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 zxpmail/ReqForge --skill reqforge-greenkeepergit clone --depth 1 https://github.com/zxpmail/ReqForgeWrote 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/zxpmail/reqforge/reqforge-greenkeeper)<a href="https://agentmods.dev/skills/zxpmail/reqforge/reqforge-greenkeeper"><img src="https://agentmods.dev/badge/skills/zxpmail/reqforge/reqforge-greenkeeper/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/zxpmail/reqforge/reqforge-greenkeeper"><img src="https://agentmods.dev/badge/skills/zxpmail/reqforge/reqforge-greenkeeper.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00000 | $0.01113 |
| Opus 5.5 | $0.00000 | $0.00445 |
| Sonnet 5.5 | $0.00000 | $0.00223 |
| Haiku 4.5 | $0.00000 | $0.00111 |
Grade A, and why
reqforge-greenkeeper 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 1mo 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 — 100 lines — stays where its author put it; the contents beside it link to each section on GitHub.
name: reqforge-greenkeeper description: Used when maintaining the ReqForge repository itself and its release gates fail — pnpm test, pnpm forge-smoke, pnpm sync:discover, adapter drift, skill fixtures, loadouts, or test-demo golden path. Restores a green, synced state with minimal changes. Not for bugs in user apps built with Forge. version: 1.0.0 updated: 2026-07-16 requires: []
[Task]
Restore the ReqForge framework repository to a green maintenance state. Diagnose failing release gates, apply minimal invariant-preserving fixes, sync adapters when core assets change, and verify pnpm sync:discover, pnpm validate-skill, pnpm test, and pnpm forge-smoke.
[Not For]
- Bugs in a user product built with ReqForge → /bug-fixer
- Product features / Spec / Plan / Phase implementation → /product-spec-builder, /dev-planner, /dev-builder
- Shipping a user product artifact → /release-builder
- Creating a new Skill from scratch (no gate failure) → /skill-builder
- Evolving methodology from feedback without a red gate → /evolution-engine
[Dependency Check]
Required:
- Working directory = ReqForge repo root (package.json name reqforge, core/skills/, adapters/, scripts/forge-smoke/ present)
- Node.js + pnpm available
Optional:
- Git for `git status` / `git diff`
- `pnpm install` if `node_modules/` missing
If not the ReqForge framework repo → stop and route to `/bug-fixer` or `/request-dispatcher`.
[First Principles]
→ references/first-principles.md
核心：Evidence First / Fix the invariant / Core→Sync / Surgical Changes。
[Output Style]
Tone: SRE restoring a green build — evidence, root cause, minimal diff, verify counts.
Report: failing gate → cause → files → sync:discover / test / forge-smoke results.
[File Structure]
reqforge-greenkeeper/ ├── SKILL.md ├── skill.json ├── commands/reqforge-greenkeeper.md └── references/ ├── first-principles.md ├── anti-rationalization.md └── workflow.md
[Output Artifacts]
- Patches under core/, scripts/, or tests (adapters only via pnpm sync)
- Verification summary: sync discover + validate-skill + test + forge-smoke
[Anti-Rationalization Checklist]
→ references/anti-rationalization.md
[Workflow]
→ references/workflow.md
1. **Baseline** — `sync:discover` + `test` + `forge-smoke`; name the failing gate
2. **Classify** — adapter drift / fixtures / skill count / loadout / demo / verify docs
3. **Minimal fix** — preserve gates; core then `pnpm sync`
4. **Verify** — discover 0 drift, validate-skill clean, test + forge-smoke green
5. **Report** — cause, files, pass counts
[Gotchas]
Fixture parser vs Skill content: Quoted YAML values need unquoted search; reference expectations may need filenames, not only bodies.
Adapter drift: Editing core/skills/* without pnpm sync leaves four adapters stale — smoke will fail or users see old copy.
Vitest ≠ forge-smoke execution: pnpm test only checks smoke registry; pnpm forge-smoke runs the 15 scripts.
Demo contamination: test-demo/todo-cli writes todo.json under cwd — parallel files need isolation or fileParallelism: false.
Count gates: Bump skills-complete / adapters-sync expected count only when a real Skill directory is intentional and valid.
argument-hint: Bare argument-hint: [foo] is a YAML array — Copilot CLI drops the skill. Always quote.
What ships with it
5 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.
- 1mo ago First seen · 100 lines · 0 tokens per session scan A 9304c16c9da0
reqforge-greenkeeper is a skill published in the GitHub repository zxpmail/ReqForge (18 stars, last pushed 12d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,113 tokens. 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
developing-openrig
Use when changing OpenRig's own source in a clone of the openrig repository: finding which package or file owns a behaviour, choosing which tests to run, testing a change without disturbing the OpenRig daemon your own session runs on, judging whether a diff touches a high-risk area, or preparing a pull request. Not…
oma-debug
Diagnose a reproducible failure, fix its cause, and verify the regression. Use for crashes, incorrect behavior, and failing tests.
repair-prevention-assessment
A completion gate for fixes and self-repair work. It creates a machine-checkable assessment that separates evidence a current issue is closed from evidence that the fix will remain effective.
app-runtime-verify
Verify a mobile or app runtime: run the app (device, emulator, or headless), read captured output (logcat, iOS device log, or Metro/JS console), classify errors per stack, and decide a PASS/FAIL gate. Adapters: React Native/Expo, Unity mobile. Do not use to plan a screen (use implementation-plan), to write or fix code…
test-failure-explorer
Import and query an existing Vitest 3.2 JSON report to explore test failures, file-level errors and original diagnostic evidence.
systematic-debugging
A step-by-step method for finding the underlying cause of technical problems before changing code. It covers reading errors, reproducing failures, checking recent changes, and tracing data across system components.