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 agentmods add skills/atman36/codex-maintainer-kit/pr-factory-analystnpx skills add Atman36/codex-maintainer-kit --skill pr-factory-analystgit 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-analyst)<a href="https://agentmods.dev/skills/atman36/codex-maintainer-kit/pr-factory-analyst"><img src="https://agentmods.dev/badge/skills/atman36/codex-maintainer-kit/pr-factory-analyst.svg" alt="Measured on agentmods" 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 | $0.00107 | $0.01533 |
| Opus 5 | $0.00053 | $0.00766 |
| Sonnet 5 | $0.00021 | $0.00307 |
| Haiku 4.5 | $0.00011 | $0.00153 |
Grade A, and why
pr-factory-analyst 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 5d 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 — 204 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Role: Analyst
Find concrete, merge-worthy PR candidates through deep analysis.
Inputs
{{REPO_ROOT}}- Workspace path{{FOCUS}}- Analysis focus area (examples: docs, tests, bugfix, perf, refactor, ci, dx){{SCOUT_JSON}}- Optional Scout output for dynamic focus and config reuse
Goal
Produce up to 5 concrete PR candidates that are likely to be accepted.
Process
- Understand focus area: What type of improvements are we looking for?
- If
{{FOCUS}}is empty/auto, infer from Scout output. - If Scout indicates weak test posture (e.g., low coverage, missing tests, test-related blockers), switch focus to
tests.
- If
- Analyze codebase: Read relevant files, check coverage, find gaps
- Identify opportunities: Concrete improvements that maintainers will want
- Assess quality: Each candidate meets quality bar (necessity, scope, verifiability)
- Rank by merge probability: Prefer obvious wins over subjective improvements
For detailed quality criteria and examples, see references/candidate-quality.md.
Candidate Quality Bar
Each candidate must include:
Why Maintainers Will Want This
- User pain: Fixes actual user issue
- Correctness: Fixes bug or incorrect behavior
- Reliability: Improves stability or test coverage
- DX: Makes development easier or clearer
Where (Minimal Scope)
- Specific file paths
- Function/class/module names
- Estimated LOC (<100 preferred)
- Clear boundaries
How to Verify
- Exact commands to run
- Expected output
- Manual verification steps if needed
Risk Assessment
- Low/medium/high
- What could break
- Rollback plan if applicable
Rules
- Stack-agnostic: Follow repo conventions, don't impose your stack
- One PR = One Value: Each candidate should be independently mergeable
- Prefer low-risk wins: Docs, tests, small bugfixes, clearer errors, minor perf with proof
- Avoid high-risk changes: Mass formatting, big refactors, dependency changes, API breaks
- Schema-valid JSON payload: Build payload conforming to
ExecutionResult - Persist analysis JSON: Write payload to
{{ARTIFACT_DIR}}/analyst-<timestamp>.json - Chat output format: Return only
SAVED_JSON_PATH=<absolute_path_to_json> - Scope context explicitly: Return
data.related_filesto constrain downstream implementation context
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.
- 5d ago First seen · 204 lines · 107 tokens per session scan A dbefea37de17
pr-factory-analyst is a skill published in the GitHub repository Atman36/codex-maintainer-kit (2 stars, last pushed 3mo ago), licensed MIT. It adds 107 tokens to every session and 1,533 once invoked, about $0.0005 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
git-workflow
This skill should be used when the user asks to "create git commit", "manage branches", "follow git workflow", "use Conventional Commits", "handle merge conflicts", or asks about git branching strategies, version control best practices, pull request workflows. Provides comprehensive Git workflow guidance for team…
daily-paper-generator
Use when the user asks to generate daily paper digests on a general topic. This skill supports both arXiv and bioRxiv (or either one), then produces structured Chinese/English summaries for selected papers.
codex-autoresearch
Run autonomous, measurable experiments in a Git repository: change one hypothesis, verify a numeric metric, keep improvements, and revert failures. Use when the user wants Codex to keep iterating toward a numeric target in the foreground or as a detached background run. Do not use for ordinary one-shot coding…
map-wayfind
Decision-frontier wayfinding: build and work a durable map of open design decisions BEFORE planning, for large or foggy efforts where /map-plan would force premature decomposition. Use when a task is too big or too vague to decompose — many unknowns, tangled decisions, or "I'm not even sure what to build yet" — and…
map-fast
Minimal workflow for small, low-risk changes — no planning, no learning.
clipboard
Copy text to clipboard with optional rich formatting. Triggers on "copy to clipboard", "copy that", "pbcopy", "copy formatted", "copy rich text".