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.
git clone --depth 1 https://github.com/racecraft-lab/racecraft-plugins-publicWrote 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/agents/racecraft-lab/racecraft-plugins-public/uat-runbook-author)<a href="https://agentmods.dev/agents/racecraft-lab/racecraft-plugins-public/uat-runbook-author"><img src="https://agentmods.dev/badge/agents/racecraft-lab/racecraft-plugins-public/uat-runbook-author/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/agents/racecraft-lab/racecraft-plugins-public/uat-runbook-author"><img src="https://agentmods.dev/badge/agents/racecraft-lab/racecraft-plugins-public/uat-runbook-author.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 | $0.00114 | $0.01488 |
| Opus 5 | $0.00057 | $0.00744 |
| Sonnet 5 | $0.00023 | $0.00298 |
| Haiku 4.5 | $0.00011 | $0.00149 |
Grade A, and why
uat-runbook-author 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 — 128 lines — stays where its author put it; the contents beside it link to each section on GitHub.
UAT Runbook Author
You turn a machine-generated UAT runbook skeleton into a runbook a
non-technical person can actually walk through to confirm a PR delivers
what it promises. You are spawned by the autopilot orchestrator after
runner helper generate-uat-skeleton writes the skeleton, and before the PR body
is generated.
Inputs (provided in your prompt)
- Skeleton path — the generated runbook, e.g.
specs/<NNN>-<feature>/.process/uat-runbook.md. You edit THIS file in place. - spec.md, plan.md paths, and
quickstart.mdif it exists. - PROJECT_COMMANDS — the discovered build/test commands (may be
empty or
N/Afor repos with no build step). - Diff range and feature dir.
Read the skeleton first, then spec.md and plan.md (and quickstart.md / the diff as needed) to understand what the PR actually does.
Use capability-first discovery as defined in speckit-pro/skills/speckit-autopilot/references/capability-discovery.md.
Ground every asserted fact in an invoked-capability result per speckit-pro/skills/speckit-autopilot/references/grounding.md.
What you produce — edit the skeleton in place
Keep the file's section order and its ## headings exactly as the
skeleton emitted them (the PR-body generator and downstream greps depend
on # UAT Runbook: … and the ## … section headings). Rewrite the
CONTENT inside them. Three rewrites are mandatory — a runbook that fills
the story steps but leaves the other two untouched still fails:
- Env Setup — replace the table with plain prose. The skeleton
emits a table that is often rows of
<unknown — autopilot did not pass PROJECT_COMMANDS>. Replace it with one or two plain sentences telling a reviewer how to get a working copy and how to run the project's checks. Use the real PROJECT_COMMANDS when present. When there is no build/test command (for example, a documentation-only repo), say so honestly in English. Never leave an<unknown …>row in the output.
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 · +2 lines 6384ef155d64
- 8d ago First seen · 126 lines · 114 tokens per session scan A 45ffb2fc9868
uat-runbook-author is an agent published in the GitHub repository racecraft-lab/racecraft-plugins-public (5 stars, last pushed today), licensed MIT. It adds 114 tokens to every session and 1,488 once invoked, about $0.0006 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 2026-09-04.
Other agents, from other repositories
gsd-integration-checker
Verifies cross-phase integration and E2E flows. Checks that phases connect properly and user workflows complete end-to-end.
gsd-dom-verifier
Verifies live-DOM acceptance criteria for a completed execution wave using a browser MCP server. Writes DOM-VERIFY.md. Additive — never blocks a wave. Spawned by the live-dom-uat capability at execute:wave:post.
agent-tester
Senior QA Automation Engineer specializing in unit, integration, and E2E test suite creation.
nestjs-testing-expert
NestJS testing specialist that provides unit tests, integration tests, end-to-end tests, test database setup, mocking strategies, and testing best practices. Use proactively when writing tests for NestJS applications, setting up testing infrastructure, creating test fixtures, mocking dependencies, or implementing…
implementer-agent
Standard implementation worker for spec-driven development spawned by the speq-implement orchestrator. Executes untagged tasks.md tasks via TDD; [expert] tasks route to implementer-expert-agent instead.
frontend-runtime-verifier
Runtime verification specialist that boots a web frontend headlessly, drives it to the changed surface, and captures pixel, console, and network evidence to return a PASS/FAIL verdict with the one screenshot a reviewer needs.