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.
git clone --depth 1 https://github.com/oalders/kitchen-sinkWrote 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/oalders/kitchen-sink/request-review)<a href="https://agentmods.dev/commands/oalders/kitchen-sink/request-review"><img src="https://agentmods.dev/badge/commands/oalders/kitchen-sink/request-review.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 5.1 | $0.00006 | $0.02814 |
| Opus 5 | $0.00003 | $0.01407 |
| Sonnet 5 | $0.00001 | $0.00563 |
| Haiku 4.5 | $0.00001 | $0.00281 |
Grade C, and why
request-review 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 6d 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.
Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
$ WORKDIR="$(mktemp -d "${TMPDIR:-/tmp}/review.XXXXXX")"; trap 'rm -rf "$WORKDIR"' EXIT How it starts
The opening of the file, as written. The whole thing — 328 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Code Review
Overview
Streamlined code review workflow that gets git SHAs from context and invokes a general-purpose code reviewer without blocking on permission prompts. This allows you to leave the window while the review runs unattended.
When to Use
Use this command when:
- You've completed a feature or bug fix
- Before merging to main
- After a major code change
- When you want a fresh perspective on your work
Don't use when:
- No code has been written yet
- Just starting work on an issue
Workflow
digraph code_review {
"Get git SHAs from context" [shape=box];
"Get issue details if fix-* branch" [shape=box];
"Invoke code-reviewer subagent" [shape=box];
"Review completes" [shape=box];
"Check if PR exists" [shape=diamond];
"Post review as PR comment" [shape=box];
"Ready to merge?" [shape=diamond];
"Approve PR" [shape=box];
"Display review to user" [shape=box];
"Address feedback" [shape=box];
"Get git SHAs from context" -> "Get issue details if fix-* branch";
"Get issue details if fix-* branch" -> "Invoke code-reviewer subagent";
"Invoke code-reviewer subagent" -> "Review completes";
"Review completes" -> "Check if PR exists";
"Check if PR exists" -> "Post review as PR comment" [label="Yes"];
"Check if PR exists" -> "Display review to user" [label="No"];
"Post review as PR comment" -> "Ready to merge?";
"Ready to merge?" -> "Approve PR" [label="Yes"];
"Ready to merge?" -> "Address feedback" [label="No/With fixes"];
"Approve PR" -> "Address feedback";
"Display review to user" -> "Address feedback";
}
Steps
1. Get Git SHAs
First, check conversation context (no Bash needed):
- Base SHA: Look for recent
git logoutput, gitStatus, or known commit reference - Head SHA: Shown in your own
git commitoutput or recent git commands
If not in context, run separate git commands:
# Run these as SEPARATE tool calls, not chained
git rev-parse origin/main # or HEAD~1, or specific commit
git rev-parse HEAD
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.
- 6d ago First seen · 328 lines · 6 tokens per session scan C faf951f72e04
request-review is a command published in the GitHub repository oalders/kitchen-sink (4 stars, last pushed 6d ago), licensed MIT. It adds 6 tokens to every session and 2,814 once invoked, about $0.0000 per session on Opus 5. A static security scan graded it C with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other commands, from other repositories
devkit.github.review-pr
Provides comprehensive GitHub pull request review with code quality, security, and best practices analysis. Use when reviewing a PR before merging.
speckit.spex.submit
Push and create PR for team review, with optional watch mode for CI monitoring.
git
The pre-finish status: branch, hygiene findings, message checks, workflow lint, template state.
code-review
Code review for branch changes. Analyzes git diff between branches with multi-level depth (low/medium/high). Matches changes against task description. Returns structured report with severity levels and verdict.
repo-audit
Audit a codebase (local or remote GitHub/GitLab) against architecture principles and requirements, surfacing drift, risk, and missing decisions.
advanced-code-review-context
Advanced Code Review Phase 2: Context Analysis - load previous reviews, PR history, declined items.