Borrowing it
Nothing to install: this file belongs to sagar-shirwalkar/collibra-atlas. 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/sagar-shirwalkar/collibra-atlas/main/.agents/skills/code-review/SKILL.mdgit clone --depth 1 https://github.com/sagar-shirwalkar/collibra-atlasWrote 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/sagar-shirwalkar/collibra-atlas/code-review)<a href="https://agentmods.dev/skills/sagar-shirwalkar/collibra-atlas/code-review"><img src="https://agentmods.dev/badge/skills/sagar-shirwalkar/collibra-atlas/code-review/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/sagar-shirwalkar/collibra-atlas/code-review"><img src="https://agentmods.dev/badge/skills/sagar-shirwalkar/collibra-atlas/code-review.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 | $0.00044 | $0.01468 |
| Opus 5 | $0.00022 | $0.00734 |
| Sonnet 5 | $0.00009 | $0.00294 |
| Haiku 4.5 | $0.00004 | $0.00147 |
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 11d 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 — 108 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Code Review
Tenets
- Review the code, not the author. Feedback addresses the change, not the person. No "you" — "This path lacks error handling."
- Automate what you can. Style, formatting, and lint are tools' jobs, not reviewers'. If it can be a CI check, don't review it by hand.
- Every comment earns its place. A vague concern ("this could be better") wastes the author's attention more than a clear blocking issue ("this SQL is injectable"). Say nothing, say it clearly, or say "approve".
- Bias toward action. A review that blocks for a week is worse than a review that approves with follow-up. Block only what would ship a bug; suggest everything else.
Leading words
- Triage — The first pass: assess scope, decide what to probe deeply, identify what needs immediate attention vs what can wait.
- Gate — A condition the change must meet before shipping. Gating issues block merge; everything else is a suggestion.
Phases
PHASE 1: Scout
Completion criterion: the PR's purpose, scope, and risk level are understood.
- Read the PR description and linked issue. What is the change meant to do?
- Scan the file list. How many files changed? (>400 lines across >10 files → suggest splitting.)
- Check CI status. If tests fail or lint is red, flag it immediately — no point reviewing code that doesn't pass its own bar.
- Identify the risk zone: does the change touch auth, data persistence, public API surfaces, or concurrency? Those files get a deeper probe.
PHASE 2: Triage
Completion criterion: every file has been read once; issues are captured by category, not yet classified by severity.
One pass through every changed file, top to bottom. For each file, check against the categories below. Capture every observation as a note — don't classify yet, don't skip anything because it seems minor.
- Correctness — Off-by-one, unhandled None/null, wrong branch taken, boundary condition missed, assumption violated.
- Security — Unvalidated input, injection surface, hardcoded secret, missing auth gate, data leak in error message. See SECURITY.md for deeper reference.
- Performance — Loop over a query, N+1, blocking call in async path, allocation in hot loop, unbounded growth.
- Maintainability — Magic number, duplicated logic, function doing too much, name that obscures intent, dead code.
- Test quality — Missing test for the change, test that mocks everything and asserts nothing, test that depends on another test's state.
What ships with it
1 file 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.
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.
- 11d ago First seen · 108 lines · 44 tokens per session scan A 1ff2faa27ead
code-review is a skill published in the GitHub repository sagar-shirwalkar/collibra-atlas (0 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 44 tokens to every session and 1,468 once invoked, about $0.0002 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 2026-08-31.
Other skills, from other repositories
autoreview
Pre-commit/ship code review: Codex default; optional Claude or Pi.
omh-code-review
This is a Hermes-native code-review workflow skill.
revdiff-plan
Review the last Codex assistant message (plan, analysis, or proposal) with inline annotations in a TUI overlay. Extracts the most recent response from Codex rollout files and opens it in revdiff for review and annotation. Activates on "revdiff-plan", "review plan with revdiff", "annotate plan", "review last response"…
code-reviewer
Code review specialist focused on patterns, bugs, security, and performance.
full-repo-review
Comprehensive four-wave review of all repo source files, producing a prioritized issue backlog.
agent-teams-simplify-and-harden
Implementation + audit loop using parallel agent teams with structured simplify, harden, and document passes. Spawns implementation agents to do the work, then audit agents to find complexity, security gaps, and spec deviations, then loops until code compiles cleanly, all tests pass, and auditors find zero issues or…