Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/ProductionMasterAI/production-masternpx agentmods add skills/productionmasterai/production-master/run-production-masterWrote 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/productionmasterai/production-master/run-production-master)<a href="https://agentmods.dev/skills/productionmasterai/production-master/run-production-master"><img src="https://agentmods.dev/badge/skills/productionmasterai/production-master/run-production-master/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/productionmasterai/production-master/run-production-master"><img src="https://agentmods.dev/badge/skills/productionmasterai/production-master/run-production-master.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 | $0.00065 | $0.00453 |
| Opus 5 | $0.00032 | $0.00227 |
| Sonnet 5 | $0.00013 | $0.00091 |
| Haiku 4.5 | $0.00006 | $0.00045 |
Grade A, and why
run-production-master 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 9d 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
run-production-master
End-to-end local verification for this npm-workspaces monorepo. Run every gate the way CI does, in order, and stop at the first failure.
Steps
-
Install — clean, reproducible install from the lockfile:
npm ci -
Build all workspaces — compile every package under
packages/*:npm run build --workspaces --if-present -
Test — run the full test suite across workspaces:
npm run test --workspaces --if-present -
Lint — the same lint gate CI enforces (warnings fail the build):
npm run lint --workspaces --if-present -
Validate install manifests — confirm each adapter package ships a well-formed, parseable install manifest before it can be published:
node scripts/validate-manifests.mjsThis checks every
packages/*/manifest.json(or the repo's manifest convention) parses as JSON and carries the required fields. If the script is absent, fall back to a JSON parse sweep:find packages -name 'manifest.json' -exec node -e 'JSON.parse(require("fs").readFileSync(process.argv[1]))' {} \;
Reporting
- Report each step as pass/fail with the command that proved it.
- On failure, show the failing output (trimmed) and stop — do not continue to later steps.
- Only report the repo as healthy when steps 1–5 all pass; cite the final command's output as evidence.
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.
- 9d ago First seen · 60 lines · 65 tokens per session scan A 6800fadb0107
run-production-master is a skill published in the GitHub repository ProductionMasterAI/production-master (0 stars, last pushed 2d ago), licensed MIT. It adds 65 tokens to every session and 453 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 2026-08-31.
Other skills, from other repositories
gentle-ai-bench
Trigger: bench, journey, journeys, driven mode, gentle-ai-bench, journey corpus, j-numbers, bench axis. Author and verify gentle-ai bench journeys; go test ./bench never proves driven execution.
go-testing
Trigger: Go tests, go test coverage, Bubbletea teatest, golden files. Apply focused Go testing patterns.
remove-ai-slops
Removes AI-generated code smells from branch changes or an explicit file list behind regression tests. Use when the user asks to clean up, deslop, or remove AI-slop patterns from recent changes.
testing-anti-patterns
Reviews test code to identify and fix common testing anti-patterns including flaky tests, over-mocking, brittle assertions, test interdependency, and hidden test logic. Flags bad patterns, explains the specific defect, and provides corrected implementations. Use when reviewing test code, debugging intermittent or…
eval-leakage-audit
Audits whether a verification (eval/metric/experiment/holdout) actually secures independent external ground truth, or whether the designer, the model, and the scorer are just confirming each other in a circle — via a 21-pattern taxonomy. Read-only. Use before trusting any 'how we'll know it worked' — A/B tests…
coverage
Compute code coverage for active track or module. Targets 95%+ coverage with report and justification for uncovered lines. Complements TDD workflow.