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 mathiasbourgoin/roster --skill code-quality-auditorgit clone --depth 1 https://github.com/mathiasbourgoin/rosterWrote 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/mathiasbourgoin/roster/code-quality-auditor)<a href="https://agentmods.dev/skills/mathiasbourgoin/roster/code-quality-auditor"><img src="https://agentmods.dev/badge/skills/mathiasbourgoin/roster/code-quality-auditor/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/mathiasbourgoin/roster/code-quality-auditor"><img src="https://agentmods.dev/badge/skills/mathiasbourgoin/roster/code-quality-auditor.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 | $0.00021 | $0.01515 |
| Opus 5.5 | $0.00008 | $0.00606 |
| Sonnet 5.5 | $0.00004 | $0.00303 |
| Haiku 4.5 | $0.00002 | $0.00152 |
Grade A, and why
code-quality-auditor 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 1mo 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 — 123 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Code Quality Auditor
Check implementation against knowledge base properties and conventions. Uses only built-in tools (grep, wc, read) — no external linters required.
Steps
1. Load KB References
- Read
kb/properties.mdfor invariants, constraints, and quality thresholds. - Read
kb/glossary.mdfor canonical naming conventions and term definitions. - Read
kb/spec.mdfor architectural boundaries and module responsibilities. - Read
kb/architecture.md(top-level and per-module, if present) for declared structural expectations — module boundaries, dependency direction, layering. Check code structure against them; a divergence is a finding (cite file:line), and expectations that are not statically verifiable are noted as such, never assumed satisfied.
2. Check: Function Size
- Scan source files for function/method definitions.
- Measure line count per function (use grep + wc approach).
- Flag functions exceeding the threshold defined in
kb/properties.md; if unspecified there, use the max-function-length limit from the project's code-quality rule (.claude/rules/code-quality.md) — do not re-declare the number here. - Exclude test files from size checks unless properties.md says otherwise.
3. Check: DRY Violations
- Search for duplicated code blocks (identical or near-identical sequences of 5+ lines).
- Look for repeated patterns: duplicated error handling, copy-pasted validation logic, repeated configuration blocks.
- Flag each duplication with both locations.
4. Check: Naming Consistency with Glossary
- For each term in
kb/glossary.md, search the codebase for variant spellings, abbreviations, or synonyms. - Example: if glossary defines "Transaction", flag code using "tx", "txn", "trans" inconsistently.
- Check that type names, function names, and module names use glossary-canonical forms.
5. Check: Invariant Preservation
- For each invariant in
kb/properties.md, verify the code maintains it:- If an invariant says "X is never null", search for code paths where X could be null.
- If an invariant says "Y is always called before Z", trace call sequences.
- If an invariant says "all inputs are validated", check for unvalidated entry points.
- This is best-effort static analysis — flag suspicious patterns, don't claim proof.
- When reading
kb/properties.md, skip the contents of the fencedcode-intelblock (envelope:schema/kb-schema.md): those declarations are machine-checked by the roster-qa code-intel gate, and interpreting them as prose invariants would double-report.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 1mo ago Changed · +20 lines 2e0870f78493
- 2mo ago First seen · 103 lines · 21 tokens per session scan A ff0f5b152023
code-quality-auditor is a skill published in the GitHub repository mathiasbourgoin/roster (2 stars, last pushed 6d ago), licensed MIT. It adds 21 tokens to every session and 1,515 once invoked, about $0.0001 per session on Opus 5.5. 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 2026-08-31.
Other skills, from other repositories
autoreview
Structured code review through the shared OpenClaw agent-skills installation.
agent-teams-simplify-and-harden
Implementation + audit loop using parallel agent teams with structured simplify, harden, and document passes. Spawns implementation agents to do the work, then audit agents to find complexity, security gaps, and spec deviations, then loops until code compiles cleanly, all tests pass, and auditors find zero issues or…
omh-code-review
This is an OMH code-review workflow skill, projected for Agent Skills hosts (Claude Code, Codex, Cursor, opencode, OpenClaw, pi).
revdiff-plan
Review the last Codex assistant message (plan, analysis, or proposal) with inline annotations in a TUI overlay. Extracts the most recent response from Codex rollout files and opens it in revdiff for review and annotation. Activates on "revdiff-plan", "review plan with revdiff", "annotate plan", "review last response"…
explore-unknowns
Guide the user through a quadrant walk that maps the unknowns of a task — open by listing the known knowns, then work through known unknowns, unknown knowns, and unknown unknowns one stage at a time, ending with a complete four-quadrant map in the user's hands. Use when a request is ambiguous or underspecified, the…
re0-merge
Review and land an external contribution the way this suite does: gate it against the thesis, land it with the author's credit intact, complete a new skill rather than merging it raw, then approve, credit, and explain before closing. Use when reviewing a pull request, as any collaborator or maintainer, not only the…