Borrowing it
Nothing to install: this file belongs to r3bl-org/r3bl-open-core. 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/r3bl-org/r3bl-open-core/main/.agents/skills/code-review/SKILL.mdgit clone --depth 1 https://github.com/r3bl-org/r3bl-open-coreWrote 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/r3bl-org/r3bl-open-core/code-review)<a href="https://agentmods.dev/skills/r3bl-org/r3bl-open-core/code-review"><img src="https://agentmods.dev/badge/skills/r3bl-org/r3bl-open-core/code-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 | $0.00015 | $0.00768 |
| Opus 5 | $0.00008 | $0.00384 |
| Sonnet 5 | $0.00003 | $0.00154 |
| Haiku 4.5 | $0.00002 | $0.00077 |
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 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.
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 — 81 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Interactive Code Review Workflow
Use this skill when the user runs the /code-review slash command or uses any of these
natural language triggers:
- "show me the code changes you made here, one chunk at a time interactively. i will type 'good' if i approve"
- "review the code changes chunk by chunk"
- "interactive code review"
- "review changes interactively"
Purpose
Provides a structured, low-cognitive-load, interactive code review experience in chat. Instead of dumping large diffs or requiring the user to navigate full files in an external editor, changes are broken into small, logical, self-contained diff chunks presented one turn at a time.
Workflow
1. Collect & Partition Diff Chunks
- Run
git diffon the current working tree (or inspect specific target files). - Partition the changes into small, logical, self-contained chunks:
- Separate by file whenever possible.
- For larger files, divide into logical functional blocks (e.g., imports, core logic, tests).
- Determine total chunk count (N).
2. Present Chunks Iteratively (One Turn per Chunk)
For each chunk (e.g., Chunk X of N):
- Heading & File Link:
### Chunk X of N: path/to/file.rs(use clickable markdown file links). - Context & Rationale: Provide a concise 1-2 sentence explanation of what changed in this chunk and why.
- Test Coverage Verification:
Invoke the
check-test-coverageskill for the modified file:- Verify that all custom logic branches, state transitions, and error paths in this file/chunk are covered by tests.
- Confirm zero test bloat (no redundant tests asserting standard library behaviors, compiler derives, or third-party macros).
- Report a concise 1-line coverage status.
- Diff Snippet:
Provide a clean
diffcode block containing only the relevant hunk. - Approval Prompt:
Ask:
Please reply with **"good"** to approve and move to Chunk X+1. - STOP and WAIT: Do NOT output subsequent chunks in the same turn. Yield control and wait for user input.
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 · +13 lines 287adca958f5
- 7d ago First seen · 68 lines · 15 tokens per session scan A 791eacafeb40
code-review is a skill published in the GitHub repository r3bl-org/r3bl-open-core (483 stars, last pushed today), licensed Apache-2.0. It adds 15 tokens to every session and 768 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 skills, from other repositories
gh-find-prs
Survey open Codewhale PRs and triage each for mergeability and disposition against the real landing branch.
gh-compile-issues
Triage N GitHub issues into a coverage matrix: fetch each, check current code, classify already-done/quick-fix/design/defer with cited evidence.
review
Read-only correctness review with actionable findings first, tight file/line evidence, severity, and a concise residual-risk summary.
simplify
Improve clarity and reduce needless complexity after behavior is understood; preserve behavior and keep cleanup separate from correctness fixes.
cmd-review
Review the current diff or selected files (usage: /review [--last-diff|--target |--file |files...] [--style ]).
m15-anti-pattern
Use when reviewing code for anti-patterns. Keywords: anti-pattern, common mistake, pitfall, code smell, bad practice, code review, is this an anti-pattern, better way to do this, common mistake to avoid, why is this bad, idiomatic way, beginner mistake, fighting borrow checker, clone everywhere, unwrap in production…