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/kirodotdev/kirocrew/prepare-prnpx skills add kirodotdev/KiroCrew --skill prepare-prgit clone --depth 1 https://github.com/kirodotdev/KiroCrewWrote 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/kirodotdev/kirocrew/prepare-pr)<a href="https://agentmods.dev/skills/kirodotdev/kirocrew/prepare-pr"><img src="https://agentmods.dev/badge/skills/kirodotdev/kirocrew/prepare-pr.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 | $0.00000 | $0.10919 |
| Opus 5 | $0.00000 | $0.05459 |
| Sonnet 5 | $0.00000 | $0.02184 |
| Haiku 4.5 | $0.00000 | $0.01092 |
Grade C, and why
prepare-pr scanned grade C with 1 finding 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 yesterday.
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.
Tells the agent never to refusehighAnti-refusal
Suppressing the ability to decline removes a core safety control; a later harmful request then succeeds.
- **Never decline a reviewer's wider scope without a failing test proving the narrower scope is sufficient.** How it starts
The opening of the file, as written. The whole thing — 519 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Prepare PR
Drive the working tree to a review-ready PR, then keep driving until CI and the review bots are satisfied. Opening the PR is the midpoint, not the end.
This file carries only what the loop executes. The reasons behind the rules —
incident evidence, script internals, design history — are in
references/rationale.md; read it when you need to justify a deviation, not on
every load.
Mode — decide once, at the start
| Signal in the request | Mode |
|---|---|
| Anything else, including ambiguity and a PR you opened incidentally | Full loop (default) |
| An explicit stop: "update the PR", "push my changes", "sync my branch", "just update the body/description", "don't wait for CI" | Prepare-only |
| An explicit ship: "ship this PR", "land it", "auto-merge it once green" | Full loop + arm auto-merge at Phase 4 |
Precedence, when a request carries more than one signal: an explicit ship beats an explicit stop, and either beats the default. So "push this and make it green" is full loop — a stop signal only wins when it is the whole ask.
- Full loop — Phase 0 once, then Phase 1 → 2 → 3 repeatedly until review-ready or escalation.
- Prepare-only — Phase 0 once, then ONE pass of Phase 1 → 2 → push → a single
pr_status.pysnapshot → report → STOP. The Phase 2 gate still runs; a push always goes out locally-green. No server poll, no auto-merge. - Say in one line which mode you picked, so the user can redirect.
Never merge a PR yourself. Auto-merge (Phase 4) hands the merge to GitHub, which lands it only once the repo's own required reviews and checks pass. Generic remediation ("fix CI", "make it green") is not a ship request.
Review-ready — the definition
All four, together:
pr_status.pyexits 0 —PR Readinessstatus andreadiness: passedlabel green.- Mergeable: no conflicts, not draft, not
CHANGES_REQUESTED. - One clean commit on a feature branch (when the profile sets
single_commit). - Every raised concern answered on the PR — see "Dispositions" below.
What ships with it
14 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.
- profiles/kirocrew.json 3.8 KB
- references/gate-floor.md 16 KB
- references/rationale.md 14 KB
- scripts/_review_contract.py 18 KB runs code
- scripts/diff_signals.py 2.8 KB runs code
- scripts/enable_automerge.py 3.8 KB runs code
- scripts/local_review.py 69 KB runs code
- scripts/monitor_armed.py 5.9 KB runs code
- scripts/pr_findings.py 24 KB runs code
- scripts/pr_status.py 73 KB runs code
- scripts/preflight.py 6.1 KB runs code
- scripts/prove.py 19 KB runs code
- scripts/push_guard.py 20 KB runs code
- scripts/resolve_profile.py 15 KB runs code
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.
- yesterday Changed · +8 lines af3b5cb42d33
- 4d ago First seen · 511 lines · 0 tokens per session scan C 5893954d6021
prepare-pr is a skill published in the GitHub repository kirodotdev/KiroCrew (3,532 stars, last pushed yesterday), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 10,919 tokens. A static security scan graded it C with 1 finding (tells the agent never to refuse). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
commit
Generate git commit messages from staged changes.
conventional-git
Conventional Commits v1.0.0 branch naming, worktree naming, and commit message standards for GitHub and GitLab projects. Use when creating branches, naming worktrees, writing commits, generating commit messages, reviewing branch conventions, or setting up changelog automation. Apply when your project needs consistent…
commit
Atomic git commit with conventional message. Use when the user says "commit", "save my changes", "commit this", or wants to create a git commit. Stages specific files, writes a conventional commit message with body explaining non-obvious decisions. Never uses git add -A.
commit
Smart commit: bump version, find related issues, commit with Co-authored-by, push. Use when the user says 'commit' or wants to finalize changes.
git-commit-convention
写 git 提交信息、整理提交历史时使用——Conventional Commits 的格式、类型选择和拆分原则。.
ijfw-commit
Terse conventional commits. Trigger: commit, git commit, /ijfw-commit.