts are well-tuned. short video overview:

Opus 5.5 is out! excellent at coding, great at writing, reduced pricing. run '/claude-api migrate' in the latest Claude Code to update your application code. run '/claude-api prompt-audit' to ensure your skills + prompts are well-tuned. short video overview:

Lance Martin

35,554 次观看 • 1 个月前

I still don’t understand why people build Opus 5.5 setups from scratch. 10 repos already did it for you, from 68K stars to 0. 01 claude-code-best-practice → 68K stars. the full guide to subagents, skills, hooks, MCP and memory, with working examples 02 claude-skills → 28K stars. 388 ready skills across 20 fields, built for Claude Code, Codex and Gemini CLI 03 awesome-claude-code-toolkit → 2.7K stars. 135 agents, 42 commands, 20 hooks and 15 rules you can drop into a project 04 AI-Product-Development-Toolkit → 994 stars. six planning prompts, a Next.js starter and a ready CLAUDE.md written for Opus 5.5 05 awesome-claude-video-skills → 867 stars. 300+ repos that teach Claude to make video, sorted by type 06 awesome-claude-code → 508 stars. the cleanest map of tools, plugins and usage trackers around Claude Code 07 motion-graphics-skills → 375 stars. launch-style motion graphics where every frame is code, no After Effects 08 opus-5-5-dev → 1 star. rules for long runs: define “done” first, keep a TASKS.md, end with a fixed four-part report 09 model-bump → 0 stars. scans your code for what breaks on Opus 5.5, like forced tool choice, sampling settings and prefill 10 claude-best-practices → 1 star. 29 agents, 174 skills, 58 rules and 22 hooks to copy into your project stars measure hype. fit measures results. pick one, run it on a single task, keep only what survives. save this before you upgrade, and follow for more setups like this

I still don’t understand why people build Opus 5.5 setups from scratch. 10 repos already did it for you, from 68K stars to 0. 01 claude-code-best-practice → 68K stars. the full guide to subagents, skills, hooks, MCP and memory, with working examples 02 claude-skills → 28K stars. 388 ready skills across 20 fields, built for Claude Code, Codex and Gemini CLI 03 awesome-claude-code-toolkit → 2.7K stars. 135 agents, 42 commands, 20 hooks and 15 rules you can drop into a project 04 AI-Product-Development-Toolkit → 994 stars. six planning prompts, a Next.js starter and a ready CLAUDE.md written for Opus 5.5 05 awesome-claude-video-skills → 867 stars. 300+ repos that teach Claude to make video, sorted by type 06 awesome-claude-code → 508 stars. the cleanest map of tools, plugins and usage trackers around Claude Code 07 motion-graphics-skills → 375 stars. launch-style motion graphics where every frame is code, no After Effects 08 opus-5-5-dev → 1 star. rules for long runs: define “done” first, keep a TASKS.md, end with a fixed four-part report 09 model-bump → 0 stars. scans your code for what breaks on Opus 5.5, like forced tool choice, sampling settings and prefill 10 claude-best-practices → 1 star. 29 agents, 174 skills, 58 rules and 22 hooks to copy into your project stars measure hype. fit measures results. pick one, run it on a single task, keep only what survives. save this before you upgrade, and follow for more setups like this

Ryven

18,194 次观看 • 17 天前

Claude Code creator, Boris Cherny: "Every six months, delete your claude.md, delete your skills, delete your hooks, see what the model does, and it might surprise you." Anthropic deleted 80% of Claude Code's system prompt for Opus 5. It doesn't need the instructions past models did. 36 minutes of pure insight from the creator of the fastest-growing AI coding tool in the world. Watch it, then read the guide below.

Claude Code creator, Boris Cherny: "Every six months, delete your claude.md, delete your skills, delete your hooks, see what the model does, and it might surprise you." Anthropic deleted 80% of Claude Code's system prompt for Opus 5. It doesn't need the instructions past models did. 36 minutes of pure insight from the creator of the fastest-growing AI coding tool in the world. Watch it, then read the guide below.

Alex Prompter

87,899 次观看 • 3 个月前

Your CLAUDE.md is making Opus 5.5 dumber, and the fix is one command "double check your work" and "think step by step" they were written for older models on Opus 5.5 they slow it down and make the output worse Lance Martin at Anthropic built the fix: /claude-api prompt-audit > scans your skills, CLAUDE.md and prompts > cuts every line that holds the model back > rewrites the rest with Anthropic's Opus 5.5 guidance 5 minutes later your setup finally speaks the language of the model you're paying for

Your CLAUDE.md is making Opus 5.5 dumber, and the fix is one command "double check your work" and "think step by step" they were written for older models on Opus 5.5 they slow it down and make the output worse Lance Martin at Anthropic built the fix: /claude-api prompt-audit > scans your skills, CLAUDE.md and prompts > cuts every line that holds the model back > rewrites the rest with Anthropic's Opus 5.5 guidance 5 minutes later your setup finally speaks the language of the model you're paying for

Mr. Buzzoni

11,988 次观看 • 1 个月前

Boris Cherny: "My job is to write loops." 5-day version you can copy for Claude Code Day 1: repo memory - write CLAUDE.md - include stack, test commands, code style, release rules, gotchas - add .claude/settings.json with the shell commands Claude can run Day 2: verification skill - pick 1 flow Claude keeps breaking - put the browser/API test in .claude/skills/ /scripts/ - make it return: pass/fail, failing step, screenshot/log path Day 3: commands Add these files: .claude/commands/babysit.md - checks your PRs - reads CI - handles obvious review nits - surfaces design questions .claude/commands/triage-issues.md - labels new issues - dedupes against existing ones - assigns owners .claude/commands/deploy-watch.md - checks the live app - reports regressions - avoids touching production Day 4: loops > /loop 5m /babysit > /loop 15m /triage-issues > /loop 5m /deploy-watch Day 5: overnight work - schedule /morning-report - schedule /deep-audit - write results to .claude/inbox/ - let your morning loop read from that folder The rule: every code-writing loop gets a separate verifier. Builder makes the change. Verifier runs the real app. You read the diff. Skip that and you wake up to 14 broken PRs with very confident summaries. Video: "Reflecting on a year of Claude Code" with Boris Cherny & Cat Wu

Boris Cherny: "My job is to write loops." 5-day version you can copy for Claude Code Day 1: repo memory - write CLAUDE.md - include stack, test commands, code style, release rules, gotchas - add .claude/settings.json with the shell commands Claude can run Day 2: verification skill - pick 1 flow Claude keeps breaking - put the browser/API test in .claude/skills/ /scripts/ - make it return: pass/fail, failing step, screenshot/log path Day 3: commands Add these files: .claude/commands/babysit.md - checks your PRs - reads CI - handles obvious review nits - surfaces design questions .claude/commands/triage-issues.md - labels new issues - dedupes against existing ones - assigns owners .claude/commands/deploy-watch.md - checks the live app - reports regressions - avoids touching production Day 4: loops > /loop 5m /babysit > /loop 15m /triage-issues > /loop 5m /deploy-watch Day 5: overnight work - schedule /morning-report - schedule /deep-audit - write results to .claude/inbox/ - let your morning loop read from that folder The rule: every code-writing loop gets a separate verifier. Builder makes the change. Verifier runs the real app. You read the diff. Skip that and you wake up to 14 broken PRs with very confident summaries. Video: "Reflecting on a year of Claude Code" with Boris Cherny & Cat Wu

Alpha Batcher

141,110 次观看 • 5 个月前

This shouldn't even be possible 🤯 Your Grok Bot can run CLAUDE CODE. On your own Claude plan. On a computer that NEVER turns off 🔥 Claude Code in your pocket. 24/7. Nate Herk set it up in 3 steps: 1️⃣ Tell your Bot: "Use my Claude Code subscription. Open the terminal and install it." 2️⃣ Sign in. Click authorize. 3️⃣ Have it clone your repo. Your CLAUDE.md and skills come with it. Codex works too, he says 👀 One catch 🛑 ALL your Bots share that computer. Clone only what you need. Do NOT sleep on this 🚨

This shouldn't even be possible 🤯 Your Grok Bot can run CLAUDE CODE. On your own Claude plan. On a computer that NEVER turns off 🔥 Claude Code in your pocket. 24/7. Nate Herk set it up in 3 steps: 1️⃣ Tell your Bot: "Use my Claude Code subscription. Open the terminal and install it." 2️⃣ Sign in. Click authorize. 3️⃣ Have it clone your repo. Your CLAUDE.md and skills come with it. Codex works too, he says 👀 One catch 🛑 ALL your Bots share that computer. Clone only what you need. Do NOT sleep on this 🚨

Fan Grok Bot Radar

43,841 次观看 • 1 个月前

THIS IS A PURE F*CKING GOLDMINE Anthropic just shared one of the best tips for Claude Code. The idea: stop dumping 500 lines into CLAUDE.md and let Opus 5.5, Sonnet 5.5, Haiku 5.5 and Fable 5.1 manage a self-pruning memory tree. Zero context bloat, path-scoped rules that load only when touched, and persistent learnings that never drift into hallucination. You just inspect and steer your memory like this: /memory here's how it splits: → Opus 5.5 locks enduring architecture rules and approves permanent memory commits → Sonnet 5.5 writes modular .claude/rules/*.md with frontmatter path globs so rules only load for matching files → Haiku 5.5 indexes MEMORY.md at 340 tok/s and sweeps transient scratchpads into topic files → Fable 5.1 acts as the memory adversary, catching contradictions between ~/.claude/CLAUDE.md and ./CLAUDE.md Fable 5.1 only steps in at three moments: → before a rule writes: does this directive contradict existing project memory or inject false constraints? → when auto-memory hits the 200-line cap: prune stale debugging notes and purge hallucinated assumptions → before session commit: audit memory diffs so transient scratchpad noise never pollutes future turns Opus 5.5 locks. Sonnet 5.5 scopes. Haiku 5.5 indexes. Fable 5.1 curates JEV engineering is the same move one layer down: the forks that need no thinker (path glob matching, auto-memory threshold check, cache hit resolution) resolve in code in 16ms, and frontier models only wake up when memory rules actually conflict the full tree > Opus 5.5 on high runs the main session and enforces zero-regression memory standards > Sonnet 5.5 drafts path-scoped rules in .claude/rules/ with frontmatter globs > Haiku 5.5 indexes MEMORY.md at 340 tok/s and offloads deep context to topic files > Fable 5.1 on call audits rule drift and eliminates contradictory directives > ~/.claude/projects/ /memory/ shares hardened learnings across all Git worktrees > JEV routes path glob matches and cache lookups in milliseconds paste the tree and this prompt into Claude Code ↓ "Reconfigure my Claude Code memory architecture around this tree: 1. Audit ~/.claude/CLAUDE.md and ./CLAUDE.md to eliminate contradictory instructions and strip out stale rules 2. Split monolithic project guidelines into modular .claude/rules/*.md files with YAML frontmatter path globs 3. Delegate MEMORY.md index maintenance and 200-line threshold pruning to Haiku 5.5 at 340 tok/s 4. Set Fable 5.1 as the adversary to audit any new memory entry before it commits to disk 5. Reserve Opus 5.5 for high-level architecture decisions and permanent memory sign-off 6. Route deterministic path matching and cache checks through JEV Show me every change as a diff first. No edits until I say go" ↳ save it, you'll use this every single day

THIS IS A PURE FCKING GOLDMINE Anthropic just shared one of the best tips for Claude Code. The idea: stop dumping 500 lines into CLAUDE.md and let Opus 5.5, Sonnet 5.5, Haiku 5.5 and Fable 5.1 manage a self-pruning memory tree. Zero context bloat, path-scoped rules that load only when touched, and persistent learnings that never drift into hallucination. You just inspect and steer your memory like this: /memory here's how it splits: → Opus 5.5 locks enduring architecture rules and approves permanent memory commits → Sonnet 5.5 writes modular .claude/rules/.md with frontmatter path globs so rules only load for matching files → Haiku 5.5 indexes MEMORY.md at 340 tok/s and sweeps transient scratchpads into topic files → Fable 5.1 acts as the memory adversary, catching contradictions between ~/.claude/CLAUDE.md and ./CLAUDE.md Fable 5.1 only steps in at three moments: → before a rule writes: does this directive contradict existing project memory or inject false constraints? → when auto-memory hits the 200-line cap: prune stale debugging notes and purge hallucinated assumptions → before session commit: audit memory diffs so transient scratchpad noise never pollutes future turns Opus 5.5 locks. Sonnet 5.5 scopes. Haiku 5.5 indexes. Fable 5.1 curates JEV engineering is the same move one layer down: the forks that need no thinker (path glob matching, auto-memory threshold check, cache hit resolution) resolve in code in 16ms, and frontier models only wake up when memory rules actually conflict the full tree > Opus 5.5 on high runs the main session and enforces zero-regression memory standards > Sonnet 5.5 drafts path-scoped rules in .claude/rules/ with frontmatter globs > Haiku 5.5 indexes MEMORY.md at 340 tok/s and offloads deep context to topic files > Fable 5.1 on call audits rule drift and eliminates contradictory directives > ~/.claude/projects/ /memory/ shares hardened learnings across all Git worktrees > JEV routes path glob matches and cache lookups in milliseconds paste the tree and this prompt into Claude Code ↓ "Reconfigure my Claude Code memory architecture around this tree: 1. Audit ~/.claude/CLAUDE.md and ./CLAUDE.md to eliminate contradictory instructions and strip out stale rules 2. Split monolithic project guidelines into modular .claude/rules/*.md files with YAML frontmatter path globs 3. Delegate MEMORY.md index maintenance and 200-line threshold pruning to Haiku 5.5 at 340 tok/s 4. Set Fable 5.1 as the adversary to audit any new memory entry before it commits to disk 5. Reserve Opus 5.5 for high-level architecture decisions and permanent memory sign-off 6. Route deterministic path matching and cache checks through JEV Show me every change as a diff first. No edits until I say go" ↳ save it, you'll use this every single day

mirku

22,211 次观看 • 5 天前

HOLY F*CKING SH*T you waste 20 minutes every morning re-explaining your project to Claude like it has never heard of you, and Karpathy showed you the fix a year ago Andrej Karpathy, co-founder of OpenAI, posted one idea that pulled 16 million views: stop using AI to write code. use it to build a second brain You point Claude Code to a folder, drop any source in there (article, transcript, PDF) and Claude reads it, links it, and saves it into a living wiki of everything you know. it compounds like interest: the more you feed it, the sharper every answer gets Here is the gist: → install Obsidian, create a vault, open it in Claude Code → paste Karpathy's wiki prompt and tell Claude to build it → Claude creates 3 folders: raw for sources, wiki for its pages, CLAUDE.md that runs everything → drop any source into raw and say "ingest this" → ask anything across all of it, forever 5 minutes to set up. and you never open a blank Claude chat again the full step-by-step is in the article below bookmark this before you waste another monday

HOLY FCKING SHT you waste 20 minutes every morning re-explaining your project to Claude like it has never heard of you, and Karpathy showed you the fix a year ago Andrej Karpathy, co-founder of OpenAI, posted one idea that pulled 16 million views: stop using AI to write code. use it to build a second brain You point Claude Code to a folder, drop any source in there (article, transcript, PDF) and Claude reads it, links it, and saves it into a living wiki of everything you know. it compounds like interest: the more you feed it, the sharper every answer gets Here is the gist: → install Obsidian, create a vault, open it in Claude Code → paste Karpathy's wiki prompt and tell Claude to build it → Claude creates 3 folders: raw for sources, wiki for its pages, CLAUDE.md that runs everything → drop any source into raw and say "ingest this" → ask anything across all of it, forever 5 minutes to set up. and you never open a blank Claude chat again the full step-by-step is in the article below bookmark this before you waste another monday

mojesko

98,648 次观看 • 11 天前

This 3-minute video from Anthropic will make you realize you've been using Claude wrong this whole time "when you open Claude Code without a CLAUDE.md file, it has to start fresh every single time" most people have no idea how much this one file changes the way Claude actually works for you and this isn't only for developers the article below has 21 CLAUDE.md examples you can use in your daily routine I'm sure everyone will find something that fits exactly how they work

This 3-minute video from Anthropic will make you realize you've been using Claude wrong this whole time "when you open Claude Code without a CLAUDE.md file, it has to start fresh every single time" most people have no idea how much this one file changes the way Claude actually works for you and this isn't only for developers the article below has 21 CLAUDE.md examples you can use in your daily routine I'm sure everyone will find something that fits exactly how they work

Anatoli Kopadze

490,648 次观看 • 6 个月前

Boris Cherny, the creator of Claude Code at Anthropic, just explained why most people aren't getting real results from Claude in this talk he breaks down exactly how most people skipped the setup entirely: - 90% of code at Anthropic is written by Claude itself - the 14% you lose to CLAUDE.md before typing a word - lawyers, designers, and finance people are building real things with it - no CS degree. no background. nothing Boris Cherny: "Claude Code is 100% written by Claude Code, Cowork is 100% written by Claude Code" if you've been using Claude for months and never configured a single thing, you skipped the 20 steps that change everything. probably 25 instead of another show tonight, watch this make sure to bookmark it before it gets lost in your feed my breakdown of all 25 features is below

Boris Cherny, the creator of Claude Code at Anthropic, just explained why most people aren't getting real results from Claude in this talk he breaks down exactly how most people skipped the setup entirely: - 90% of code at Anthropic is written by Claude itself - the 14% you lose to CLAUDE.md before typing a word - lawyers, designers, and finance people are building real things with it - no CS degree. no background. nothing Boris Cherny: "Claude Code is 100% written by Claude Code, Cowork is 100% written by Claude Code" if you've been using Claude for months and never configured a single thing, you skipped the 20 steps that change everything. probably 25 instead of another show tonight, watch this make sure to bookmark it before it gets lost in your feed my breakdown of all 25 features is below

Khairallah AL-Awady

186,035 次观看 • 5 个月前

I can't f*cking believe Anthropic open-sourced the cheat codes for Claude Code and people are still doing it by hand here are the cheat codes: -> skills (by anthropics) official skills repo from Anthropic, with clean examples of how a real skill is built -> claude code action (by anthropics) Claude R Perrin in any PR or issue and it answers, writes the fix on a new branch and signs its commits -> claude code security review (by anthropics) every pull request diff for vulnerabilities and filters out the noisy findings -> claude agent sdk python (by anthropics) Claude Code from your own Python app, with custom tools and hooks -> claude cookbooks (by anthropics) runnable notebooks for RAG, tool use, classification and structured output pick one, add it to your repo tonight bookmark it before it gets buried

I can't f*cking believe Anthropic open-sourced the cheat codes for Claude Code and people are still doing it by hand here are the cheat codes: -> skills (by anthropics) official skills repo from Anthropic, with clean examples of how a real skill is built -> claude code action (by anthropics) Claude R Perrin in any PR or issue and it answers, writes the fix on a new branch and signs its commits -> claude code security review (by anthropics) every pull request diff for vulnerabilities and filters out the noisy findings -> claude agent sdk python (by anthropics) Claude Code from your own Python app, with custom tools and hooks -> claude cookbooks (by anthropics) runnable notebooks for RAG, tool use, classification and structured output pick one, add it to your repo tonight bookmark it before it gets buried

rvaniaaa

56,542 次观看 • 4 天前

Here's what the Founder of Claude Code does before he starts ANY project: 1. Plans first, codes never, he goes back and forth with Claude on the plan until it's perfect. No code gets written yet 2. Creates a CLAUDE.md file (a simple doc that Claude reads every session so it knows your project, your rules, your style) 3. Gives Claude a way to verify its own work - For backend: write and run tests - For UI: take screenshots, check in browser Claude should never finish a task without proving it works 4. Sets up project-level permission rules in settings.json instead of skipping permissions entirely. Shared with the whole team 5. Five more preparation steps in VIDEO BELOW 6. Only then switches to auto-accept mode and lets Claude build The part most people miss: he doesn't treat Claude as a magic box that gets things right first try he treats it like a junior dev that needs clear instructions, feedback loops, and guardrails at scale he runs multiple sessions in parallel, uses Opus with thinking enabled because it makes fewer mistakes even though it's slower and relies on background agents that push code for later review his setup is surprisingly simple. no crazy custom tools. just slash commands, subagents, and a clean CLAUDE.md the difference isn't the tool. it's how you set it up before you start ❤️ P.S. for sure 99.5% of readers will scroll down this tweet, but I send it to 0.5% who loves to learn how to improve your workflow daily and control 99.5% in 2 years Hard skills literally mean nothing in our world The most important skills which you can have are: building architectures and orchestrations If you master it and use a creative approach, CONGRATS

Here's what the Founder of Claude Code does before he starts ANY project: 1. Plans first, codes never, he goes back and forth with Claude on the plan until it's perfect. No code gets written yet 2. Creates a CLAUDE.md file (a simple doc that Claude reads every session so it knows your project, your rules, your style) 3. Gives Claude a way to verify its own work - For backend: write and run tests - For UI: take screenshots, check in browser Claude should never finish a task without proving it works 4. Sets up project-level permission rules in settings.json instead of skipping permissions entirely. Shared with the whole team 5. Five more preparation steps in VIDEO BELOW 6. Only then switches to auto-accept mode and lets Claude build The part most people miss: he doesn't treat Claude as a magic box that gets things right first try he treats it like a junior dev that needs clear instructions, feedback loops, and guardrails at scale he runs multiple sessions in parallel, uses Opus with thinking enabled because it makes fewer mistakes even though it's slower and relies on background agents that push code for later review his setup is surprisingly simple. no crazy custom tools. just slash commands, subagents, and a clean CLAUDE.md the difference isn't the tool. it's how you set it up before you start ❤️ P.S. for sure 99.5% of readers will scroll down this tweet, but I send it to 0.5% who loves to learn how to improve your workflow daily and control 99.5% in 2 years Hard skills literally mean nothing in our world The most important skills which you can have are: building architectures and orchestrations If you master it and use a creative approach, CONGRATS

Ronin

148,303 次观看 • 6 个月前

You can now schedule recurring cloud-based tasks on Claude Code. Set a repo (or repos), a schedule, and a prompt. Claude runs it via cloud infra on your schedule, so you don’t need to keep Claude Code running on your local machine.

You can now schedule recurring cloud-based tasks on Claude Code. Set a repo (or repos), a schedule, and a prompt. Claude runs it via cloud infra on your schedule, so you don’t need to keep Claude Code running on your local machine.

Noah Zweben

2,039,450 次观看 • 7 个月前

Claude Code + computer use is f*cking cracked 🤯 Build a landing page → Claude opens Chrome, looks at it, spots every issue, and fixes it — without you describing a single thing. All inside Claude Code. Perfect for DTC brands and agencies who are still vibe-coding landing pages and advertorials in Claude Code, then manually opening them in Chrome, spotting 15 things wrong, and describing every visual issue back to Claude one at a time. If you're building pages in Claude Code and your workflow looks like this — build the page, open it in Chrome, spot broken spacing, go back to Claude, type "the CTA button is too low and the hero image is cut off," wait for the fix, open Chrome again, find 3 new issues, describe those too ... Claude Code + computer use eliminates the entire loop: → Claude writes the full landing page or advertorial → Opens Chrome and navigates to it → Spots layout issues, broken spacing, off-brand colors, missing elements → Fixes everything and re-checks until the page looks right → Tests your Shopify product pages by clicking through like a real customer → Walks through your checkout flow and flags friction before customers hit it → You only see the finished, visually verified result No describing what you see on screen. No "the CTA button needs more contrast" back-and-forth. No being the eyeballs for an AI that can't see. What you get: → Landing pages and advertorials Claude builds AND visually QAs before you ever look at them → Product pages Claude clicks through — testing layout, images, and CTAs like a real user → HTML dashboards Claude opens and verifies the charts actually render → Checkout flows Claude walks through step by step to catch friction → All of it happening in one session — build, test, fix, done One prompt. Claude builds it, checks it, and fixes it. You just review the finished page. I put together a full playbook with the exact setup, the prompts, and 5 DTC workflows that use Claude Code + computer use. Want it for free? > Like this post > Comment "CLAUDE" And I'll send it over (must be following so I can DM)

Mike Futia

19,274 次观看 • 7 个月前