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-publishergit 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-publisher)<a href="https://agentmods.dev/skills/atman36/codex-maintainer-kit/pr-factory-publisher"><img src="https://agentmods.dev/badge/skills/atman36/codex-maintainer-kit/pr-factory-publisher/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-publisher"><img src="https://agentmods.dev/badge/skills/atman36/codex-maintainer-kit/pr-factory-publisher.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 | $0.00089 | $0.00999 |
| Opus 5 | $0.00044 | $0.00500 |
| Sonnet 5 | $0.00018 | $0.00200 |
| Haiku 4.5 | $0.00009 | $0.00100 |
Grade A, and why
pr-factory-publisher 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 — 119 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Role: Publisher
Publish an implemented change as a GitHub pull request.
Inputs
{{REPO_ROOT}}- Local repository path{{REPO_URL}}- Upstream repository URL (preferred){{BASE_BRANCH}}- Base branch (default:main){{HEAD_BRANCH}}- Head branch (must exist locally and be checked out){{PRSPEC_JSON}}- Final PRSpec JSON (from PR Writer or Pipeline)
Preconditions
- Work is already implemented and committed (Publisher should not edit code).
- User explicitly requested publishing (fork/push/PR). If not requested, return
status="skipped".
Process
-
Verify git state
git status --porcelainis empty (or only expected files)- Current branch is
{{HEAD_BRANCH}} - Branch has commits ahead of base
-
Run safety gate (recommended)
- Scan for forbidden tool-state files and secret-ish strings before pushing.
- If PR Factory kit tools are available, run (from the kit repo root):
python tools/quality_gate.py --repo {{REPO_ROOT}} --base-ref origin/{{BASE_BRANCH}} --prspec {{PRSPEC_JSON}} --enforce-files-touched- Optional strict cleanup: add
--autoclean-unplanned
- If the repo has no
origin/{{BASE_BRANCH}}, run againstHEADor skip and record a warning.
-
Check GitHub CLI readiness
gh auth status(must be logged in)- Avoid depending on external
jqbinary; preferghbuilt-ins (--json,--jq,--template).
-
Fork (if needed) + configure remote
gh repo fork {{REPO_URL}} --clone=false(idempotent for existing forks)- Ensure a git remote exists (e.g.
fork) pointing to your fork.
-
Push
git push -u <fork-remote> {{HEAD_BRANCH}}
-
Create PR
- Use PRSpec
titleandbody_markdown. - Only claim success if you have the PR URL.
- Verify via
gh pr viewand capture URL/number.
- Use PRSpec
Output Format
Return JSON conforming to ../../schemas/execution_result.schema.json:
{
"schema_version": "1.0",
"id": "publish-<timestamp>",
"stage": "publish",
"status": "success",
"summary": "Opened PR for <owner>/<repo> from <forkOwner>:<headBranch>",
"started_at": "2026-02-12T16:12:00Z",
"finished_at": "2026-02-12T16:14:00Z",
"exit_code": 0,
"stdout": "",
"stderr": "",
"artifacts": [],
"metrics": {
"duration_ms": 120000,
"cost_usd": 0.0,
"tokens_in": 0,
"tokens_out": 0
},
"errors": [],
"warnings": [],
"data": {
"fork": {
"url": "https://github.com/<you>/<repo>",
"owner": "<you>",
"remote_name": "fork"
},
"push": {
"remote": "fork",
"branch": "<headBranch>"
},
"pr": {
"url": "https://github.com/<upstreamOwner>/<repo>/pull/123",
"base": "main",
"head": "<you>:<headBranch>"
},
"commands_run": [
"gh auth status",
"gh repo fork ... --clone=false",
"git push -u fork <headBranch>",
"gh pr create ...",
"gh pr view ... --json url,number"
],
"notes": []
}
}
What ships with it
1 file 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 · 119 lines · 89 tokens per session scan A 914cf644faab
pr-factory-publisher is a skill published in the GitHub repository Atman36/codex-maintainer-kit (2 stars, last pushed 3mo ago), licensed MIT. It adds 89 tokens to every session and 999 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…