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 issuesgit 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/issues)<a href="https://agentmods.dev/skills/danielbirk04/capusqa/issues"><img src="https://agentmods.dev/badge/skills/danielbirk04/capusqa/issues/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/issues"><img src="https://agentmods.dev/badge/skills/danielbirk04/capusqa/issues.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 | $0.00088 | $0.01063 |
| Opus 5.5 | $0.00035 | $0.00425 |
| Sonnet 5.5 | $0.00018 | $0.00213 |
| Haiku 4.5 | $0.00009 | $0.00106 |
Grade A, and why
issues 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
that env var is set. `curl -s $BASE/api/status` first — no response ⇒ `capusqa Copies of this mod
1 near-identical copy found in the catalogue:
- capusqa-issues — 89% identical, 27 lines differ
How it starts
The opening of the file, as written. The whole thing — 67 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/capusqa:issues — findings & fixes (Issues found)
The dashboard Issues board, in chat: every finding from every run, grouped into clusters, with triage + the coding-tool handoff. Read/written through the daemon, so it matches the dashboard and persists.
Reaching the daemon
BASE = the capusqa URL in .mcp.json (default http://127.0.0.1:7777). GET =
no auth; POST adds -H "Authorization: Bearer $CAPUSQA_DASHBOARD_TOKEN" only if
that env var is set. curl -s $BASE/api/status first — no response ⇒ capusqa serve (see /capusqa:help).
Show issues
curl -s "$BASE/api/findings?limit=200" (filters: status
open|fixed|wontfix|duplicate, severity critical|high|medium|low, run_id) →
{findings:[…], finding_groups:[…], runs:[…]}. Prefer finding_groups — the
dashboard's unit is the cluster ("found N times"), not the raw finding.
Render by severity, hot (critical/high) first: summary, expected vs observed,
count, status, which run(s)/mode(s) it appeared in. For deeper triage the
findings_query / issues_query MCP tools also work.
The feed honors the user's severity floor (Settings → Findings, the
/capusqa:settings Findings area): below-floor findings are hidden — medium
(the default) hides low, high also hides medium, all shows
everything. The response carries the applied min_severity + a
hidden_below_floor count; add &min_severity=all to one request to see
everything regardless of the floor. Mention the count if anything is hidden so
"nothing shown" is never mistaken for "nothing found". The same floor is what
the hand-off considers (and, when automatic fixing ships, what the
auto-improvement loop may fix).
Triage — mark fixed · rate · re-test
The Issues board's per-issue actions, all POST $BASE/api/findings/<finding_id>
(authed, content-type: application/json):
- Mark fixed:
-d '{"status":"fixed","fix_note":"<why>"}'. (The APIstatusalso acceptsopen|wontfix|duplicate, though the board's button only marks fixed.) - Rate helpful / not helpful (the 👍/👎 on each issue — feeds fleet scoring):
-d '{"user_rating":"up"}'(or"down", or"none"to clear). - Re-test: see below.
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 · 67 lines · 88 tokens per session scan A 74a59f0e4bed
issues is a skill published in the GitHub repository DanielBirk04/capusqa (0 stars, last pushed 3mo ago), licensed Apache-2.0. It adds 88 tokens to every session and 1,063 once invoked, about $0.0004 per session on Opus 5.5. A static security scan graded it A with 1 finding (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
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.
verify-omnigent
Drive Omnigent the way a user does and prove a behavior with recorded evidence, using an isolated server, runner, and mock model plus a feature map of every user entry point. Load before reproducing a user-facing bug, before claiming a fix works, or when reviewing whether a change covered every surface (session vs.…
test-master
Generates test files, creates mocking strategies, analyzes code coverage, designs test architectures, and produces test plans and defect reports across functional, performance, and security testing disciplines. Use when writing unit tests, integration tests, or E2E tests; creating test strategies or automation…
dogfood
Systematically explore and test a mobile app on iOS/Android with agent-device to find bugs, UX issues, and other problems. Use when asked to dogfood, QA, exploratory test, find issues, bug hunt, or test this app on mobile.
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.
critique
Adversarial design critique of the current work — render it, look at it, and argue for rejection. Run after the gates are green, never instead of them.