Загрузка видео...
Не удалось загрузить видео
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:... show more
49,415 просмотров • 2 дней назад •via X (Twitter)
Комментарии: 14
Advisor on Fable 5.1 and the main session on Opus 5.5 is the split a lot of long sessions needed. The three gates (plan, repeated error, before done) stop Fable from narrating every tool call. Pin those three in CLAUDE.md so a new chat does not forget them.
alpho
useful pipeline here
advisor that reads every tool call is how taste stays in the loop.
running an observer model out of band catches tunnel vision before bad patches get committed. way smarter than asking the primary model to critique its own code in the same thread
opus writing fable reading is basically pair programming with a senior who only speaks when you're about to break prod
It’s like a pilot with a second set of eyes: Opus drives, while the advisor checks the route at the moments where a wrong turn gets expensive.
Setuju sih setup dua model gini kepake banget, apalagi pas server utamanya lagi ngadat kayak sekarang, kerjaan riset langsung berhenti di tengah jalan. Btw pas advisor baca seluruh session, konteksnya nggak keburu kepotong ya kalau sessionnya udah panjang banget?
What are you building that you even need all this???
Impressive
Well said!
Opus écrit, Fable vérifie : l'orchestre est enfin complet pour coder sans faux pas
whats the actual latency hit on that, does fable add like 2s per turn
Interesting Claude Code setup for efficient AI collaboration.
![i finally mastered how to maximise my opus 5.5 usage limits... the trick: let jev choose which subagent gets each task and how much effort it should use. [here’s how i’d wire it:] claude breaks the project into tasks. jev selects from predefined worker profiles. claude applies the selected settings and dispatches the work. → main session, medium: clarify the requirements, define what “done” looks like, and prepare the tasks → builder, low: small, clearly defined tasks with existing examples or patterns → builder, medium: tasks that connect multiple parts or need decisions within the approved plan → verifier, high: check requirements, probe edge cases, and report problems for the builder to fix jev gets the task’s scope, what’s uncertain, and the consequences of failure. it chooses from the profiles allowed for that task. your approval checkpoints stay in place. paste this into your next planning session: “use opus 5.5 with jev selecting the worker and effort profile for each task. first, check that a working jev integration is available and that this environment supports separate effort settings for subagents. check for configuration or environment overrides that could prevent those settings from taking effect. if anything is missing, explain what needs wiring before proceeding. break my request into tasks with clear ownership, dependencies, relevant context, and acceptance checks. keep small related tasks together when a separate subagent would add unnecessary overhead. keep the main session at medium effort. offer jev these worker profiles: builder at low effort for small, clearly defined tasks using existing patterns; builder at medium effort for tasks that connect multiple parts or require decisions within the approved plan; verifier at high effort for checking requirements and edge cases. give jev each task’s scope, uncertainties, dependencies, and consequences of failure. only offer profiles appropriate to the current stage. validate its selection before dispatching. use the actual jev integration; don’t simulate its decisions. if it abstains or returns an invalid choice, stop that handoff and ask me. show me the task plan and proposed assignments before starting. after approval, launch the selected workers with their assigned effort settings, relevant context, file ownership, and completion checks. let me review the result before verification. the verifier may add tests but must leave implementation code unchanged. have it report what passed, what failed, and what remains uncertain. send implementation fixes back to the builder, then recheck the affected parts. if a task repeatedly fails, examine the requirements and approach before increasing effort. report available total usage, including jev calls, worker calls, retries, and verification. don’t invent missing data. compare similar completed tasks before claiming savings.” steal this 👇](https://image.24vids.com/tw-2103852115341049897/amplify_video_thumb/2103851843214614528/img/QwYdKECdjfJZgMMK.jpg)
![Anthropic just gave OpenClaw the green light Anthropic staff confirmed that CLI-based usage is sanctioned. We’ve successfully bridged the Claude Code CLI directly into the OpenClaw gateway, letting you run your entire agent fleet on your Pro/Max plan and no additional API tokens required. The Implementation: - Auth: Log in to Claude Code locally: claude auth login - Path: Grab your binary location: which claude - Bridge: Drop the path into your openclaw.json under agents.defaults: "cliBackends": { "claude-cli": { "args": [ "-p", "--output-format", "json" ], "command": " ", "input": "arg", "output": "json", "serialize": true, "sessionArg": "--session-id", "sessionMode": "existing" } }, "model": { "primary": "claude-cli/claude-opus-4-6" }, "models": { "claude-cli/claude-opus-4-6": {}, "claude-cli/claude-opus-4-7": {}, "claude-cli/claude-sonnet-4-6": {} }, The Result: OpenClaw reuses your local session IDs and subscription limits. You get the full power of Opus and Sonnet without the restricted OAuth endpoints or the API tax. They sanctioned the path. We built the bridge. Here is a video how I done it step by step:](https://image.24vids.com/tw-2046679352977580437/amplify_video_thumb/2046678940803117057/img/whpOwezqwjM1NOY5.jpg)
