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/updatenpx skills add DanielBirk04/capusqa --skill updategit 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 | $0.00075 | $0.00699 |
| Opus 5 | $0.00037 | $0.00349 |
| Sonnet 5 | $0.00015 | $0.00140 |
| Haiku 4.5 | $0.00007 | $0.00070 |
Grade A, and why
update 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 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
- **Running daemon**: `curl -s $BASE/api/status` → `version`. How it starts
The opening of the file, as written. The whole thing — 52 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/capusqa:update — update CapusQA
CapusQA's setup is install-idempotent, not upgrade-aware: after a new version the
plugin and the running daemon can stay on the old one. This command does the
upgrade end to end. Most of it is shell + the claude CLI; only the model
refresh goes through the daemon.
1 — See what you're on
BASE = the capusqa URL in .mcp.json (default http://127.0.0.1:7777).
- Running daemon:
curl -s $BASE/api/status→version. - Installed package:
uv tool list | grep capusqa. - Plugin:
claude plugin list | grep capusqa. If these disagree, that's the upgrade gap — fix below.
2 — Update the package
- From PyPI:
uv tool upgrade capusqa. - From local source (dev):
uv tool install --force '<repo-path>[browser]'([browser]keeps web testing). Confirm withuv tool list | grep capusqa.
3 — Update the Claude plugin
claude plugin marketplace update capusqa-marketplace, then
claude plugin update capusqa@capusqa-marketplace. (Applies on the next Claude Code
launch — note that.) Confirm with claude plugin list | grep capusqa.
4 — Restart the daemon onto the new version
The running daemon keeps the old code in memory until restarted. Only if no run
is live (curl -s $BASE/api/live shows none):
- Find and stop it:
kill $(lsof -tiTCP:7777 -sTCP:LISTEN). - Start fresh, detached:
capusqa servein a new terminal, ornohup capusqa serve >/tmp/capusqa.log 2>&1 &. Verify:curl -s $BASE/api/statusnow shows the new version.
5 — Vision models (optional)
Refresh OmniParser: curl -s -X POST $BASE/api/models/download (authed), then
poll curl -s $BASE/api/models/status until ready.
6 — Relaunch Claude Code
Plugins load at launch, so ⌘Q and reopen to pick up the new plugin. Then
claude plugin list and /capusqa reflect the new version.
When something's off
Plugin still old after relaunch → claude plugin uninstall capusqa@capusqa-marketplace
then /capusqa:setup (or the CLI capusqa setup) to reinstall. Daemon won't restart
(port busy) → make sure the old process is killed and nothing else holds :7777.
More → /capusqa:help.
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 · 52 lines · 75 tokens per session scan A 36bad06489d8
update 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 699 once invoked, about $0.0004 per session on Opus 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
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.