Borrowing it
Nothing to install: this file belongs to c9r-io/orchestrator. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/c9r-io/orchestrator/main/.claude/skills/qa-doc-gen/SKILL.mdgit clone --depth 1 https://github.com/c9r-io/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/c9r-io/orchestrator/qa-doc-gen)<a href="https://agentmods.dev/skills/c9r-io/orchestrator/qa-doc-gen"><img src="https://agentmods.dev/badge/skills/c9r-io/orchestrator/qa-doc-gen/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/c9r-io/orchestrator/qa-doc-gen"><img src="https://agentmods.dev/badge/skills/c9r-io/orchestrator/qa-doc-gen.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 | $0.00143 | $0.03074 |
| Opus 5.5 | $0.00057 | $0.01230 |
| Sonnet 5.5 | $0.00029 | $0.00615 |
| Haiku 4.5 | $0.00014 | $0.00307 |
Grade A, and why
qa-doc-gen 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 2mo 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.
4. **Dynamic values**: Use `{placeholder}` syntax in SQL and curl commands How it starts
The opening of the file, as written. The whole thing — 227 lines — stays where its author put it; the contents beside it link to each section on GitHub.
QA Doc Gen
After a feature plan is confirmed or a refactor is completed, generate and synchronize test documentation so all QA/security/UIUX docs match real behavior.
Workflow
1. Extract feature details and behavior deltas from confirmed plan / implemented code
2. Determine module classification and file naming
3. Generate design doc(s) under docs/design_doc/ (platform doc, before QA)
4. Generate QA test document(s) following project format
5. Run cross-doc impact scan on docs/qa, docs/security, docs/uiux
6. Patch all impacted existing docs to remove stale steps/assertions
7. Update docs/qa/README.md index
8. Update docs/design_doc/README.md index
9. Update docs/security/README.md and docs/uiux/README.md when changed
Step 1: Extract from Confirmed Plan
From the confirmed plan and merged implementation, extract:
- Feature name: What the feature is called
- Module: Which module it belongs to (used as the folder under
docs/qa/, e.g.docs/qa/{module}/) - Behavior: Normal flow, error cases, edge cases
- Behavior deltas: What changed compared to old docs (auth rules, token types, permission boundaries, UI routes, API contracts, redirects)
- Falsified statements: Which existing statements anywhere in the repo this change makes untrue — a removed config value still documented as available, a mechanism still described as current, a compatibility claim that no longer holds. List these explicitly; they drive Step 5 and are the most common source of doc drift surviving a "closed" change.
- UI interactions: Pages, buttons, forms involved
- UI entry points: Navigation links, quick links, sidebar items, or buttons that lead to the feature
- API endpoints: If applicable, include method, path, request/response
- Database changes: New tables/columns, expected data states
- Acceptance criteria: What constitutes correct behavior
- Non-functional requirements: Security/perf/availability/observability notes if present in the plan
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 2mo ago First seen · 227 lines · 143 tokens per session scan A 2d7714511469
qa-doc-gen is a skill published in the GitHub repository c9r-io/orchestrator (21 stars, last pushed 1mo ago), licensed MIT. It adds 143 tokens to every session and 3,074 once invoked, about $0.0006 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 2026-08-30.
Other skills, from other repositories
codew-release-qa-sweep
Use before claiming Codewhale release work is done: run the full gate sweep and list the manual QA targets.
cw-dogfood
Use when a Codewhale change needs proving in the real product, or when asked to build/install/dogfood the local binaries: stamped release build, atomic install, fresh-shell verification, and the manual QA that gates cannot cover.
cw-gates
Use before claiming any Codewhale change is done, green, or ready to land: the focused-to-broad verification ladder, the budget checks CI enforces, and the rules for what counts as a passing test.
test-driven-development
Use when implementing any feature or bugfix, before writing implementation code.
verification-before-completion
Use when about to claim work is complete, fixed, or passing, or before committing or creating PRs.
verify
Exercise the real app/API/CLI and collect observable evidence; tests alone do not count as end-to-end verification.