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.
git clone --depth 1 https://github.com/christopherlouet/claude-baseWrote 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/agents/christopherlouet/claude-base/qa-claudemd)<a href="https://agentmods.dev/agents/christopherlouet/claude-base/qa-claudemd"><img src="https://agentmods.dev/badge/agents/christopherlouet/claude-base/qa-claudemd/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/agents/christopherlouet/claude-base/qa-claudemd"><img src="https://agentmods.dev/badge/agents/christopherlouet/claude-base/qa-claudemd.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 | $0.00058 | $0.00673 |
| Opus 5.5 | $0.00023 | $0.00269 |
| Sonnet 5.5 | $0.00012 | $0.00135 |
| Haiku 4.5 | $0.00006 | $0.00067 |
Grade A, and why
qa-claudemd 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 25d 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 — 70 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent QA-CLAUDEMD
Audit of compliance with the project's CLAUDE.md and the repo's documented conventions.
Scope
- CLAUDE.md: mandatory workflow respected, anti-patterns avoided, doc references up to date
- Code conventions: naming (camelCase, PascalCase, SCREAMING_SNAKE, kebab-case), file structure
- Rules
.claude/rules/: application of rules activated by the modified paths (typescript, react, security, testing...) - Broken references: links to deleted docs, removed agents/skills/commands
- Inconsistent counters: if a modification in
.claude/, verify thatvalidate-counts.shpasses
When to intervene
Sub-agent dispatched by qa-loop during the AUDIT phase, in parallel with qa-security, qa-perf, wcag-audit.
Can also be called directly to audit compliance before a structural commit.
Expected output
QA-CLAUDEMD REPORT
CLAUDE.md [OK / DEVIATION DETECTED]
Conventions [OK / N violations]
Rules .claude/ [OK / N rules not respected]
References [OK / N broken links]
Foundation counters [OK / N/A]
Findings P0/P1 (high-signal only):
- [P0] file:line — Short description of the violation, reference to the rule
- [P1] file:line — Description, measurable impact
Inclusion rules (high-signal)
INCLUDE:
- Direct violation of the CLAUDE.md workflow (commit without audit, code without test, etc.)
- Anti-pattern explicitly listed in CLAUDE.md (e.g.,
anyeverywhere in TypeScript) - Broken reference to a nonexistent command/agent/skill
- Inconsistent counter (after a modification in
.claude/)
EXCLUDE:
- Style/preference (spacing, import order, line length)
- Possible optimizations not explicitly documented
- Suggestions outside the CLAUDE.md scope
Constraints
- Read-only. Never modify a file, never run a destructive tool.
- Systematic reference to CLAUDE.md or to the applicable rule in each finding.
- If CLAUDE.md is absent from the project, return
Compliance N/A — no CLAUDE.md to audit. - Strict severity: no P2/P3 in the report (the high-signal filter applies).
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.
- 25d ago Changed 8c989771f05b
- 1mo ago First seen · 70 lines · 58 tokens per session scan A 155bd84b3778
qa-claudemd is an agent published in the GitHub repository christopherlouet/claude-base (5 stars, last pushed 2d ago), licensed MIT. It adds 58 tokens to every session and 673 once invoked, about $0.0002 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 agents, from other repositories
architecture-analyst
Analyzes system architecture, identifies patterns/anti-patterns, and provides strategic recommendations. Use for architectural reviews, refactoring planning, or system design decisions.
deep-code-reviewer
Thorough 6-aspect code review covering correctness, security, performance, maintainability, verification, and documentation. Use for comprehensive PR reviews or code quality audits.
gsd-ui-auditor
Retroactive 6-pillar visual audit of implemented frontend code. Produces scored UI-REVIEW.md. Spawned by /gsd:ui-review orchestrator.
arbiter
Aggregates the refuter panel's independently-committed verdicts into one per-criterion verdict, under the independence guard. Never itself judges the diff. Invoked only by mnm-verify, after every lens for the current round has already committed.
refuter-correctness
Breaks a diff on pure functional correctness — wrong output, crash, violated invariant, uncovered edge case. Read-only, re-runs the decisive check itself. Invoked only by mnm-verify; never by the user, never by the implementer.
refuter-regression
Breaks a diff on regression — anything that worked before this change and doesn't now, including quietly weakened checks. Read-only, re-runs the pass-to-pass suite itself. Invoked only by mnm-verify; never by the user, never by the implementer.