fable-harness

Templates and risk-tier evolution policy for authoring new agents, skills, and hooks — the 3 artifact kinds this harness produces (no "mcp" kind; this harness has no MCP). Used primarily by meta-agent when extending the harness. Auto-invocable.

Reference-only skill documenting where artifacts live, the 3-verdict vocabulary (pass/pass-with-notes/reject), and the Preserved-Invariants-vs-Changed-Behaviors contract for revising an existing artifact. Load before writing or revising any artifact under .fable/. Auto-invocable.

Show CONSTITUTION.md's content and invariant list on request, re-run the SHA-256 hash check against CONSTITUTION.sha256 on demand, and document the amendment procedure. Useful for Claude to consult proactively as well as for a user to invoke directly.

Merge-safe installer that makes FABLE-HARNESS's agents/skills/hooks available at Claude Code's user scope (~/.claude), so they work across every project, not just H:\FABLE-HARNESS. Manual-only — never auto-invoked, since this touches shared, hard-to-reverse state outside this project.

Canonical model-tier reference and the Fable-5 manual-only enforcement protocol. Consult before writing or changing any model field (agent frontmatter, skill frontmatter, Task dispatch parameter, settings.json availableModels, env vars). Auto-invocable — any agent or skill authoring a new artifact should load this first.

Highest-stakes planning skill using Fable-5. Manual-only — Claude can never auto-invoke this; only a user typing /plan-deep can. Use for the small number of asks big enough to warrant Fable-level structure and thinking budget (major-scope architecture, cross-cutting rewrites, irreversible decisions).

Everyday, auto-invocable planning skill for routine feature/bug/refactor work. Sonnet-tier — the non-Fable default. Use for most planning needs; escalate to /plan-deep (manual-only, Fable-5) only for the rare highest-stakes plan.

Run one of the 10 standing governance-forum reviews (taxonomy_blueprint.md Section 8.2 — discovery, scope, design, architecture, api_contract, threat_privacy, test_readiness, release_readiness, incident_postmortem, service_review) over an existing artifact or change. Auto-invocable when a user asks for a focused review pass rather than new production. The actual orchestration lives in .claude/workflows/review.js, invoked here via the Workflow tool.

Run a request through the full FABLE-HARNESS lifecycle (triage -> profile -> taxonomy -> generate per section -> judge -> verify -> missability -> finalize). Auto-invocable for substantive feature/bugfix/refactor requests; the actual orchestration logic lives in .claude/workflows/run.js, invoked here via the Workflow tool.

Maps a request to one or more of the 16 taxonomy_blueprint.md sections (4.1-4.16), enforcing the taxonomy-mapping-with-floor rule — even trivial requests get a floor artifact. Delegates the actual mapping decision to the taxonomy-mapper agent and persists the result to .fable/<run_id>/taxonomy_map.json. Auto-invocable.

Dispatches the independent verifier agent, enforces Reflexion x1 (one retry-with-critique per stage) and bounded-retry-then-escalate at 3 total verify loops. This is what /verify invokes and what the Stop hook ultimately points at. Auto-invocable.