From mycelium
Verifies features/stories meet Definition of Done criteria via checklists for functionality, code quality, testing, and security before completion.
How this skill is triggered — by the user, by Claude, or both
Slash command
/mycelium:definition-of-doneThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
DoD checklist enforcement.
DoD checklist enforcement.
Before checking any item below as DONE, perform a completion audit against the actual current state, not against intent or memory:
Do not rely on any of the following as proof of completion:
These clauses address two documented Mycelium failures: Eval Overfitting (2026-04-30 — agent encoded eval answers into documentation to "pass," gaming the proxy instead of checking the criterion) and SessionStart relay leak (2026-05-02 — agent declared turns complete while skipping protocol steps). Borrowed from OpenAI Codex /goal continuation template's completion-audit specification (logged 2026-05-03).
docs/adr/ was scaffolded by /mycelium:delivery-bootstrap)npx claudepluginhub haabe/mycelium --plugin myceliumValidates completed work across all dimensions: code quality, test coverage, security review, documentation, accessibility. This is the intersection of all roles' acceptance criteria.
Performs comprehensive quality audits verifying planning conformance, DDD validation, security checks, tests, browser verification, and metrics before deployment or PR merge.
Runs pre-implementation validation checklist before delivery work, checking constraints, scope, context, tech readiness, security, accessibility, and validation strategy.