Borrowing it
Nothing to install: this file belongs to Peaky8linders/claude-cortex. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/Peaky8linders/claude-cortex/main/.claude/commands/review-and-ship.mdgit clone --depth 1 https://github.com/Peaky8linders/claude-cortexWrote 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/commands/peaky8linders/claude-cortex/review-and-ship)<a href="https://agentmods.dev/commands/peaky8linders/claude-cortex/review-and-ship"><img src="https://agentmods.dev/badge/commands/peaky8linders/claude-cortex/review-and-ship/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/commands/peaky8linders/claude-cortex/review-and-ship"><img src="https://agentmods.dev/badge/commands/peaky8linders/claude-cortex/review-and-ship.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 | $0.00023 | $0.00718 |
| Opus 5 | $0.00012 | $0.00359 |
| Sonnet 5 | $0.00005 | $0.00144 |
| Haiku 4.5 | $0.00002 | $0.00072 |
Grade A, and why
review-and-ship 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 9d 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 — 80 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/review-and-ship — Deep Code Review, Fix, Test, and Ship PR
You are a senior engineering lead running the full review-to-ship pipeline. Your job is to review the current branch's changes, fix all issues found, verify tests pass, and create a PR — all in one continuous flow.
Step 1: Pre-flight Checks
Before anything else, verify the environment is ready:
git remote -v # remote configured?
gh auth status # gh CLI authenticated?
git diff main...HEAD --stat # branch has diverged from main?
If any check fails, fix it before proceeding. If the branch has no changes vs main, STOP — tell the user there's nothing to review.
Step 2: Deep Code Review with Parallel Agents
Spawn 3 parallel agents to review the diff against the base branch:
- Security & Safety Agent — OWASP top 10, injection risks, hardcoded secrets, unsafe deserialization, auth gaps
- Code Quality Agent — Dead code, duplicated logic, unused imports, spaghetti control flow, naming inconsistencies, missing error handling
- Architecture & Performance Agent — Circular dependencies, N+1 queries, missing indexes, oversized payloads, wrong abstraction level
Each agent should:
- Read the full diff:
git diff main...HEAD - Read any files that need full context
- Return findings as a prioritized list with severity (critical/high/medium/low)
Step 3: Consolidate & Fix
Merge all agent findings into a single prioritized list. Then:
- Fix all critical and high issues — these are blockers
- Fix medium issues if the fix is straightforward (< 5 lines)
- Note low issues but skip them unless trivial
- Do NOT fix cosmetic-only issues that don't affect correctness
Step 4: Run Full Test Suite
cd brainiac && python -m pytest tests/ -v
cd contextscore && pytest tests/ -v
cd cortex && npm test
If tests fail: diagnose root cause, fix source code, re-run. Do not proceed until all tests pass.
Step 5: Create PR
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.
- 9d ago First seen · 80 lines · 23 tokens per session scan A 534a060650da
review-and-ship is a command published in the GitHub repository Peaky8linders/claude-cortex (11 stars, last pushed 2mo ago), licensed MIT. It adds 23 tokens to every session and 718 once invoked, about $0.0001 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 2026-08-30.
Other commands, from other repositories
release-readiness
Trigger a pre-merge release readiness review on a GitHub PR, GitLab MR, or local branch.
release
Release manager for frontend and mobile. Writes App Store notes, user-facing changelog, flags stale docs and landing copy. Actions: notes | changelog | docs | sync.
ia-document-release
Post-ship documentation sync. Reads all project docs, cross-references the diff, updates README/ARCHITECTURE/CONTRIBUTING/CLAUDE.md to match what shipped, polishes CHANGELOG voice, and optionally bumps the version.
ia-changelog
Create engaging changelogs for recent merges to main branch.
release
Bump version, commit, push, mirror to ai-skills, and update local plugin.
harness:pr-fleet
Autonomous PR-queue land orchestrator — triage the open-PR queue, fan out worktree-isolated review-assist subagents that run the real code-review pipeline, independently verify each PR by all-OS CI and review verdict, and land exactly the PRs a human authorized up front. Never silently auto-merges unreviewed work.