quality

quality is a skill for Claude Code from pnmcguire480/cairntir. It costs 141 tokens per session (3,756 once invoked), scanned A, original, MIT.

A quality gate that checks whether a project follows its specification and scores its overall health across six levels. It requires every finding to cite the file, line, expected result, actual result, and verdict.

In plain words
What is it for?
It is for testing specification compliance, reviewing project health, and deciding whether a project is ready to ship.
Why use it?
It prevents claims about code quality from being accepted without direct evidence and stops work when required checks fail.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: mentions CLAUDE.md; mentions AGENTS.md.

Part of the cairntir plugin — 2 skills, 3 commands shipped together

Good fit It is for testing specification compliance, reviewing project health, and deciding whether a project is ready to ship.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/pnmcguire480/cairntir/quality
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent
npx skills add pnmcguire480/cairntir --skill quality
Clone the repo
git clone --depth 1 https://github.com/pnmcguire480/cairntir

Made for: Claude Code.

Or install cairntir, the plugin that ships this one along with the rest of its 2 skills, 3 commands.

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

README.md
[![agentmods](https://agentmods.dev/badge/skills/pnmcguire480/cairntir/quality/github.svg)](https://agentmods.dev/skills/pnmcguire480/cairntir/quality)
Your own site
<a href="https://agentmods.dev/skills/pnmcguire480/cairntir/quality"><img src="https://agentmods.dev/badge/skills/pnmcguire480/cairntir/quality/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

Your own site · 80×15
<a href="https://agentmods.dev/skills/pnmcguire480/cairntir/quality"><img src="https://agentmods.dev/badge/skills/pnmcguire480/cairntir/quality.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 141 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,756 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. 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 $0.00141 $0.03756
Opus 5 $0.00071 $0.01878
Sonnet 5 $0.00028 $0.00751
Haiku 4.5 $0.00014 $0.00376

Measured 4d ago against content hash 40a2377d6c33, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

quality scanned grade A with 0 findings 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 4d 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.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

lineage/brainstormer/quality-SKILL.md · 369 lines

How it starts

The opening of the file, as written. The whole thing — 369 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Quality (PALADIN) — Ship Gate

The Principle

Nothing ships unexamined. Catch the dumbest problems first so you never waste time debugging a subtle race condition when the real issue was a typo. Each tier is a gate. If a gate fails, you stop, fix, and re-run. You do NOT skip ahead.

Evidence Before Claims

Every PALADIN finding — at any stage, any tier — must cite evidence. Not summaries. Not impressions. The actual proof.

Required for every finding:

  1. File and line — where the issue lives
  2. Expected — what the spec, standard, or convention requires
  3. Found — what actually exists in the code
  4. Verdict — PASS, FAIL, or WARN with the specific gap stated

Why this rule exists: LLMs are confident. Confidence is not evidence. A model can say "the auth middleware correctly validates tokens" without having read the middleware. PALADIN does not accept claims. It accepts file paths, line numbers, and diffs between expected and found.

The enforcement: If a Stage 1 or Stage 2 check cannot produce a file:line citation for a finding, that check is INCOMPLETE, not PASS. Absence of evidence is not evidence of compliance.


TRIGGER

  • "test", "QA", "ship it", "deploy", "is this ready"
  • "paladin", "quality check", "quality audit", "run quality"
  • brainstormer quality run (CLI command)

ANTI-TRIGGER — do NOT fire Quality when:

  • Explaining code → use Comprehension
  • Generating ideas → use Ideation
  • Visual/UI direction → use Design
  • Research/experimentation phase → use Auto-Research
  • Already passed a formal third-party audit → note it, don't re-audit

INPUT CONTRACT

Input Source Required?
Project codebase Filesystem scan Yes
CLAUDE.md Project root Recommended
ARCHITECTURE.md Project root Optional (integrity checks)
paladin.config.json Project root Optional (custom thresholds)
.brainstormer-quality-history Project root Optional (trend data)
Pattern registry docs/codeglass/patterns.md Optional (anti-patterns)
CRUCIBLE falsifiable claims From CRUCIBLE Phase 3 Optional (→ test cases)

Read the full file on GitHub · 369 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. 4d ago First seen · 369 lines · 141 tokens per session scan A 40a2377d6c33

Subscribe to this mod's changes

quality is a skill published in the GitHub repository pnmcguire480/cairntir (2 stars, last pushed yesterday), licensed MIT. It adds 141 tokens to every session and 3,756 once invoked, about $0.0007 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-04.