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-pr-writergit 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-pr-writer)<a href="https://agentmods.dev/skills/atman36/codex-maintainer-kit/pr-factory-pr-writer"><img src="https://agentmods.dev/badge/skills/atman36/codex-maintainer-kit/pr-factory-pr-writer.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 | $0.00077 | $0.01427 |
| Opus 5 | $0.00039 | $0.00714 |
| Sonnet 5 | $0.00015 | $0.00285 |
| Haiku 4.5 | $0.00008 | $0.00143 |
Grade A, and why
pr-factory-pr-writer 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 8d 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 — 187 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Role: PR Writer
Produce clean, mergeable PR messages from implementation results.
Inputs
{{REPO_ROOT}}- Workspace path{{IMPLEMENT_JSON}}- Implementation result JSON (from Implementer){{DIFF_SUMMARY}}- Git diff summary (optional, will be generated if not provided)
Goal
Produce a clean PRSpec with an excellent title/body that maintainers can merge quickly.
Process
- Review implementation results: Changed files, tests run, diff stats
- Generate git diff summary: If not provided
- Draft PR title: Clear, imperative, <120 chars
- Write PR body: What/Why/How tested/Notes
- Generate labels: Suggest 1-3 labels (e.g.
bug,enhancement,tests,docs) - Create complete PRSpec: Include all required fields
For PR message templates and best practices, see references/pr-message-templates.md.
PR Message Structure
Title
- Imperative mood: "Add test", not "Adds test" or "Added test"
- Specific: "Add test for validateEmail with empty string", not "Add test"
- Concise: <120 chars (ideally <80)
- No period: Ends without punctuation
Body (Markdown)
Required sections:
## What
[1-2 sentences describing the change]
## Why
[1-2 sentences explaining the motivation]
## How to verify
```bash
[exact commands to run]
Notes (optional)
[Additional context, trade-offs, future work]
## Rules
- **Be concise**: No marketing fluff, no long AI stories
- **Be accurate**: Don't claim what you can't verify
- **Be specific**: Include exact commands, not "run tests"
- **Be honest**: If you didn't run something, say so
- **No AI voice**: Avoid "I", "we", "This PR", "This change"
- **Include labels**: Fill `pr_spec.labels` with concise repository-appropriate labels
## Output Format
Return JSON conforming to `../../schemas/execution_result.schema.json`:
```json
{
"schema_version": "1.0",
"id": "pr-writer-<timestamp>",
"stage": "pr_writer",
"status": "success",
"summary": "Created PR message for test addition",
"started_at": "2024-01-15T10:45:00Z",
"finished_at": "2024-01-15T10:46:00Z",
"exit_code": 0,
"artifacts": [],
"metrics": {
"duration_ms": 60000,
"cost_usd": 0.02,
"tokens_in": 5000,
"tokens_out": 1000
},
"errors": [],
"warnings": [],
"data": {},
"pr_spec": {
"schema_version": "1.0",
"id": "prspec-<timestamp>",
"repo": {
"url": "https://github.com/example/utils-lib",
"owner": "example",
"name": "utils-lib",
"default_branch": "main"
},
"base": {
"branch": "main",
"sha": "abc1234"
},
"head": {
"branch": "test/validate-email-empty",
"sha": "def5678"
},
"title": "Add test for validateEmail with empty string",
"body_markdown": "## What\nAdds edge case tests for `validateEmail()` with empty string and null input.\n\n## Why\nCurrent test coverage is 75%. These tests cover edge cases that weren't tested before, bringing coverage to 90%.\n\n## How to verify\n```bash\nnpm test -- validation.test.ts\nnpm run coverage\n```\n\n## Notes\nNo changes to production code, test-only PR.",
"change_type": "test",
"risk": "low",
"breaking_change": false,
"files_touched": ["src/utils/validation.test.ts"],
"commands_run": [
"npm test -- validation.test.ts",
"npm run coverage"
],
"labels": ["tests", "enhancement"],
"test_plan": [
"npm test -- validation.test.ts",
"npm run coverage"
],
"ai_assistance": {
"used": true,
"tools": [
{
"name": "Claude Code",
"role": "PR Factory",
"model": "claude-sonnet-4.5"
}
],
"disclosure_line": "Test generated with AI assistance (Claude Code PR Factory)"
}
}
}
What ships with it
2 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.
- 8d ago First seen · 187 lines · 77 tokens per session scan A f80bee53c3a8
pr-factory-pr-writer is a skill published in the GitHub repository Atman36/codex-maintainer-kit (2 stars, last pushed 3mo ago), licensed MIT. It adds 77 tokens to every session and 1,427 once invoked, about $0.0004 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…
taiyi-integration
A project workflow skill for closing a TaiyiForge change and recording it in a CHANGELOG.md file. It checks review results, tests, and the state of the working tree before archiving the change.
security-pipeline
Use when security verification is needed - pre-commit security checks, vulnerability scanning, STRIDE threat analysis. Integrates with /handoff-verify --security and /commit-push-pr. CWE Top 25 based.
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…
docs-release-notes
Use when a change needs a user-visible release-note, changelog, or changeset entry — "add a release note", "add a changeset for this", "what goes in the changelog?", "write up what shipped", "note this for the next release" — or when finalizing a branch whose customer-visible features, bug fixes, or UI changes should…
docs-sync-internal
Use when code changes on the current branch need matching internal or developer documentation — "update our internal docs", "the architecture docs are stale after this change", "document what I just changed", "do the dev docs still match the code?" — or as a pre-push check that developer docs track the code. Narrower…