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.
npx skills add pnmcguire480/cairntir --skill qualitygit clone --depth 1 https://github.com/pnmcguire480/cairntirWrote 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.
[](https://agentmods.dev/skills/pnmcguire480/cairntir/quality)<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.
<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>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.
| Model | Per session | Once 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 |
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.
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:
- File and line — where the issue lives
- Expected — what the spec, standard, or convention requires
- Found — what actually exists in the code
- 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) |
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.
- 4d ago First seen · 369 lines · 141 tokens per session scan A 40a2377d6c33
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.
Other skills, from other repositories
implement
Implement an agreed specification through existing seams with tests, checks, and review.
go-testing
Trigger: Go tests, go test coverage, Bubbletea teatest, golden files. Apply focused Go testing patterns.
verify-implementation
A workflow that runs a project’s verification skills to produce a report on coding patterns, architecture rules, and project conventions. It is intended for work after implementation, before a pull request, or during code review.
semgrep-rule-variant-creator
Creates language variants of existing Semgrep rules. Use when porting a Semgrep rule to specified target languages. Takes an existing rule and target languages as input, produces independent rule+test directories for each language.
ln-23-test-suite-auditor
Audits existing tests for meaningful coverage, trustworthy oracles, and maintenance value. Not for test implementation or a single delivery review.
ln-21-documentation-auditor
Audits documentation and comments for trustworthy claims, coverage, and discoverability. Not for code, test, or architecture audits.