settings

A chat interface for configuring CapusQA's Settings dashboard. It covers test modes, run defaults, handoff behaviour, findings, people, saved credentials, usage, and plans.

In plain words
What is it for?
Choosing a settings area, creating custom test modes, changing run behaviour, managing personas and audiences, adding logins or secrets, and viewing usage or plan information.
Why use it?
It replaces searching through dashboard settings with guided configuration through CapusQA's daemon.

Skill for Claude CodeCodex

Install

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.

agentmods
npx agentmods add skills/danielbirk04/capusqa/settings
Any agent
npx skills add DanielBirk04/capusqa --skill settings
Clone the repo
git clone --depth 1 https://github.com/DanielBirk04/capusqa

Made for: Claude Code, Codex.

Per session 105 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,825 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00105 $0.01825
Opus 5 $0.00053 $0.00912
Sonnet 5 $0.00021 $0.00365
Haiku 4.5 $0.00011 $0.00183

Measured yesterday against content hash 19f7c3410abe, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

settings 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.

**only if** that env var is set. `curl -s $BASE/api/status` first.
Origin

Copies of this mod

1 near-identical copy found in the catalogue:

client/claude/capusqa/skills/settings/SKILL.md · 119 lines

How it starts

The opening of the file, as written. The whole thing — 119 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/capusqa:settings — configure CapusQA (Settings)

The dashboard Settings page, in chat. Ask what to configure, then drive that tab's daemon endpoints. If the user already named the area (e.g. "add a login"), skip the menu and go straight there.

Reaching the daemon

BASE = the capusqa URL in .mcp.json (default http://127.0.0.1:7777). GET = no auth; POST/DELETE add -H "Authorization: Bearer $CAPUSQA_DASHBOARD_TOKEN" only if that env var is set. curl -s $BASE/api/status first.

Ask what to configure (AskUserQuestion)

The dashboard groups ten tabs (the picker maxes at 4 options — offer the ones that fit the user's hint, or let them name another):

  • Testing — Test modes · Run defaults · Handoff mode · Findings
  • People & data — Personas · Audiences · Saved secrets · Role logins
  • Platform — Usage · Your plan

Then handle the chosen one:

Test modes

The four built-ins (Auto / User experience / Bug / Production — Production is "Coming soon", not launchable yet) are fixed; users author custom modes = the override/pin layer on a base profile's smart defaults. List: curl -s $BASE/api/test_modes. Create: POST $BASE/api/test_modes (authed) {"name":"…","icon":"C","copy":"…","config":{"base":"auto|ux|bug|production", "agent_count":5,"depth":"low|medium|high|xhigh|max","prompt":"extra tester instructions","focus":["checkout","auth"],"audience":["<audience_id>"], "default_goal":"…"}}. Only base is required; every override is optional — omit agent_count to let the orchestrator size the run, omit depth to match the chosen thoroughness. Edit: POST $BASE/api/test_modes/<id>. Restore a builtin: POST $BASE/api/test_modes/<id>/restore_defaults. Delete a custom one: DELETE $BASE/api/test_modes/<id>. (No user-facing engine/thoroughness on a mode — thoroughness is the per-launch "How thorough" control.)

Run defaults

  • Read: curl -s $BASE/api/settings.run_defaults + .recovery. Models/effort/backends: curl -s $BASE/api/agent_models.
  • Save: POST $BASE/api/settings (authed) {"run_defaults":{"model":"", "effort":"","backend":"auto","workers":2,"pacing":"human","scan_depth": "standard","seed":42,"default_credential_ids":[…]},"recovery":{"mode":"ask", "max_retries":2}}. model/effort empty = inherit the backend's default; workers is the Agent limit (max testers per run + concurrent runner workers, 1–16); pacing ∈ human|fast; scan_depth ∈ quick|standard|deep; recovery.mode ∈ ask|auto (the "When a session needs attention" choice).

Read the full file on GitHub · 119 lines

Changes

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.

  1. yesterday First seen · 119 lines · 105 tokens per session scan A 19f7c3410abe

Subscribe to this mod's changes

settings is a skill published in the GitHub repository DanielBirk04/capusqa (0 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 105 tokens to every session and 1,825 once invoked, about $0.0005 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.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

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.

obra/superpowers · 37 tokens

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.

microsoft/vscode · 53 tokens

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…

microsoft/vscode · 71 tokens

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.

microsoft/vscode · 56 tokens

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.

microsoft/vscode · 62 tokens