Загрузка видео...
Не удалось загрузить видео
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... show more
319,285 просмотров • 2 дней назад •via X (Twitter)
Комментарии: 34
Fable draws from your same weekly quota, I'd rather use all of it using opus since it feels better to use than fable right now usage wise.
Doesn’t fable eat the weekly too? I hit 100% on weekly the other day and tried fable to see if it worked but it didn’t
Fable doesn't need to step in, it is inferior in everything to opus 5.5
I have been letting Fable plan and direct Opus until 5.5 came along. Opus is really quick now. That makes it easy to forget about Fable. The long waiting times were my biggest complaint of using Fable + subagents.
the repeat-error trigger is the part i needed. my overnight loops keep rediscovering the same broken fix at 3am and waking me up for it
J'aime cette astuce : Opus 5.5 pilote le tout pendant que Fable surveille les détails pour toi. Malin !
API key required.
Opus is better. Cleaner. Hardly touching fable rn.
solid. just note the docs say advisor timing is model-driven, so that claude.md rule is doing the real work.
Maximizing multi-agent delegation like this makes development so much more efficient.
ok buddy
This is basically model specialization without paying the expensive inference cost on every step
AI backseating AI
把好钢都用在刀刃上这招确实高明
you're still burning weekly credits though
Using the second model as a reader that only steps in at decision points is a cleaner split than running two agents on the same task. The hard part is keeping those moments few. If the advisor starts commenting on every step, the quota win disappears.
@grok come dovrei impostare questi subagenti di fable 5.1?
interesting that you have it on advisor the general version is separating available capability from active context. your system can have access to a much larger surface than what needs to participate in every turn.
Having a second model only chime in at decision points feels like a solid way to keep costs sane without losing the sanity check.
bravo but not bravo
这波算力分配省心又高效
Same idea I landed on without the advisor command. Cheap model stays in the session. Expensive model only gets the decision points
这个搭配还挺实用，就是怕旁观的比干活的还费配额。
the advisor kept asking "is this right?" so i muted it
这套分工挺省脑子，像给主力配了个场外教练
That looks interesting defenitly would love to test it out, but I'm sure my claude would mess it up either way
this post is pure gold
This is so true
advisor is just polite for don't burn opus
this seems smart but also like it's overindexing on something. I'm not sure what.
メインモデルとアドバイザーを分けて、クォータを無駄にしない運用は本当に参考になります。3つの介入タイミングも試してみます。ありがとうございます!
woah bro, setting this up right now
Don’t do this, it is not needed
sounds like a decent setup. gotta see if fable 5.1 throws any curveballs while opus keeps grinding. 🤔
![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)
![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)
