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 DanielBirk04/capusqa --skill capusqa-doctorgit clone --depth 1 https://github.com/DanielBirk04/capusqaWrote 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/danielbirk04/capusqa/capusqa-doctor)<a href="https://agentmods.dev/skills/danielbirk04/capusqa/capusqa-doctor"><img src="https://agentmods.dev/badge/skills/danielbirk04/capusqa/capusqa-doctor.svg" alt="Measured on agentmods" 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 | $0.00075 | $0.00733 |
| Opus 5 | $0.00037 | $0.00367 |
| Sonnet 5 | $0.00015 | $0.00147 |
| Haiku 4.5 | $0.00007 | $0.00073 |
Grade B, and why
capusqa-doctor scanned grade B with 2 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 7d 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.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
`BASE` = the `capusqa` MCP server URL from `~/.codex/config.toml` Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
`curl -s $BASE/api/status` first — no response ⇒ the daemon is down: `capusqa serve` This is a copy
89% identical to doctor — 23 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 47 lines — stays where its author put it; the contents beside it link to each section on GitHub.
capusqa-doctor — environment health (Home → System status)
The Home → System status checks, in Codex — same source of truth as capusqa doctor
(capusqad/doctor.py). Diagnose, then hand the user the exact fix for each red.
Reaching the daemon
BASE = the capusqa MCP server URL from ~/.codex/config.toml
([mcp_servers.capusqa] url = "http://127.0.0.1:7777/mcp" → BASE =
http://127.0.0.1:7777). GET is open on localhost; the POSTs below add -H "Authorization: Bearer $CAPUSQA_DASHBOARD_TOKEN" only if that env var is set.
curl -s $BASE/api/status first — no response ⇒ the daemon is down: capusqa serve
(or capusqa serve --open), and stop here; nothing else is checkable.
Run the checks
curl -s $BASE/api/doctor → {checks:[{id,label,ok,required,category,hint,detail}], models_dir, mcp_url}. Show passing ones as a short green list, then walk each
failing one using its hint — required:true failures first (those block runs):
- Accessibility not trusted (macOS) — synthesized clicks/keys are silently
dropped. Fix: System Settings → Privacy & Security → Accessibility, enable the
app running the daemon, then restart
capusqa serve.POST $BASE/api/doctor/requestfires the OS dialogs — offer it. - Screen Recording not granted — captures come back blank. Same panel → Screen Recording. The preflight API can report false while capture actually works — trust a real run over the flag.
- Vision models missing /
DEGRADED: OCR-only— icon perception off; text / DOM still work. Download:$capusqa-updatestep 5, orPOST $BASE/api/models/download- poll
curl -s $BASE/api/models/statusuntilready(~1.5 GB).
- poll
- Browser extra missing —
uv tool install 'capusqa[browser]' && playwright install chromium(only for URL/web targets). - MCP / skills not registered — re-wire with the CLI
capusqa setup, or$capusqa-setup.
Re-run curl -s $BASE/api/doctor after each fix; stop when the required rows are
green.
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.
- 7d ago First seen · 47 lines · 75 tokens per session scan B de0093295fcc
capusqa-doctor is a skill published in the GitHub repository DanielBirk04/capusqa (0 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 75 tokens to every session and 733 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it B with 2 findings (reads agent configuration directories, makes network calls). It is 89% identical to doctor, differing in 23 lines, and is treated as a copy.
Other skills, from other repositories
browse
Drive a real browser through Aside: open a page, read it, click through a flow, take screenshots, check console errors. (gstack).
playwright-cli
A command-line tool for controlling Chromium, Firefox, and WebKit browsers, including navigation, page interaction, screenshots, PDFs, and recorded actions.
webapp-testing
Toolkit for interacting with and testing local web applications using Playwright. Supports verifying frontend functionality, debugging UI behavior, capturing browser screenshots, and viewing browser logs.
browser-qa
A browser-based quality check for deployed web pages and user flows. It uses browser automation to test rendering, navigation, forms, interactions, responsive behaviour, and accessibility-related issues.
test-electron-app
Drive the real running PostHog Electron app (live tRPC, workspace-server, real data) over CDP with agent-browser. Connect to the running app on port 9222, test desktop changes against a local Django stack, snapshot the accessibility tree, inspect network requests, and screenshot only when explicitly asked. Use when…
smoke-test
Run smoke tests against a deployed or local app based on your git diff. Each test uses Skyvern browser tools (navigate, act, validate, screenshot) with Chrome DevTools MCP as fallback. Posts screenshot evidence as PR comments.