fable-opus
Run fable-mode execution discipline on Claude Opus — one rung below Fable 5.1 on the escalation ladder. Routes the task to the @fable-orchestrator agent (Opus, Write-less), 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 Opus ("fable on opus", "stage this on opus", "deep work mode, opus"). Escalate to fable-fable when the orchestrator reports the task exceeds Opus's ceiling. Do NOT use for ordinary single-pass tasks — and prefer fable-sonnet or fable-haiku when the task doesn't need peak reasoning.
How do I install this agent skill?
npx skills add https://github.com/mrtooher/fable-mode --skill fable-opusIs this agent skill safe to install?
- Gen Agent Trust Hubpass
The skill defines a multi-agent orchestration workflow for complex tasks. It includes design-level security notes regarding tool access but contains no malicious code, obfuscation, or external dependencies.
- Socketpass
No alerts
- Snykpass
Risk: LOW · No issues
What does this agent skill do?
Fable Mode — Opus (v3, agent-routed)
v3 change: delegation is enforced structurally, not requested in prose. The
orchestrator is a real agent definition (agents/fable-orchestrator.md) with no
Write/Edit tool — it cannot do the work inline, so "spawn a worker" stops being
a suggestion the model can skip. (Change prompted by field report: prose-level
"you may spawn workers" almost always ran inline on the main thread.)
If a task has one obvious correct approach and fits in a single pass, skip this loop and do it directly.
How to run it
- Confirm the fable agents are installed (
fable-orchestrator,fable-worker-sonnet,fable-worker-haiku,fable-verifierappear in the available agent types). If they are not, fall back to the inline method: spawn a general-purpose Opus agent and pass it the Core Loop, domain patterns, and operational rules verbatim from the fable-mode skill, which is installed alongside this one. Do NOT try to readagents/fable-orchestrator.md— agent files exist only on surfaces that load anagents/directory (Claude Code), never on skill-only surfaces (Cowork), which is exactly where this fallback fires. - Spawn @fable-orchestrator via the Task tool (
subagent_type: "fable-orchestrator"). Brief it with: the user's task, the output directory, relevant session context, and any user-set limits (warning threshold, worker cap, deadline). - Do not restate the Core Loop or operational rules in the briefing — the orchestrator's agent definition carries them. Brief the task, not the method.
- When it returns, relay the result, every stage it marked unverified, and its recommendations (surfaced scope it did not build). If it reports the task beyond Opus's capability, offer a fable-fable rerun (Fable 5.1) rather than retrying Opus.
- Mandatory delivery gate: before presenting the result to the user, invoke
the double-check skill on the finished deliverable. Pass it the
orchestrator's closing
FINAL-COLD-CHECK:line verbatim —yesmeans fable-verifier already checked the finished deliverable and double-check runs the seam check only;intermediates-only,no, or a missing line means the full panel runs. Do not skip the gate; the user relies on it instead of re-checking the work themselves.
Known limitation
Write-removal closes the front door, not the side door: the orchestrator keeps Bash for running verification commands, and Bash can technically create files. Its definition forbids that use; if audits show it writing through Bash, the next tightening is removing Bash and routing even check-execution through workers (cost: one extra hop per check).
How can the creator link this skill?
Add the canonical catalog link to the repository README so users can inspect current installs and available audits. The publishing guide covers the complete discovery path.
<a href="https://skillzs.dev/skills/mrtooher/fable-mode/fable-opus">View fable-opus on skillZs</a>