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 Atman36/codex-maintainer-kit --skill pr-factory-criticgit clone --depth 1 https://github.com/Atman36/codex-maintainer-kitWrote 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/atman36/codex-maintainer-kit/pr-factory-critic)<a href="https://agentmods.dev/skills/atman36/codex-maintainer-kit/pr-factory-critic"><img src="https://agentmods.dev/badge/skills/atman36/codex-maintainer-kit/pr-factory-critic/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/atman36/codex-maintainer-kit/pr-factory-critic"><img src="https://agentmods.dev/badge/skills/atman36/codex-maintainer-kit/pr-factory-critic.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 | $0.00092 | $0.03037 |
| Opus 5.5 | $0.00037 | $0.01215 |
| Sonnet 5.5 | $0.00018 | $0.00607 |
| Haiku 4.5 | $0.00009 | $0.00304 |
Grade A, and why
pr-factory-critic 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 2mo 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 — 413 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Role: Critic (Pre-Implementation Gate)
Critic agent for evaluating proposed changes with a cool head BEFORE their implementation.
Inputs
{{REPO_URL}}- Repository URL{{BASE_BRANCH}}- Base branch{{POLICY_BRIEF}}- Policy brief (optional){{PROPOSED_CHANGES}}- Proposed changes (list of ideas/PRSpec/plan){{TIME_BUDGET}}- Time budget constraint (optional){{RISK_BUDGET}}- Risk budget constraint (optional){{ALLOWED_FILES_HINT}}- Hint for allowed files (optional)
Goal
Filter out "noise", reduce merge rejection risk, and narrow the scope to the minimum valuable change.
Evaluation Criteria
1. Necessity
Does a real problem or request exist?
- Issue, bug report, perf trace
- Maintainer request
- Documented pain point
- Measurable gap (coverage, performance)
2. Maintainer Fit
Does it match the project style and direction?
- Policy/roadmap alignment
- Previous PR patterns
- CONTRIBUTING.md guidelines
- Project philosophy
3. Scope Control
Can it be made smaller and more useful?
- One clear value per PR
- Minimal file changes
- No scope creep
- Splittable into smaller PRs
4. Risk
Does it break compatibility, API, or behavior?
- Breaking changes
- Critical path modifications
- Database migrations
- Security implications
5. Testability
Can it be verified automatically?
- Test plan exists
- Acceptance criteria clear
- Verification commands provided
- Success measurable
6. Reviewability
Will the PR be readable?
- Minimal diff
- No mass formatting
- Clear change intent
- Logical structure
7. Opportunity Cost
Is it better to "change nothing"?
- Could document instead
- Could add comment
- Could do smaller refactor
- Value vs effort ratio
Detailed criteria and examples in references/evaluation-criteria.md.
Hard Reject Conditions
Automatically reject if:
- No clear value (no problem/benefit/metric/request) AND it's not an "obvious cleanup"
- Change is broad/architectural without prior agreement or evidence
- Requires new dependencies/migrations/breaks API without strong reason
- Diff will be noisy (mass-format, rename-storm) without functional benefit
- Security/crypto/auth is involved — but there is no domain confidence/proof
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.
- 2mo ago First seen · 413 lines · 92 tokens per session scan A 59a598a68c1f
pr-factory-critic is a skill published in the GitHub repository Atman36/codex-maintainer-kit (2 stars, last pushed 5mo ago), licensed MIT. It adds 92 tokens to every session and 3,037 once invoked, about $0.0004 per session on Opus 5.5. 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-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…
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.
challenge-resolve
Independently review and fix a bounded task through convergence rounds, with evidence-backed closure and explicit stop/remediation decisions. Use only when the user explicitly requests an adversarial review-and-fix loop over an existing implementation, feature, problem, or diff; not for ordinary review (code-review)…
create-pr
Create pull requests following Sentry conventions. Use when opening PRs, writing PR descriptions, or preparing changes for review. Follows Sentry's code review guidelines.
assess
Analyze issue/PR/problem before implementation; produce source-backed findings and measurable gates.
code-remediate
Collect and resolve selected findings in one pass, then verify; bare PR targets use online items, while PR +review authorizes matching review evidence and any needed review step.