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 Samuel0101010/wisp-orchestrator --skill qa-verificationgit clone --depth 1 https://github.com/Samuel0101010/wisp-orchestratorWrote 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/samuel0101010/wisp-orchestrator/qa-verification)<a href="https://agentmods.dev/skills/samuel0101010/wisp-orchestrator/qa-verification"><img src="https://agentmods.dev/badge/skills/samuel0101010/wisp-orchestrator/qa-verification.svg" alt="Measured on agentmods" 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 | $0.00030 | $0.00369 |
| Opus 5 | $0.00015 | $0.00185 |
| Sonnet 5 | $0.00006 | $0.00074 |
| Haiku 4.5 | $0.00003 | $0.00037 |
Grade A, and why
qa-verification scanned grade A with 0 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 8d 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.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
Your verdict is only as good as the commands you actually ran. Method:
- Execute, never assume. Run every gate yourself — build, tests, lint, and any custom check from the task. Reading the code is not verification; command exit codes are.
- Check the goal, not just the gates. Green tests on the wrong feature are a FAIL. Re-read the task's goal and confirm the produced behavior matches it (run the app or a smoke command when possible).
- Evidence per claim. Every PASS/FAIL line you report must name the command you ran and quote the relevant output (exit code, failing test name, error line). A claim without a command behind it is worthless.
- Report failures precisely. For each failure: the exact command, the exact error text, the file/line if visible, and ONE suspected cause. No vague "something seems broken".
- Honesty beats optimism. If you could not verify something (missing tool, timeout, unclear criterion), say UNVERIFIED with the reason — do not round it up to PASS or down to FAIL.
- Do not fix. You verify. If you are not explicitly told to repair, report findings and stop; fixing is the builder's job and your edits would mask the regression you were asked to catch.
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.
- 8d ago First seen · 28 lines · 30 tokens per session scan A 89f4fbd06257
qa-verification is a skill published in the GitHub repository Samuel0101010/wisp-orchestrator (4 stars, last pushed 4d ago), licensed Apache-2.0. It adds 30 tokens to every session and 369 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
qa
Browser-based QA verification. Launches a real browser, navigates the app, clicks buttons, fills forms, and tests user flows. Works as a standalone skill or as a phase end condition in campaigns. Requires Playwright (optional dependency, graceful skip if not installed).
live-preview
Mid-build visual verification loop. Takes screenshots of components during construction, not just after. Catches visual regressions and invisible features before they compound. Requires Playwright or similar screenshot tool.
test-gen
Generate and verify tests — happy path, edge cases, error paths — using the project's own framework and patterns.
verify
Self-test the Citadel hook pipeline from within a live session. Exercises real tool calls (Write, Edit, Bash, Read) and checks that hooks fired, telemetry accumulated, and no errors occurred. Reports HOOK HEALTH: PASS or HOOK HEALTH: FAIL with a per-hook breakdown.
browser-check
Drive a real browser and come back with a MEASUREMENT rather than an impression - console errors and >=400 responses as counts, computed styles as JSON when appearance is disputed. Use when work touches UI, when a review must verify one, or when fidelity-gate asks for its measurement.
run-smoke-tests
Run Playwright smoke tests, debug failures, and verify fixes. Use for smoke, e2e, Playwright, or pre-ship browser verification.