night-market-completion-integrity-campaign
FeaturedBind loop 'done' to unfakeable gates. Use to harden egregore/herald loops or promote completion_integrity. Not for QA gates; use night-market-validation-and-qa.
Install
Quality Score: 88/100
Skill Content
Details
- Author
- athola
- Repository
- athola/claude-night-market
- Created
- 9 months ago
- Last Updated
- today
- Language
- Python
- License
- MIT
Bundled in these plugins
Similar Skills
Semantically similar based on skill content — not just same category
false-completion-gate
Fires when a state-mutating task is about to be declared Done (success summary or completion verdict) — to catch silent success, the highest-frequency invisible agent failure where confident 'done' language hides work that never landed. Decomposes the completion into receipt-checkable assertions, then dispatches a reconciliation auditor that cross-references each claim against the session's tool-call LEDGER (did the producing action fire?) and a fresh postcondition READ-BACK of the named artifact (does the file/test/commit exist and match?), gating the Done behind a BACKED/UNBACKED/UNVERIFIABLE verdict plus a bounded repair loop. Distinct from shadow-verify, which RE-DERIVES an investigation finding's correctness — this reconciles a COMPLETION against execution receipts, never re-deriving the claim. Use before any Done/success in implementation, fix, refactor, migration, or multi-file write work. Skip text-terminal sessions (explanation, Q&A) and work that already failed loudly.
completion-gate
Use when requested behavior appears complete, remaining work is optional, perfectionism delays delivery, or the agent continues auditing, refining, testing, or researching after proof.
auto-loop
Drive a Claude Code session toward a verifiable goal until done or a hard cap fires - autonomous loop, no user intervention. Use for refactor batches, test-suite green-up runs, migration loops where success is a check command (tests, lint, custom predicate) plus a fresh-context audit. Hosts the loop intra-session via Stop hook with two-vote completion gate; supports optional Codex /goal delegation. For numeric-metric keep/discard loops, use vd:optimize-loop.