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 stuartshields/claude-setup --skill qa-checkgit clone --depth 1 https://github.com/stuartshields/claude-setupWrote 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/stuartshields/claude-setup/qa-check)<a href="https://agentmods.dev/skills/stuartshields/claude-setup/qa-check"><img src="https://agentmods.dev/badge/skills/stuartshields/claude-setup/qa-check/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/stuartshields/claude-setup/qa-check"><img src="https://agentmods.dev/badge/skills/stuartshields/claude-setup/qa-check.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 | $0.00041 | $0.03816 |
| Opus 5.5 | $0.00016 | $0.01526 |
| Sonnet 5.5 | $0.00008 | $0.00763 |
| Haiku 4.5 | $0.00004 | $0.00382 |
Grade A, and why
qa-check scanned grade A 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 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.
Runs shell commandslowCapability
Expected in a hook, worth knowing in a rule or an instructions file.
- No `eval()`, `Function()`, or `child_process.exec()` with user input. How it starts
The opening of the file, as written. The whole thing — 266 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Skill: qa-check (Global)
When to Use
Run /qa-check on any web project to audit for Accessibility (WCAG 2.2 AA), Performance, and Code Quality issues. This skill auto-detects the tech stack and adapts its checks accordingly.
Use $ARGUMENTS to scope the audit to a specific directory or file pattern (e.g., /qa-check src/components/). If empty, audit the entire project.
Do NOT fix issues - only report them. Present findings as structured Markdown tables.
Method
Phase 0: Stack Detection
Before running any checks, detect the project's tech stack by scanning the working directory for marker files. Report what was detected before proceeding.
Detection Rules
Scan in this order. A project can match multiple stacks (e.g., WordPress with Node build tools).
| Stack | Marker Files |
|---|---|
| WordPress / PHP | wp-config.php, composer.json with "wordpress", style.css containing Theme Name:, functions.php, wp-content/ or content/ directory |
| Python | requirements.txt, pyproject.toml, setup.py, setup.cfg, Pipfile, manage.py (Django), app.py or wsgi.py (Flask) |
| Node / JS | package.json - then inspect for framework indicators: next (Next.js), express (Express), nuxt (Nuxt), @angular/core (Angular), react (React), vue (Vue), svelte (Svelte) |
| Static Web | *.html files in root or src/, *.css files, no backend markers detected |
Detection Output
Print a summary before running checks:
## Stack Detection
| Stack | Detected | Markers Found |
|---|---|---|
| WordPress/PHP | Yes/No | wp-config.php, style.css (Theme Name: ...) |
| Python | Yes/No | requirements.txt, manage.py |
| Node/JS | Yes/No | package.json (express, react) |
| Static Web | Yes/No | index.html, styles.css |
Then determine which template/view files to scan:
- WordPress:
*.phpin theme directory,template-parts/,templates/,inc/ - Python (Flask):
templates/**/*.html,app/templates/**/*.html - Python (Django):
**/templates/**/*.html,**/templatetags/*.py - Node (Next.js):
pages/**/*.{js,jsx,tsx},app/**/*.{js,jsx,tsx},components/**/*.{js,jsx,tsx} - Node (Express):
views/**/*.{ejs,pug,hbs,html},public/**/*.html - Node (React/Vue/Svelte):
src/**/*.{jsx,tsx,vue,svelte} - Static Web:
*.html,src/**/*.html
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 First seen · 266 lines · 41 tokens per session scan A 0fee6abc79ce
qa-check is a skill published in the GitHub repository stuartshields/claude-setup (2 stars, last pushed 4mo ago), licensed MIT. It adds 41 tokens to every session and 3,816 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it A with 1 finding (runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
debug
Instrument web/web-app code with structured debug logging via a global variable (window.debuglogs). Produces a clean JSON timeline for reproducing and diagnosing bugs. Use when user wants to debug a feature or track down a bug.
anomaly-alert
Identify anomalous sessions using Agent Monitor data — cost outliers from the pricing engine, token anomalies (cache miss spikes, compaction baseline surges), unusual event type ratios (PreToolUse/PostToolUse gaps, APIError clusters), behavioral deviations from workflow intelligence (complexity score outliers, error…
transcript-grep
Search a Claude Code session transcript for a string or regex pattern and show every matching message with surrounding context. Reads /api/sessions/:id/transcript and resolves sessions via /api/sessions?limit= from the Agent Monitor dashboard. Use when hunting for a specific message, prompt, tool call, or error inside…
regression-watch
Detect quality and efficiency regressions over time using Agent Monitor data — rising error rate (APIError events), falling cache hit rate, growing compaction frequency, and climbing cost-per-session. Splits history into an earlier baseline window and a recent window and reports which metrics are getting worse, by how…
hook-inventory
Inventory hooks across the user, project, and project-local settings plus the /.claude/hooks scripts directory — read through the Agent Monitor Config Explorer API — and flag hooks that POST to the network or run arbitrary commands. Reads /api/cc-config/hooks and /api/cc-config/hook-scripts. Use when auditing hook…
event-trace
Trace the full event chain for one Claude Code session into an ordered timeline of every event type with toolname and summary, highlighting gaps, out-of-order events, and failures. Reads /api/events?sessionid= and /api/sessions/:id from the Agent Monitor dashboard. Use when debugging what a session actually did, step…