跳至正文
OpenAgentSkill
浏览已开放 · 目录记录日期 2026-11-21 · 自动更新和账户服务暂时关闭。
开发与测试

night-market-change-control

Classify, gate, and review changes. Use when landing a PR, releasing, or amending rules. Do not use for failure triage; use night-market-debugging-playbook.

athola · 已有 AI 审核记录

安装与使用

运行命令前先阅读来源与依赖说明。复制命令不会自动安装或执行。

npx skills add athola/claude-night-market --skill night-market-change-control

技能说明


name: night-market-change-control description: 'Classify, gate, and review changes. Use when landing a PR, releasing, or amending rules. Do not use for failure triage; use night-market-debugging-playbook.'

Night Market Change Control

Every change to this repo passes through a fixed law stack, a classification step, and a gauntlet of automated gates. This skill tells you which class your change is, which gates it must pass, and which rules are non-negotiable because a past incident made them so. Nothing here may be routed around: if a gate fails, fix the cause, never the gate.

Jargon used below: a "gate" is any automated check that can block a commit, PR, or release. An "ADR" is an Architecture Decision Record in docs/adr/. The "Iron Law" is constitution rule 3: no implementation without a failing test first.

The law stack

When two documents conflict, the higher one wins.

RankSourceContents
1CONSTITUTION.md10 immutable rules, override and amendment process
2.claude/rules/8 project rules (markdown style, read budgets, slop gates, invariants)
3docs/adr/17 numbered decision records (0001 to 0017)
4Guides in docs/quality-gates, testing-guide, plugin-development-guide

A skill, hook, or agent instruction that says "skip rule N" without an explicit user grant or a merged amendment is itself a defect (CONSTITUTION.md, Override mechanism section).

The ten constitution rules

One line each. Where a rule was written in blood, the incident column names the blood.

#RuleMotivating incident
1Disclose AI involvement in every PR; never strip real or add fake AI attributionEnforced by hook plugins/imbue/hooks/vow_no_ai_attribution.py
2AI commits over 200 changed lines need a spec, ADR, or plan doc first (lockfiles, fixtures, snapshots excluded)Size = scrutiny principle; see the unbloat incident under non-negotiables
3Iron Law TDD: failing test before implementation for plugin Python. Skills and prose need structural tests (test_skill_<name>.py)Design principle, no single incident
4One identity leak ("As a large language model") in any committed artifact is an automatic revertPattern catalog in scribe slop-detector
5Quality claims ("fast", "production-ready") need in-repo evidence or deletionDesign principle
6No bypassing gates: no --no-verify, no SKIP=hook, no unauthorized force push, no bare suppression comments without a stated reasonNeutered-mypy incident (CHANGELOG 1.9.12); bulk-ignore revert 06b9b1db
7New dependencies need justification; 18 months unmaintained is presumed abandoned; verify AI-suggested package names against the registrySlopsquatting defense; hook guard_package_hallucination.py (imbue)
8Docs cost reader-time (audience x frequency x per-read time); writing effort must matchDesign principle
9Prefer deletion over rewriting; AI slop is overwhelmingly additiveDesign principle
10Errors are not optional: propagate by default, no bare except, safe-to-discard needs an inline "why" commentSilent-failure sweep 666171c3; ecosystem bare-except campaign

Change classification

Classify before the first commit. The class decides the paperwork.

ChangeRequired process
AI-generated diff, 200 changed lines or fewerPlain PR through the standard gates
AI-generated diff over 200 changed linesSpec, ADR, or planning doc BEFORE the code (rule 2)
Load-bearing design decisionNumbered ADR in docs/adr/ (next number after 0017)
New project-wide ruleNew file in .claude/rules/ via plain PR; existing rules cite an origin issue or discussion (#454, #457)
Constitution amendmentPR titled constitution: amend rule N, a summary of what changes and why, sign-off from the repo owner
ReleaseVersion bump, changelog section, v-prefixed tag (lifecycle below)

The change lifecycle

1. Branch

Branch from master (the main branch) using <topic>-<version>:

git checkout master && git pull
git checkout -b my-topic-1.9.16

Live examples in git branch -a: ai-slop-1.9.4, bugfixes-1.9.5, discussions-fix-1.9.14. Never delete backup/unbloat-* branches. They are the recovery points for past deletion campaigns (backup/unbloat-20260328 is how the 2026-03-28 over-deletion was undone).

2. Local gates before committing

make lint          # ruff format + ruff check --fix + bandit
make typecheck     # per-plugin strict mypy (all plugins)
make test          # per-plugin pytest via scripts/run-plugin-tests.sh
make validate-all  # plugin structure validation

Plugin tests MUST run per plugin (make <plugin>-test or make -C plugins/<plugin> test). Root pytest excludes plugins/* to avoid import-path collisions.

3. The pre-commit gauntlet

git commit runs .pre-commit-config.yaml hooks in this order (verified 2026-07-02):

  1. Suppression guards: check-noqa (blocks bare inline lint suppressions), check-docstring-quality, check-json-utils-drift, check-per-file-ignores.
  2. Hook registration: check-hook-registrations, check-plugin-hooks.
  3. Code gates: run-plugin-typecheck --all (strict mypy on every plugin, not just changed ones), run-plugin-tests --changed.
  4. Skill and plugin validation: validate-skill-descriptions, one validate-<plugin>-plugin hook per plugin, check-context-optimization, validate-description-budget, check-markdown-links, capabilities-sync-check, check-skill-graph-drift, check-skill-exit-criteria-drift.
  5. Standard file hygiene (trailing whitespace, YAML/TOML/JSON syntax, merge conflicts, debug statements).
  6. bandit security scan.
  7. ruff-format, ruff-fix, ruff-check.
  8. Pin freshness: check-ruff-version, check-pinned-versions.

The typecheck gate

阅读完整来源 ↗