Opus 4.6 lets you set the effort level Not... every task needs high reasoning. For simpler tasks you can set it to low or medium. Claude thinks less (or skips it entirely), makes fewer tool calls, and gives more concise answers Lower effort = faster responses with fewer tokens!show more

Opus 5.5 works best on 'low' reasoning effort. I... ran some tests as part of a project I'm working on. Opus 5.5 on 'low' reasoning vs. 'max' was at parity on task completion but 12x lower cost! Set 'low' reasoning effort by default and increase it for the hardest problems.show more

ANTHROPIC JUST DROPPED THE OFFICIAL GUIDE TO PROMPTING OPUS... 5 This is the most important prompting guide for anyone using Claude. Bookmark this before you forget. Most people still prompt Opus 5 like older models. That's the mistake. > give the complete task upfront — don't drip-feed instructions. > explicitly ask for shorter responses if you want them. > use low/medium effort by default. increase effort only when needed. > let it finish the entire feature instead of asking for partial implementations. > use subagents intentionally for large codebases, not every task. Opus 5 is at its best when you stop micromanaging it and let it own the work. Read it before writing your next prompt. Claude → Opus 5 → Agentic Execution → Production-Ready Output → Moneyshow more

Claude Code tip: if Opus 5.5 is already your... main model, Fable 5.1 has been sitting idle this whole time. wire it in with /advisor start it with /advisor fable Opus 5.5 writes every line. Fable 5.1 reads the whole session, every tool call, and says nothing until one of three moments: → a plan gets proposed: is this actually the right move, or just the first one? → the same error comes back twice: is the search stuck, or is this a dead end? → the task gets marked done: what got missed while it was moving fast? Opus 5.5 ships. Fable 5.1 catches what would've shipped broken. Jev engineering makes the same move one layer down: forks that don't need a real thinker, which file, which tool, retry or give up, get routed to Jev and answered in under half a second. the expensive model only ever sees the forks that genuinely split. the tree this runs on: > Opus 5.5, high effort, owns the main session > explorer, medium effort, reads the code > worker, medium effort, edits and runs tests > researcher, medium effort, pulls the docs > Fable 5.1 outside all of it, on call, never writing a line itself drop the tree and this prompt into Claude Code: "Rebuild my Claude Code setup around this tree: 1. Look in ~/.claude/agents and .claude/agents for subagents that already cover explorer, worker and researcher. Draft new ones only for roles that are missing. Set each to model: opus, effort: medium. If an existing subagent is pinned to a different model, list it, don't touch it. 2. Set the main session's effortLevel to high in ~/.claude/settings.json, and set advisorModel to fable. 3. Check for anything disabling the advisor: CLAUDE_CODE_DISABLE_ADVISOR_TOOL, DISABLE_TELEMETRY, any variable blocking feature-flag fetches, and CLAUDE_CODE_EFFORT_LEVEL, which overrides subagent effort. Report what you find. Change nothing yet. 4. Add one line to ~/.claude/CLAUDE.md: consult the advisor before a large plan, when an error repeats, and before marking a long task done. Show every change as a diff first. Don't touch anything until I say go."show more

jev + sonnet 5.5 is f**king insane. my entire... workflow got 4x faster after adding these 6 lines to CLAUDE.md. [with jev connected, paste this👇] 1. Before you start a Claude worker, ask Jev once to select a host-approved profile with one or two sessions. The profile must specify each session’s model and effort level. If Jev makes no selection, use the host default. 2. The host must check Jev’s selection. The host must set the model and effort before each session starts. Keep these settings fixed during the session. The host controls permissions and approvals. 3. Use Sonnet 5.5 at medium effort for clear coding tasks. Use higher effort for complex reasoning or JSON tasks. Use a second Claude only for independent research or a review that the user requested. 4. Give the second Claude the task, applicable files, limits, and completion requirements. Return its findings and evidence to the lead. 5. Complete the requested work. Ask the user only when you cannot continue without input or before an action that needs approval. Do not add features, tests, files, documentation, refactors, or review rounds that the user did not request. When the work is complete and checked, stop. Report the result. 6. Before you report completion, run a test, build, type check, or command that checks the code change. If no check can run, identify the missing check. Explain why it cannot run. same task. two timers. watch the difference.show more

I’ve been using Claude Code’s Concise Output Style and... it makes the experience much cleaner I’d combine it with these settings: - Output Style: Concise Straight to the answer, no preambles or unnecessary narration - spinnerTipsEnabled: false No tips while Claude is thinking - awaySummaryEnabled: false No recap when you return to the terminal - verbose: false Keeps commands and tool calls compact Claude Code feels much less noisyshow more

Jev + Opus 5.5 is the most underrated setup... in AI right now, and i don't get why nobody's talking about it. I stopped letting Opus make every small decision in my agents. Jev makes them now. My Opus bill dropped ~500% on the same tasks, same results. Here's what Jev handles: - which files and notes to load before Opus sees anything - which effort level each task actually needs - what to do when a tool fails - which tests to run, and when to stop Opus only gets called for the hard reasoning. Every decision is a typed result the host checks before it runs. The exact prompt to set this up in your workflow is below.show more

PEOPLE ARE BURNING THROUGH THEIR TOKENS IN 30 MINUTES... AND BLAMING CLAUDE The problem isn’t with the model. The problem is how they’re using it A simple formatting question they set Max effort The 40th message in the chat the model re-reads the entire history from the beginning Every single time. Using your tokens Low effort costs 10 times less than Max Just get into the habit of routing tasks by level and your limit won’t run out by noon Tokens don’t disappear. You’re just paying for unnecessary processingshow more

Introducing Span-02: anytime reasoning for decisions. Reasoning models make... you pick an effort level and wait. Span-02 takes a deadline and always returns its best decision so far. It gets better the longer it thinks. With reasoning off, it beats Jev at 1/4 of the price, and runs at 1/3 the latency of decision models at its level. It can: - Answer with numbers and scores, not just probabilities and choices - See images and screens (multimodal) - Take a configurable reasoning time And it’s fully open weight!show more

Sonnet 5 is here. It's worse than Opus 4.8... on nearly every benchmark... Does that mean it's useless? Absolutely not. Use it with Claude Code Dynamic Workflows! 1. /model set to Sonnet 5 2. /effort set to Ultracode 3. Any complex task will kick off a dynamic workflow This will only become more powerful when Fable is back. You'll use Fable 5 as the superintelligent advisor and Sonnet 5 as the fast and efficient implementer.show more

Anthropic just published its official prompting guide for Opus... 5.5. If you're still writing prompts the way you did for Opus 5, you're paying more and getting less. Here's what changed 👇 1. Default to medium effort Medium on 5.5 already outperforms high on Opus 5, at a lower cost. Maxing it out by habit just burns tokens. 2. Drop "think step by step" Reasoning is built in now. The model decides how much thinking a task needs, so asking it to think harder adds nothing. 3. A check-in isn't a finish line On long runs, it sends progress updates along the way. If it stops to report, tell it to keep going. 4. Fence off anything you paste Put emails, docs, and web text in clearly labeled sections or tags. That way it can tell your instructions apart from the material it's working on. 5. Retire your image workarounds Those custom chart readers and OCR steps you built are probably dead weight. It reads screenshots, diagrams, and charts accurately on its own. 6. For design work, name what you don't want "Make it unique" gets you generic. "No purple gradients, no centered hero, no emoji icons" gets you something different. It follows specific bans much better than vague direction. ♻️ Repost to save someone a few API bills.show more

You don’t have to use one model (or one... provider!) for everything. With Workshop, you can combine frontier and local models in the same workflow. For example: Opus can be the main agent, and delegate specific tasks to Gemma 4 via subagents. Better quality where it matters. Better privacy, speed, and cost where it counts. One workflow, best model for each task.show more

Claude Code Scheduled Tasks is now available... here's a... solid idea to connect it with Telegram Save this so you don't forget to set it up! First, ask Claude to add a simple Telegram messaging module to your repo. You can use the Telegram Bot Builder Skill from Link: Install command: npx claude-code-templates@latest --skill enterprise-communication/telegram-bot-builder Once the module is in your project, grab your bot credentials from BotFather and add the bot ID to your .env file That's it! ✅ Now every Scheduled Task you create should end with an instruction for Claude to send the task result to Telegram using that module. Claude will handle the delivery automatically on every task it runsshow more

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."show more

I’m genuinely curious because I’ve seen this called differently... at every level. I was always taught that once your pivot foot is set, you can lift it to shoot or pass but you can’t lift it and then step through onto the other foot. Is this a travel or not?show more

AI coding agents re-explore the same codebase every single... session. Repowise indexes a repo once and gives Claude Code, Codex, or any MCP agent a real dependency graph, git history, and a bug-predictive code health score. No re-grepping the same files. No stale docs. No guessing which file is about to break. The loop is simple: measure every file > locate where the risk concentrates > generate the exact refactoring plan to fix it Indexing a repo takes under 30 seconds and updates automatically on every commit. Paired benchmarks show up to 96% fewer tokens spent loading context and 70% fewer agent tool calls, at the same answer quality.show more

Perplexity Computer in 60 seconds: 1. It's a cloud-based... AI employee that runs tasks in the background. 2. 19 models working together. Claude for reasoning, GPT-5.2 for research, Grok for speed tasks. You don't pick. It routes automatically. 3. 400+ connectors. Gmail, Slack, Notion, Salesforce, HubSpot. One click to enable each. 4. Credits, not tokens. Simple tasks cost ~30. Complex builds cost 1,000+. Vague prompts waste them. Specific prompts save them. 5. Spaces = persistent project folders. Upload context once, every task inherits it. 6. Scheduled tasks run on autopilot. "Every Monday, prep my calendar." Set it and forget it. The PRD hack alone (in the article) will save you hundreds in credits. Full breakdown in the article below.show more

Rejoice. Just following up with another quick W in... Codex You can now configure your reasoning level in plan mode separately directly from your config file. This is huge for Plus users who want to plan with high or xhigh reasoning levels, and then switch over to medium reasoning for implementation, without needing the slash command. This is a great way to save your usage limits, and now it happens automatically. Even if you're on Pro, this should make you very happy. Prior to this, it was switching you automatically to medium every time you planned, which was pretty annoying. Place this near the top of your config file: plan_mode_reasoning = "high" (or xhigh) 0.150.0 is a massive quality of life update. They're clearly listening. This time I am shouting out Charlie. 🙏show more

New Claude Sonnet 5 performs at GPT 5.5 level... 6x cheaper! We gave 4 models the same prompt: build three self-contained HTML5 canvas scenes with real physics crash demos Prompts: - A car crashes into a brick wall - A wrecking ball destroys a house - A catapult throws a rock at a castle wall Outputs: Sonnet 5: 15,047 tokens, $0.15 Opus 4.8: 23,063 tokens, $0.58 Sonnet 4.6: 25,824 tokens, $0.39 GPT 5.5: 31,152 tokens, $0.94 Sonnet 5 did as well as Opus 4.8 and GPT 5.5 on all three tests. In the wrecking ball test, it beat Opus 4.8. The cable moves smoothly and every hit connects. In the catapult test, it beat GPT 5.5. The rock always lands inside the wall. Sonnet 5 still needs better detail and graphics. But it used fewer tokens than every other modelshow more

Claude Code's new dynamic workflow is the real deal.... 🤖 Why it matters: It's not just a chain of prompts — it's an autonomous agent swarm. 1. Set model to Opus 4.8 + reasoning effort /ultracode 2. Claude detects complexity, writes orchestration script on the fly 3. Spawns a parallel fleet of coordinated subagents Operator takeaway: This is the first time I've seen an agent actually decompose and delegate autonomously without a rigid framework. Have you tried it yet? 🚀show more

THIS IS F*CKING BRILLIANT. Anthropic’s docs describe one of... the smartest ways to run Opus three models work on one task and each does only the part it’s cheapest at. start Claude Code like this: claude -> model sonnet -> advisor opus you stop paying Opus prices for work that doesn’t need Opus > Sonnet runs the session and edits the code > Haiku 5.5 searches the repo and docs, at up to 40x less per token than Opus 5.5 > Opus waits as the advisor and reads the whole session, tool calls included Claude usually calls Opus at three points: > before it locks a plan > when the same error comes back > right before it says it’s done Sonnet drives. Haiku scouts. Opus signs off and if you go one step lower, most of an agent’s day is tiny choices like picking a file or a tool, or deciding whether to retry. Jev takes those first, so Sonnet and Opus only see the moments that are really open the whole setup Sonnet runs the main session Explore on Haiku 5.5 searches and pulls docs, read-only Opus on call as the advisor give Claude Code this setup and the prompt below ↓ “Set up my Claude Code exactly like this: Main model Sonnet, advisor Opus, saved as advisorModel in my settings. One read-only subagent named exactly Explore, on claude-haiku-5-5, to replace the built-in one. One line in CLAUDE.md: ask the advisor before locking a plan, after the same error twice, and before calling a task done, not more often. Check what could turn the advisor off (CLAUDE_CODE_DISABLE_ADVISOR_TOOL, DISABLE_TELEMETRY) and only report it. Show every change as a diff first. Don’t edit anything until I say go.” before you turn it on: every advisor call re-reads the whole transcript with no cache. on a 200k session that’s about $0.80 in input, against $0.04 for a normal request. keep it to a few calls the built-in Explore agent runs on your main model unless a subagent is named exactly Explore. any other name does nothing turning the advisor on or off keeps your prompt cache. switching models rebuilds it it needs the Anthropic API, and it stays off if telemetry is disabled bookmark it before your next long sessionshow more