AGENT SKILL

drift-detection

暂无简介

License 许可
Apache-2.0
最近更新
2026-11-09
Stars
★ 0
Forks
0

02 资源文件 1

03 SKILL.md 正文

Drift detection — code-side bypass scanner (F-4)

Architecture §3 F-4: "Drift-detection skill: post-commit scan for // rubric: ignore, --no-verify, repeated bypass; tracks E-5 inline suppressions."

What it scans

  • Inline-comment bypass — any source file containing the comment // rubric: ignore (case-insensitive, EOL or anywhere on a line). Repeated occurrences in a single file are counted; the count crosses an operator-set --repeated-bypass-threshold to escalate the finding.
  • --no-verify commit bypass — git log scan for commits whose messages signal pre-commit hooks were skipped. In --post-commit mode the scan is limited to HEAD; otherwise the whole reachable log is scanned.
  • E-5 inline suppression tracking — reads rubric/suppressions/<rule-id>.jsonl (the per-rule E-5 suppression log emitted by rubric/detectors/inline-suppression.sh) and surfaces per-rule suppression counts in the same report.

Output

One JSON object per line to --out <file> (JSONL — stream-parseable). Each line carries type, path (or commit), and count; escalated findings include severity:"escalated".

Dry-run

--dry-run computes the same findings but does not write the report file. The stderr summary includes dry_run=true for traceability.

Exit codes

  • 0 — clean scan (no bypasses, or --dry-run regardless of findings).
  • 2 — bypasses found in the scanned scope (gates /pr and /feature in the W-2 / W-8 push-timing decision).

04 同仓库更多 Skills

drumfiend21
drumfiend21/claude-tdd-pro

test-first-extract

Use when the user asks to EXTRACT or RELOCATE existing code into its own file, module, or component ("extract X", "split out Y", "pull Z into its own file", "decompose god-file"). NOT for net-new features (use tdd-feature-build) or behavior changes (use fix-bug). Enforces the 9-step extraction with isolated unit tests + integration regression tests as a two-tier safety net.

★ 0
drumfiend21
drumfiend21/claude-tdd-pro

tdd-feature-build

Use when the user describes a NEW feature to add ("add X to Y", "implement Z", "build a feature that…", "make it possible to…"). Enforces TDD — failing test first, minimum code to pass, refactor. Refuses to ship code without a test that demonstrably catches its absence. Does NOT trigger on bug fixes (use bug-fix-discipline) or refactors (use test-first-extract). Will ask 1-3 clarifying questions before writing any code; safe to delegate from /feature command.

★ 0
drumfiend21
drumfiend21/claude-tdd-pro

sync

Multi-machine git-backed sync of local TDD Pro state via the `tdd-pro-sync` branch. Use when operators run claude-tdd-pro on more than one machine and want their FAILURE-LOG, decisions, audit checkpoints, workflow state, operator-curated URL registries, operator/community trees, and paywalled attestations to follow them between hosts.

★ 0
drumfiend21
drumfiend21/claude-tdd-pro

strict-component-tests

Use when writing or reviewing test files. Enforces strict assertions that actually catch regressions (getByRole, exact counts, jest-dom matchers) in contrast to permissive tests (queryAllByText length > 0) that pass against broken UIs. References QUALITY-BAR.md for the canonical strictness rules.

★ 0
drumfiend21
drumfiend21/claude-tdd-pro

spec

暂无简介

★ 0
drumfiend21
drumfiend21/claude-tdd-pro

spec-first

Use when the user describes a non-trivial feature or system that should be specified in writing before any code is written. Pattern from Geoffrey Huntley's "Ralph" loop, OpenSpec, intent-driven.dev, and Kent Beck's "augmented coding" framing — specs+tests are the durable artifact, code is the disposable one. Produces a Markdown spec document that the user reviews; only after approval does any code get written (typically via tdd-feature-build or /feature).

★ 0