quality-pipeline

quality-pipeline is a skill for Claude Code from cookys/autopilot. It costs 117 tokens per session (3,854 once invoked), scanned B, original, MIT.

A pre-commit and pre-merge review workflow that runs tests, checks for unfinished code, checks that tests were not weakened, and reviews the code.

In plain words
What is it for?
Checking whether a change is ready to commit or merge, investigating test failures, scanning for incomplete implementation, and performing a structured code review.
Why use it?
It gathers the checks needed before code is committed or merged, including looking for stubs, TODOs, mocks, missing work, and invalid test changes.

Skill for Claude Code

Written for Claude Code: dynamic context !`command`. Also seen: mentions subagents; mentions Claude Code.

Needs its repository: it reads a path above its own folder, which exists only inside the repository. The line is Routing overlap? If this intent better matches a sibling skill, redirect per [references/routing-tiebreaks.md](../../references/routing-tiebreaks.md) (prefer pr.

Part of the autopilot plugin — 33 skills, 3 agents, 7 hooks shipped together

Good fit Checking whether a change is ready to commit or merge, investigating test failures, scanning for incomplete implementation, and performing a structured code review.

Compare 6 skills from other repositories ↓
Install

Getting it into your agent

It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.

Clone the repo
git clone --depth 1 https://github.com/cookys/autopilot
agentmods
npx agentmods add skills/cookys/autopilot/quality-pipeline

Made for: Claude Code.

Or install autopilot, the plugin that ships this one along with the rest of its 33 skills, 3 agents, 7 hooks.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for quality-pipeline

README.md
[![agentmods](https://agentmods.dev/badge/skills/cookys/autopilot/quality-pipeline/github.svg)](https://agentmods.dev/skills/cookys/autopilot/quality-pipeline)
Your own site
<a href="https://agentmods.dev/skills/cookys/autopilot/quality-pipeline"><img src="https://agentmods.dev/badge/skills/cookys/autopilot/quality-pipeline/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for quality-pipeline

Your own site · 80×15
<a href="https://agentmods.dev/skills/cookys/autopilot/quality-pipeline"><img src="https://agentmods.dev/badge/skills/cookys/autopilot/quality-pipeline.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 117 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,854 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 1 finding. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00117 $0.03854
Opus 5 $0.00059 $0.01927
Sonnet 5 $0.00023 $0.00771
Haiku 4.5 $0.00012 $0.00385

Measured 9d ago against content hash a5a4de8874d4, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade B, and why

quality-pipeline scanned grade B with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 9d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Reads agent configuration directoriesmediumAgent snooping

.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.

!`cat .claude/quality-gate-config.md 2>/dev/null || true`
evals/skill-onoff/packs/companions/quality-pipeline/SKILL.md · 213 lines

How it starts

The opening of the file, as written. The whole thing — 213 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Quality Pipeline (Unified Quality Gate)

Routing overlap? If this intent better matches a sibling skill, redirect per references/routing-tiebreaks.md (prefer pre-merge gate failures over manual debugging).

Pipeline is a dispatcher. Each step follows its reference doc.

Project Config (auto-injected)

!cat .claude/quality-gate-config.md 2>/dev/null || true !cat .claude/dispatch-config.md 2>/dev/null || true

Sub-step References

Available Scripts (prefer over LLM judgment)

Each script encodes a step the pipeline previously asked the LLM to do by hand. Use them; the JSON output is stable across rounds and cheap to consume.

Script Replaces LLM-judgment for When invoked
scripts/completeness-scan.sh Anti-stub regex pass + new-vs-pre-existing classification Completeness Gate step
scripts/error-path-scan.sh L0 attention-slip scan for error paths (swallowed errors, broadened catches, untested error paths) Completeness Gate step (advisory to review)
scripts/secret-scan-diff.js L0 attention-slip scan for leaked secrets Completeness Gate step (blocking)
scripts/adjudicate-findings.js "Is this finding real / repair-eligible?" — probe-backed statuses; gate --ids = claim-real; dispose + repair-gate --ids = relevance (must-fix-now); completeness = all-blocking Critical/Major dispositions over the full registry Review step: verify → classify → completeness before fix dispatch and before acceptance
scripts/review-mvp-portfolio.js Bounded multi-reviewer candidate union → verified MUST-FIX/prerequisite admission + deterministic fixed-budget maximum-score MVP, cut list, and evidence-backed backlog candidates After a panel returns a complete scored candidate matrix; canonical contract: references/reviewer-mvp-portfolio.md
scripts/check-repair-scope.js Cumulative repair stop-loss — sealed contract (seal --out + check --seal), full base_sha..HEAD churn/path/new-file accounting; TRIP ends automatic repair Before fixer, after every repair mutation, and before acceptance
scripts/check-redispatch-prompt.sh Round 2+ leaky-phrase detection (per references/blind-dispatch.md) Before every re-review dispatch
scripts/diff-file-list.sh Reviewer's "list every file I read" enumeration in Verified Clean Reviewer prompt assembly
scripts/diff-scope-report.sh v2 scope-creep filter: whitespace-only files, files not in message, comment-only hunks, quote-style swaps Code Review step (Scope Creep Scan)
scripts/resolve-dispatch.sh Per-dispatch model/mode lookup against model-routing-config.md Any subagent dispatch
scripts/check-holdout-coverage.sh Holdout gate: high-risk diffs (classify-diff-risk.sh adversarial_review) require a SHA-bound passing mutation/strength probe receipt; absent/malformed/stale/failed fail closed After impl, before merge, when the risk classifier reports high — check --range <base..head> --evidence-dir <dir> (receipts via run)
scripts/check-test-integrity.sh "Did the implementer game the tests?" — deleted / skipped / soloed / weakened existing tests, escaped fixtures/config (see references/test-integrity-gate.md) After impl, before merge — esp. delegated / /l5 hetero dispatch
scripts/verify-preexisting.sh Stash + checkout-base + run-test classification Test Failure Investigation step
scripts/verify-red-green.sh Red-green validation: a change's tests must be GREEN at head and RED at base+tests (else they don't exercise the change) — isolated detached worktrees, verdict from real exit codes When judging whether new tests actually test the change (see references/test-policy.md)
scripts/reap-dispatch-worktrees.sh Exact schema-2 worktree state classification and preserve-first dead/clean reclamation Before closing a managed root run; check blocks while exact owned worktrees remain
scripts/lifecycle-residue-receipt.js Issue or freshness-check exact worktree/branch residue evidence Before handing lifecycle truth to LSM; a valid receipt does not itself compute can_close
scripts/risk-counter.js Cross-round WTF-Likelihood Cap state tracking Self-Regulation section
scripts/diff-since-last-round.sh Round-N checkpoint + delta-since-checkpoint (dispatcher-only) Re-review Loop short-circuit decision
scripts/qc-panel.js Cross-family interrogation panel (shadow mode, task-tree engine) Shadow QC panel section below
scripts/calibration.sh Panel verdict sample store + agreement report Shadow QC panel section below
scripts/resolve-qc-gate.sh Per-project anti-skip gate strength (block/warn/off) for the .githooks/pre-push enforcer On PASS, stamp the landing/merge commit with QC-Verdict: PASS (reviewer <id>, <date>) so the pre-push gate is satisfied

Read the full file on GitHub · 213 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 9d ago First seen · 213 lines · 117 tokens per session scan B a5a4de8874d4

Subscribe to this mod's changes

quality-pipeline is a skill published in the GitHub repository cookys/autopilot (11 stars, last pushed yesterday), licensed MIT. It adds 117 tokens to every session and 3,854 once invoked, about $0.0006 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other skills, from other repositories