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-setupgit 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-setup)<a href="https://agentmods.dev/skills/danielbirk04/capusqa/capusqa-setup"><img src="https://agentmods.dev/badge/skills/danielbirk04/capusqa/capusqa-setup/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/danielbirk04/capusqa/capusqa-setup"><img src="https://agentmods.dev/badge/skills/danielbirk04/capusqa/capusqa-setup.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 | $0.00089 | $0.00739 |
| Opus 5.5 | $0.00036 | $0.00296 |
| Sonnet 5.5 | $0.00018 | $0.00148 |
| Haiku 4.5 | $0.00009 | $0.00074 |
Grade B, and why
capusqa-setup 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 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.
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.
$CAPUSQA_DASHBOARD_TOKEN"` **only if** that env var is set. `curl -s $BASE/api/status` How it starts
The opening of the file, as written. The whole thing — 50 lines — stays where its author put it; the contents beside it link to each section on GitHub.
capusqa-setup — get ready to test
Walk a new user from zero to a runnable test. The MCP + Codex skills are already
wired (that's how you got here — the CLI capusqa setup registers the capusqa MCP
server and installs these skills); this finishes the environment and preps
the project.
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). POST routes add -H "Authorization: Bearer $CAPUSQA_DASHBOARD_TOKEN" only if that env var is set. curl -s $BASE/api/status
first — no response ⇒ capusqa serve (see $capusqa-help).
1 — Environment (same checks as Home → System status)
curl -s $BASE/api/doctor → {checks:[…]}. Walk the reds; the fix for each:
- macOS Accessibility / Screen-Recording (needed for native-app clicks /
typing / screenshots):
POST $BASE/api/doctor/requestfires the OS dialogs; the user approves in System Settings → Privacy & Security. Web/URL testing needs neither. - OmniParser vision models (icon perception; optional — text/DOM works
without): download via
$capusqa-updatestep 5, orPOST $BASE/api/models/downloadthen pollcurl -s $BASE/api/models/statusuntilready(~1.5 GB). - Browser targets missing →
uv tool install 'capusqa[browser]' && playwright install chromium. Re-checkcurl -s $BASE/api/doctoruntil the required rows are green. (If the MCP server or skills themselves show unregistered, the CLIcapusqa setupre-wires them.)
2 — Project prep (so a run reaches the deep half of the app)
Optional but high-leverage — all via $capusqa-settings:
- Personas: the standard panel for speed, or a project-specific set
(
$capusqa-settings→ Personas). - A login, if the app needs one (
$capusqa-settings→ Saved secrets, or → Role logins to wire a per-URL account with its role/tenant).
3 — Test
You're ready: $capusqa-test to launch, $capusqa-runs to watch, $capusqa-issues
for what it finds.
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 · 50 lines · 89 tokens per session scan B d3544cf70bf1
capusqa-setup is a skill published in the GitHub repository DanielBirk04/capusqa (0 stars, last pushed 3mo ago), licensed Apache-2.0. It adds 89 tokens to every session and 739 once invoked, about $0.0004 per session on Opus 5.5. A static security scan graded it B with 2 findings (reads agent configuration directories, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
research-engineer
An uncompromising Academic Research Engineer. Operates with absolute scientific rigor, objective criticism, and zero flair. Focuses on theoretical correctness, formal verification, and optimal implementation across any required technology.
eval-dataset-design
A guide to creating reliable test sets for AI agents. Each evaluation task includes the request, the simulated user's behaviour, a reset starting state, and a success check that can be independently verified.
tika-eval-compare
Compare extracts from two Tika builds over a corpus to detect regressions in content, encoding, exceptions, and embedded-document handling. Use for "compare before/after extracts", "eval this change against the corpus".
cua-driver
Use Cua Driver for desktop or browser tasks that are awkward or unavailable through Bash/APIs, or when the user explicitly wants GUI interaction: app testing, visual bug reproduction, form filling, calendar entry, screenshots, and demo recording. Also covers Cua setup; not OpenAI Codex Computer Use or web research.
jetson-validate-image
Use after jetson-flash-image to run static BSP checks, on-target smoke/regression tests on a flashed DUT, or both. Not for build or flash steps. Triggers: validate bsp, on-target validation.
atmos-validation
Validate Atmos projects, components, arbitrary JSON Schema inputs, EditorConfig, and GitHub Actions; use affected-file selection and native CI annotations.