opsmill/nornir-infrahub / .agents/skills/quality-gates
quality-gates
VerifiedShared in-workflow quality gates for code/PR skills — the gate model, trust tiers, and the three primitives (evidence-before-done, independent judge, anti-gaming). DO NOT TRIGGER directly — referenced by consumer skills via relative path.
| File | Kind | Size |
|---|---|---|
| DECISION.md | markdown | 1.4 KB |
| SKILL.md | skill md | 4.7 KB |
| evals/evals.json | config | 2.5 KB |
| gates/_index.md | markdown | 387 B |
| gates/gate-model.md | markdown | 3.2 KB |
| gates/primitives/anti-gaming.md | markdown | 1.8 KB |
| gates/primitives/evidence-before-done.md | markdown | 546 B |
| gates/primitives/independent-judge.md | markdown | 3.8 KB |
| hooks/ship-gate-check.shexecutable | script | 4.3 KB |
DECISION.md
View on GitHub# DECISION.md — quality-gates ADRs
## ADR-001: In-workflow quality gates over louder prompts
**Context:** Every skill `MUST`/`STOP` is a prompt the agent may ignore; the repo has no hook/CI
enforcement. **Decision:** the critical steps become gates (independent verification + evidence +
STOP-on-fail). **Alternatives:** louder markdown (still a prompt); programmatic hooks (Claude-only,
won't port to Codex). **Consequences:** more deliberate friction at critical steps (Pattern 7).
## ADR-002: Author≠judge via a fresh subagent (P2)
**Context:** a passing self-check proves the author agrees with itself. **Decision:** ship gates
dispatch a fresh subagent given the ORIGINAL criteria (R1), never the author's summary.
**Consequences:** self-certification is impossible at ship gates; ~2x work at those points.
## ADR-003: Hybrid judge by gate purpose
**Decision:** full subagent on irreversible ship gates; lighter fresh-context re-read on
intermediate verify gates. **Consequences:** rigor concentrated where reversal is impossible.
## ADR-004: opsmill-dev is the canonical copy (R3)
**Context:** plugins ship independently, so the reference is duplicated. **Decision:**
`opsmill-dev/skills/quality-gates/` is canonical; `opsmill-repo`'s is a synced copy;
divergence resolves to software. **Consequences:** maintenance must update both; a cross-plugin
drift check is deferred (YAGNI).
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis. | Stars: 472k | Updated | Claude CodeCodex | Verified | Install |
| diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness. | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| executing-plansobra/superpowersUse when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is available | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |