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 jimtin/production-ai --skill pr-production-gategit clone --depth 1 https://github.com/jimtin/production-aiWrote 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/jimtin/production-ai/pr-production-gate)<a href="https://agentmods.dev/skills/jimtin/production-ai/pr-production-gate"><img src="https://agentmods.dev/badge/skills/jimtin/production-ai/pr-production-gate/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/jimtin/production-ai/pr-production-gate"><img src="https://agentmods.dev/badge/skills/jimtin/production-ai/pr-production-gate.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 | $0.00119 | $0.02511 |
| Opus 5 | $0.00060 | $0.01256 |
| Sonnet 5 | $0.00024 | $0.00502 |
| Haiku 4.5 | $0.00012 | $0.00251 |
Grade A, and why
pr-production-gate 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 10d 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 — 152 lines — stays where its author put it; the contents beside it link to each section on GitHub.
PR Production Gate
Purpose
Use this skill to operate or extend the fully automatic PR production gate. The gate reviews GitHub PRs for a configured repo, validates them locally in containers, rejects unsafe PRs with evidence, promotes passing PRs through the configured deployment train, verifies provider deployments, and updates repo-specific learning profiles.
The default outcome is fail closed. If any required proof is missing, inconclusive, host-only, dependent on live providers during review, or tied to a moving SHA, the PR must not deploy.
Run Statuses
Every run ends in exactly one status from this closed set:
deployed: a candidate passed every gate and the promotion train completed with smoke proof.rejected: a candidate failed;REQUEST_CHANGESposted with redacted evidence.no_eligible_prs: nothing to review — reached through the no-work fast path, cheaply.already_running: a healthy lock exists; this run exits without touching it.waiting_on_author: eligible PRs are all awaiting changes from a previous rejection.blocked_infra: the doctor preflight failed closed (disk, Docker, orphaned state) — no review work attempted.
A run that cannot name its status is a failed run.
Run Economics
A gate that is expensive when idle will be turned off. Idle cost is a design requirement:
- Run a no-work fast path before any expensive setup: check the lock, query eligible PRs, and exit
no_eligible_prsoralready_runningin seconds — never build the full controller to discover there is nothing to do. - Bounded idle cost: the scheduled run's no-work path must stay cheap enough to run on every tick without anyone noticing.
- Lane proofs may be cached and reused only with integrity constraints: keyed by a content fingerprint of that lane's exact inputs, scoped to the lane, with a bounded TTL. A cached proof never substitutes for the SHA lock, and any doubt about cache validity invalidates it — fail closed, re-run the lane.
- Flaky tests are quarantined, never silently retried: a test that fails then passes without a code change gets a quarantine entry with an expiry date and a tracking issue. Quarantined tests cannot guard deploy lanes, and retry-until-green is forbidden.
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.
- 10d ago First seen · 152 lines · 119 tokens per session scan A c771e0eb5770
pr-production-gate is a skill published in the GitHub repository jimtin/production-ai (1 stars, last pushed 2mo ago), licensed MIT. It adds 119 tokens to every session and 2,511 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 2026-08-31.
Other skills, from other repositories
code-review-excellence
This skill should be used when the user asks to review a diff or pull request, write review comments, audit code quality, establish review standards, or improve how a team performs code review.
tech-debt-ci-review
Codex adapter for deep technical-debt and CI-stability audits. Use when asked to find test theater, flaky tests, missing or mis-scoped tests, brittle CI/toolchain behavior, structural debt blocking green PRs, or a remediation order for opencode-swarm.
aster-review-ci
Run aster code reviews non-interactively in CI, GitHub Actions, or from another agent. Covers aster review --pr, --json, --stream, --comment, diff-from-stdin, token handling, and filtering findings. Use when wiring aster into a pipeline, posting PR comments, or parsing review output programmatically.
git-pr-review
A read-only reviewer for GitHub pull requests, which are proposed code changes submitted for review. It produces an evidence-based report about whether a pull request should be merged.
code-that-fits-in-your-head
Software-engineering heuristics based on Mark Seemann's Code That Fits in Your Head (2021), updated for agent-driven development. Use when writing or reviewing code, refactoring accidental complexity or a Big Ball of Mud, controlling technical or architectural debt in generated code, designing APIs and invariants…
pr-quality-qa
Judge a local diff on test coverage, error handling, and whether the tests would fail if the code regressed, and return a PASS/WARN/CRITICALFAIL verdict. Use when you say qa review my changes, run the qa gate, or are these tests good enough. Do NOT use to run all six axes (use pr-quality-all), and do NOT use to write…