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 Xakki/ai-agents-skills --skill prepare-prgit clone --depth 1 https://github.com/Xakki/ai-agents-skillsWrote 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/xakki/ai-agents-skills/prepare-pr)<a href="https://agentmods.dev/skills/xakki/ai-agents-skills/prepare-pr"><img src="https://agentmods.dev/badge/skills/xakki/ai-agents-skills/prepare-pr/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/xakki/ai-agents-skills/prepare-pr"><img src="https://agentmods.dev/badge/skills/xakki/ai-agents-skills/prepare-pr.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 | $0.00657 |
| Opus 5 | $0.00046 | $0.00329 |
| Sonnet 5 | $0.00018 | $0.00131 |
| Haiku 4.5 | $0.00009 | $0.00066 |
Grade A, and why
prepare-pr 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 — 50 lines — stays where its author put it; the contents beside it link to each section on GitHub.
prepare-pr
Gets the current branch ready for review. Default mode is draft-only: it prepares the description and stops — it does not push or open a PR unless the user asks. Stops on a red quality gate.
Git mechanics (commit format, no force-push, explicit-path staging, no trailers
beyond Agent: <zone>) follow the git-flow core. This
skill adds only the PR-assembly delta below.
Steps
- Sanity.
git status(clean? what's staged/untracked?) andgit log <base>..HEAD+git diff <base>..HEADto see what the PR contains. - Quality gate — delegate to
qa-check. Do not re-implement the checks here. If qa-check is red → stop, report, fix root cause first. - Secret / artifact leak guard. Warn on suspicious untracked or staged files
— never index them:
.env,*.pem,id_rsa,*.session,*credentials*,dump.sql,*.bak. Add specific files (git add <path>), nevergit add ./-A. - Draft the PR description from the commits — sections: Задача / Task, Что сделано / What changed, Что проверять / How to verify, Артефакты / Artifacts (links, migrations, config). Keep it factual.
- Stop (draft mode). Present the description + file list. Proceed to commit / push / open-PR only on explicit user request and per the mode chosen in ask-on-first-use.
Never (PR-specific)
- Commit directly to the base branch (master/main) without an explicit request.
- Push or open a PR automatically because the gate passed.
(General staging / force-push / no-verify / trailer rules → git-flow core.)
ask-on-first-use (per project)
Ask the user (don't guess) and offer to save to the project's .claude/:
- Base branch (
master/main/ other). - Mode —
draft(default),commit,push, orcreate-PR. - PR title convention + body template (any project-specific format).
- (optional) Secret deny-list additions beyond the defaults above.
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 · 50 lines · 92 tokens per session scan A 46dd2b2548ab
prepare-pr is a skill published in the GitHub repository Xakki/ai-agents-skills (6 stars, last pushed 20d ago), licensed MIT. It adds 92 tokens to every session and 657 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
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…
pr-description
Use when generating or updating a PR description for the current branch. Takes an optional issue number as argument.
retrospective-audit
Stage B of /prflow:retrospective-weekly: given a most-recent-first subset of one recurring pattern's occurrence-PR context bundles (bounded by auditbundlecap), re-derive the root cause and return one JSON object carrying a ranked findings array (one to three sub-patterns) — no edits, no worktree. Invoked as a subagent…
openclaw-github-dedupe
Investigate a cluster of GitHub issues and PRs, determine canonical candidates, post duplicate/related status, preserve contributor credit, and execute cleanup actions. Supports autonomous mode for provided-link-only closeout, merge/fix follow-through, changelog, and post-merge issue/PR cleanup.
openclaw-pr-batch-sweep
Select, review, repair, validate, and land batches of up to 20 low-risk OpenClaw contributor pull requests using Vincent's maintainer preferences and bounded sub-agent lanes. Use for "next 20", broad contributor PR sweeps, merge-candidate mining, or continued PR-batch work where drafts, maintainer work, trivial…