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 agentmods add skills/danielbirk04/capusqa/helpnpx skills add DanielBirk04/capusqa --skill helpgit clone --depth 1 https://github.com/DanielBirk04/capusqaWhat 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 | $0.00085 | $0.01101 |
| Opus 5 | $0.00043 | $0.00550 |
| Sonnet 5 | $0.00017 | $0.00220 |
| Haiku 4.5 | $0.00009 | $0.00110 |
Grade B, and why
help 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 yesterday.
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.
Strips warnings and disclaimersmediumAnti-refusal
Omitting safety caveats hides risk from the user and is a common jailbreak preamble.
nav and send the user to the one command they need. Route, don't lecture. Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
- **daemon down / connection refused / `curl` fails** → it isn't running: How it starts
The opening of the file, as written. The whole thing — 68 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/capusqa — the CapusQA menu
Typing /capusqa lands here. You are the navigator: mirror the dashboard's left
nav and send the user to the one command they need. Route, don't lecture.
Mental model (one breath, only if they're new)
CapusQA is persona-driven LLM testing for web and macOS apps. The daemon
(capusqa serve) is the single source of truth — every run, session, issue and
screenshot lives in ~/.capusqa. This chat and the dashboard
(http://127.0.0.1:7777/) are two clients of it: anything you do here shows in
the dashboard instantly and persists.
If they already said what they want, name the command (don't show a menu)
- start/launch a test, "test my app", "find bugs" →
/capusqa:test - "what's running", show/watch runs, a session, steer/stop →
/capusqa:runs - bugs/findings, triage, "what did it find", send to my coding tool →
/capusqa:issues - configure anything (modes, run defaults, handoff/coding tool, findings filter, personas, audiences, logins) →
/capusqa:settings - first-time wiring / "nothing works yet" →
/capusqa:setup - update CapusQA / new version / vision models →
/capusqa:update - permissions, daemon health, clicks do nothing →
/capusqa:doctor - open the dashboard / the web UI →
/capusqa:dashboard
If they typed a bare /capusqa with no intent, ask once (AskUserQuestion)
Four dashboard areas, recommended first (note in the question that Setup, Update and Doctor are also available — they can pick "Other" or just say so):
- New test (Home) — configure & start a test →
/capusqa:test - Runs — watch live / past runs →
/capusqa:runs - Issues found — findings & fixes →
/capusqa:issues - Settings — configure CapusQA →
/capusqa:settings
Then invoke the chosen skill with the Skill tool (e.g. capusqa:test) — don't
make them retype.
The full map
| Command | = dashboard | Does |
|---|---|---|
/capusqa:test |
New test (Home) | Configure & start a test (app URL, what-to-test, mode) |
/capusqa:runs |
Runs | Watch live/past runs, sessions, traces; steer/stop |
/capusqa:issues |
Issues found | Findings by severity, mark fixed, re-test, send to your coding agent |
/capusqa:settings |
Settings | Test modes · Run defaults · Handoff mode · Findings · Personas · Audiences · Saved secrets · Role logins · Usage · Your plan |
/capusqa:setup |
— | First-run: permissions, vision models, browser, project prep |
/capusqa:update |
— | Update CapusQA + plugin + vision models |
/capusqa:doctor |
Home → System status | Environment health + fixes |
/capusqa:dashboard |
the web UI | Open the dashboard in your browser |
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.
- yesterday First seen · 68 lines · 85 tokens per session scan B 11844301d885
help is a skill published in the GitHub repository DanielBirk04/capusqa (0 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 85 tokens to every session and 1,101 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it B with 2 findings (strips warnings and disclaimers, 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
agent-host-chat-contributions
Build and review cross-cutting agent-host chat behavior through lifecycle contributions. Use when adding turn lifecycle side effects, prompt or context injection, restored-history transformation, protocol-action observation, or when reviewing changes that add code to AgentSideEffects or AgentService.
auto-perf-optimize
Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.