Run fable-mode execution discipline on Claude Fable 5.1 — the top of the escalation ladder and the strongest staged run available. Routes the task to the @fable-orchestrator agent with its model overridden to Fable (`model: "fable"`), which stages the work, delegates artifact production to @fable-worker-sonnet / @fable-worker-haiku, and cold-checks deliverables with @fable-verifier. Trigger when the user explicitly asks for thorough/systematic/"deep work" handling on the strongest model ("fable on fable", "stage this on fable", "deep work mode, fable", "run this on 5.1"), or when a fable-opus run reports the task exceeds Opus's ceiling. Benchmarked 2026-09-02: zero correctness delta on Fable 5.1 at ~1.1× tokens, ~2× wall — a provenance runner, not an accuracy runner. Do NOT use for ordinary single-pass tasks — prefer fable-opus, fable-sonnet, or fable-haiku when the task doesn't need peak reasoning. Fable is plan-included; bulk work still routes down-tier.
中文简介正在准备中。当前显示原文说明。
查看安装方法安装前可以查看交给 AI 代理的指令内容。
Same structural delegation as fable-opus: the orchestrator is a real agent
definition (agents/fable-orchestrator.md) with no Write/Edit tool, so it
cannot do the work inline. The only difference from fable-opus is the model the
orchestrator runs on. Fable 5.1 is the top of the ladder (Haiku → Sonnet → Opus
→ Fable → user); gaps it cannot close go to the user.
Fable 5.1's characteristic gaps under this discipline: none measured (benchmarked 2026-09-02, 16 paired runs, n=2 per cell: 100/100 in every cell, both arms; skill cost ~1.1× tokens, ~2× wall). This is a provenance runner — worklog, reproducible checks, flagged judgment calls — not an accuracy runner. The orchestrator definition keeps the frontier-tier guards (external-artifact verification, scope rule, replan budget) because those produce the trail.
If a task has one obvious correct approach and fits in a single pass, skip this loop and do it directly. On a Fable-class model the stage map is ceremony for anything short of multi-session or many-file work.
fable-orchestrator,
fable-worker-sonnet, fable-worker-haiku, fable-verifier appear in the
available agent types) AND the Agent/Task tool accepts model: "fable".
model: "fable" and pass it the Core loop and operational
rules verbatim from agents/fable-orchestrator.md."fable" not accepted as a model → say so and run fable-opus instead.model override is documented for Claude Code
(code.claude.com/docs/en/sub-agents: "the per-invocation model
parameter" outranks the definition's frontmatter; fable is a listed
alias) and confirmed on the Cowork Agent tool. On a runtime that lacks
it, copy agents/fable-orchestrator.md to
agents/fable-orchestrator-fable.md, set name: fable-orchestrator-fable
and model: fable, and route to that instead.subagent_type: "fable-orchestrator", model: "fable"). Brief it with: the user's task,
the output directory, relevant session context, and any user-set limits
(warning threshold, worker cap, deadline).Same side door as fable-opus: the orchestrator keeps Bash for verification commands, and Bash can technically create files. Its definition forbids that use.
还没有评价。欢迎分享你的使用感受。
无需登录即可发表。欢迎分享使用感受、提问，或说明在哪些环境下无法运行。
还没有评论。来写第一条吧。
Automatic final verification pass on completed deliverables. Runs at the end of every fable-mode run — those skills invoke it before delivery. Also triggers when the user says "double check this". Uses a panel of fresh checker agents when spawning is authorized (otherwise a cold self-check) to verify the finished output — not to redo the task. Any FAIL gets fixed and re-checked before delivery.
中文简介正在准备中。当前显示原文说明。
Always-on operational guardrails, model-independent. Apply on EVERY task and EVERY model whether or not fable-mode's staged loop is running. Three rules: verify-before-flag, warning batching, and find-and-replace safety. Trigger whenever a response would flag a problem, raise a warning, or edit files with search-and-replace.
中文简介正在准备中。当前显示原文说明。
Run fable-mode execution discipline on Claude Haiku. Routes the task to the @fable-worker-haiku agent, whose definition carries the staged loop with tightened verification (no bare "unverified" allowed) and an escalate-don't-improvise rule. Trigger when the user explicitly asks for thorough/systematic handling run cheaply or fast ("fable on haiku", "deep work mode but cheap", "stage this on haiku"). For bulk mechanical work. Do NOT use for tasks needing synthesis — benchmark note: at n=1 the skill's effect on Haiku swung both directions (+25 / −17); route quality-critical work to fable-sonnet instead.
中文简介正在准备中。当前显示原文说明。
Enforces staged execution discipline on large tasks: a written stage plan, parallel delegation where the runtime supports it, a failable verification check at each stage, and a skeptical self-review before delivery. Trigger when the user explicitly asks OR when the task objectively spans multiple files, sources, or sessions. Do NOT trigger on ordinary multi-step requests that a direct attempt handles fine (autonomous triggering only; explicit invocation always runs).
中文简介正在准备中。当前显示原文说明。
Run fable-mode execution discipline on Claude Opus — the top of the escalation ladder. Trigger when the user explicitly asks for thorough/systematic/"deep work" handling on Opus ("fable on opus", "stage this on opus", "deep work mode, opus"). When a task exceeds Opus's ceiling, report that to the user rather than escalating further.
中文简介正在准备中。当前显示原文说明。
Run fable-mode execution discipline on Claude Sonnet. When invoked by slash command or by name, spawns a Sonnet subagent that follows the staged loop — stage plan, parallel delegation, a failable verification check at each stage, and a skeptical self-review before delivery; a wording-only request runs the loop inline on the current model. Trigger when the user explicitly asks for thorough/systematic/"deep work" handling on Sonnet.
中文简介正在准备中。当前显示原文说明。