Kiro Crew is a persistent development workspace where agents continue multi-step software work across sessions, schedules, and connected interfaces. Developers use it locally or remotely through a desktop app, web dashboard, CLI, Slack, or Discord, with unattended tasks and recurring jobs. The catalogue contains skills and instructions for working with this workspace.
Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/kirodotdev/KiroCrewnpx agentmods add skills/kirodotdev/kirocrew/kirocrew-prepare-prWrote 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/kirocrew-prepare-pr)<a href="https://agentmods.dev/skills/kirodotdev/kirocrew/kirocrew-prepare-pr"><img src="https://agentmods.dev/badge/skills/kirodotdev/kirocrew/kirocrew-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/kirodotdev/kirocrew/kirocrew-prepare-pr"><img src="https://agentmods.dev/badge/skills/kirodotdev/kirocrew/kirocrew-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 | $0.00085 | $0.14241 |
| Opus 5.5 | $0.00034 | $0.05696 |
| Sonnet 5.5 | $0.00017 | $0.02848 |
| Haiku 4.5 | $0.00009 | $0.01424 |
Grade C, and why
kirocrew-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 today.
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 — 749 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 merged PR: open it review-ready, then keep driving until CI and the review bots are satisfied and GitHub lands it. Opening the PR is the midpoint, not the end. Every Kiro Crew author — maintainer or outside contributor — runs this same loop, so it also states the repository's rules. It is for the Kiro Crew repository only: in any other repository, ignore it.
This file carries only what the loop executes: which script to run and what its
exit code means. A script's flags live in its usage text, each CI lane's rules in
references/ci.md, and the reasons in references/rationale.md (read it before
deviating).
Mode — decide once, at the start
| Signal in the request | Mode |
|---|---|
| Anything else, including ambiguity and a PR you opened incidentally | Full loop (default): ends by arming auto-merge and watching until it merges |
| 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 hold: "don't merge", "leave the merge to me", "review only" | Full loop without auto-merge |
Precedence: a stop signal wins only when it is the whole ask — "push this and make it green" is the full loop. A hold turns off Phase 4's auto-merge, nothing else.
- Full loop — Phase 0 once, then Phase 1 → 2 → 3 until review-ready, then Phase 4.
- 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 gh pr merge without --auto, and never bypass a required review or
check. Auto-merge hands the merge to GitHub, which lands it only once the repo's
own required reviews and checks pass.
Kiro Crew CI at a glance
Full detail: docs/ci/ci-and-reviews.md and CONTRIBUTING.md. CI wins over prose.
What ships with it
18 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 5.3 KB
- references/body-picture.md 3.1 KB
- references/ci.md 2.3 KB
- references/fallback-charters.md 1.2 KB
- references/gate-floor.md 19 KB
- references/rationale.md 40 KB
- scripts/_review_contract.py 70 KB runs code
- scripts/diff_signals.py 13 KB runs code
- scripts/enable_automerge.py 3.8 KB runs code
- scripts/green_age.py 26 KB runs code
- scripts/local_review.py 71 KB runs code
- scripts/monitor_armed.py 6.0 KB runs code
- scripts/pr_findings.py 36 KB runs code
- scripts/pr_status.py 121 KB runs code
- scripts/preflight.py 24 KB runs code
- scripts/prove.py 20 KB runs code
- scripts/push_guard.py 88 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.
- today Changed 0bd2cef85c77
- 4d ago Changed · -3 lines 0ee539166ff6
- 6d ago Changed b76f95f63e9c
- 8d ago Changed · +13 lines 86e5ce0fc0bb
- 9d ago Changed · +24 lines 1c9bb2b49b0e
- 10d ago Changed · -20 lines 12b72a6a9440
- 11d ago First seen · 735 lines · 85 tokens per session scan C 4aeb74169436
kirocrew-prepare-pr is a skill published in the GitHub repository kirodotdev/KiroCrew (4,449 stars, last pushed today), licensed Apache-2.0. It adds 85 tokens to every session and 14,241 once invoked, about $0.0003 per session on Opus 5.5. 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 2026-10-05.
Other skills, from other repositories
github-pr-workflow
GitHub PR lifecycle: branch, commit, open, CI, merge.
github-repo-management
Clone, create, fork repos; manage remotes, releases.
ship-change
Ship an OpenSpec change after openspec-apply completes. When only QA/manual tasks remain, marks them done (tested later), archives + syncs specs, commits, pushes, opens a PR against develop, watches CI, waits for CodeRabbit, auto-applies safe fixes and re-pushes, loops until CI green + no actionable review threads…
secret-leak-preflight
Use when about to commit, push, or publish -- staged changes touch config or environment files, generated artifacts (relay sessions, logs, build output) are being added, or the session handled credentials even indirectly.
chinese-commit-conventions
A Chinese-language reference for writing commit messages and changelogs, which record code changes and releases.
project-release-check
Validate this example project's release readiness. Use before publishing a release candidate.