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 IvoryCanvas/QAMap --skill qamap-pr-qagit clone --depth 1 https://github.com/IvoryCanvas/QAMapWrote 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/ivorycanvas/qamap/qamap-pr-qa)<a href="https://agentmods.dev/skills/ivorycanvas/qamap/qamap-pr-qa"><img src="https://agentmods.dev/badge/skills/ivorycanvas/qamap/qamap-pr-qa/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/ivorycanvas/qamap/qamap-pr-qa"><img src="https://agentmods.dev/badge/skills/ivorycanvas/qamap/qamap-pr-qa.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high System Prompt Leakage · line 90 Skill contains instructions that could directly expose system prompts, internal rules, or hidden instructions to users or external parties.Fix: Remove any instructions that reveal, print, or output system prompts or internal rules. System instructions should never be exposed to end users.
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 | $0.00067 | $0.02671 |
| Opus 5 | $0.00034 | $0.01336 |
| Sonnet 5 | $0.00013 | $0.00534 |
| Haiku 4.5 | $0.00007 | $0.00267 |
Grade A, and why
qamap-pr-qa 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 2d 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.
How it starts
The opening of the file, as written. The whole thing — 134 lines — stays where its author put it; the contents beside it link to each section on GitHub.
QAMap PR QA
Use QAMap as a final local QA pass before presenting a pull request for human review.
Workflow
-
Detect the comparison base.
- Prefer the target PR base branch when known.
- Otherwise use
origin/main, thenorigin/master, then the repository default branch.
-
Run QAMap from the repository root. Prefer an already installed local binary:
pnpm exec qamap qa . --base <base> --head HEAD --format agentIf QAMap is not installed, disclose that the next command downloads the pinned package from the npm registry and follow the host's network approval policy before running it:
npm exec --yes --registry=https://registry.npmjs.org --package=@ivorycanvas/[email protected] -- qamap qa . --base <base> --head HEAD --format agentThis one-off form runs outside the target repository's package-manager contract, so it does not invoke Corepack or add a
packageManagerfield. QAMap's analysis does not upload source code or make another LLM call. The calling agent still uses its own model tokens to invoke the skill and interpret the compact result.Prefer the compact agent format because it carries the decision contract in a fraction of the tokens. Drop
--format agentfor concise human-readable text, or use--format markdownfor the full trace report. The agent JSON is a versioned contract (schema: qamap.qav1, additive-only): see docs/agent-format.md in the QAMap repository. -
Read
analysisScopebefore interpreting package-relative evidence or commands.- Read
commandCwdas the command working-directory contract.workspace-rootmeans run the command from the repository root;selected-packagemeans run it fromselectedPath. Older v1 payloads may omit the field; default to the workspace root instead of guessing. automatic-packagemeans the root command already reran analysis with the selected package's routes, scripts, fixtures, and runner settings. Its commands include the package path and usecommandCwd: "workspace-root"; use the workspace-awareautomation.draftCommandas printed.explicit-packagekeeps package-local commands and usescommandCwd: "selected-package"withselectedPath.repository-rootmeans QAMap could not safely select one package. Reviewcandidatesandreason; do not silently choose a package for a cross-package or root-spanning change.- Use an explicit scoped pass only when a human wants to override that decision:
- Read
What ships with it
3 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.
- 2d ago Changed · +3 lines 944f2cb6fd58
- 5d ago Changed b1c6cc536cd8
- 11d ago First seen · 131 lines · 67 tokens per session scan A a323047bcb72
qamap-pr-qa is a skill published in the GitHub repository IvoryCanvas/QAMap (22 stars, last pushed yesterday), licensed MIT. It adds 67 tokens to every session and 2,671 once invoked, about $0.0003 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 2026-08-30.
Other skills, from other repositories
e2e
Generate and run Playwright E2E tests traced to spec.md acceptance criteria, with an optional accessibility audit. Use when saying "e2e tests" or "a11y audit".
agentplane-testkit-migration
Use when migrating Agentplane tests to @agentplane/testkit, replacing local test helpers, fixing testkit export/build failures, splitting large CLI/backend suites, or diagnosing missing testkit dist exports in package builds.
joycraft-implement
Execute atomic specs with TDD — read spec, write failing tests, implement until green, wrap up and continue the queue.
joycraft-implement-level5
Invoked by tune's roadmap or the human opting into Level 5 — set up the autofix loop, holdout scenario testing, and scenario evolution from specs.
tauri-pilot
Inspect, interact with, and test a running Tauri v2 app via CLI. Communicates over Unix socket using JSON-RPC 2.0. Use when testing UI, automating interactions, or debugging a Tauri app.
responsive-audit
Responsive audit: test pages at 375/768/1024px breakpoints via Playwright. Checks overflow, tap targets, sidebar collapse, text reflow, WCAG 1.4.4 zoom.