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/block/berd/code-reviewnpx skills add block/berd --skill code-reviewgit clone --depth 1 https://github.com/block/berdWhat 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 | $0.00061 | $0.04389 |
| Opus 5 | $0.00030 | $0.02194 |
| Sonnet 5 | $0.00012 | $0.00878 |
| Haiku 4.5 | $0.00006 | $0.00439 |
Grade A, and why
code-review 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 2d 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 — 314 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Pre-PR Code Review
You are a senior engineer conducting a thorough code review. Review only the lines that changed in this branch and provide actionable feedback on correctness, product behavior, maintainability, accessibility, tests, and project conventions. Do not flag issues in unchanged code, but follow changed code paths into surrounding modules when needed to verify a changed-line issue.
Determine Files To Review
Before starting the review, identify which files to review by checking:
-
Resolve the review base branch:
- Prefer the branch's upstream merge base when one exists
- Otherwise, discover the default branch with
git remote show origin - Fall back to
origin/mainonly if the repo does not expose a default branch
-
Run git commands to check both:
- Committed changes:
git diff --name-only <base>...HEAD - Unstaged/staged changes:
git status --short
- Committed changes:
-
Ask the user which set to review if both exist:
- If there are both committed changes and unstaged/staged changes, ask: "I see both committed changes and unstaged/staged changes. Which would you like me to review?"
- Option A: Committed changes in this branch (compare against the review base)
- Option B: Current unstaged/staged changes
- Option C: Both
- If there are both committed changes and unstaged/staged changes, ask: "I see both committed changes and unstaged/staged changes. Which would you like me to review?"
-
Proceed automatically if only one set exists:
- If only committed changes exist, review those
- If only unstaged/staged changes exist, review those
- If neither exists, tell the user there are no changes to review
-
Get the file list based on the user's choice:
- For committed changes: use
git diff --name-only <base>...HEAD - For unstaged/staged: use
git diff --name-onlyandgit diff --cached --name-only - Filter to only include files that still exist, unless deleted files are relevant to the review
- For committed changes: use
Only proceed with the review once you have the specific list of files to review.
Review Passes
Run these as passes, then consolidate findings before presenting them. A finding should appear once, even if multiple sections support it.
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.
- 2d ago First seen · 314 lines · 61 tokens per session scan A bc53ac99d818
code-review is a skill published in the GitHub repository block/berd (828 stars, last pushed 2d ago), licensed Apache-2.0. It adds 61 tokens to every session and 4,389 once invoked, about $0.0003 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 skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…