Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add clafollett/lafollettlabs-claude-plugins/plugin install code-reviewerWrote 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/clafollett/lafollettlabs-claude-plugins/code-reviewer)<a href="https://agentmods.dev/skills/clafollett/lafollettlabs-claude-plugins/code-reviewer"><img src="https://agentmods.dev/badge/skills/clafollett/lafollettlabs-claude-plugins/code-reviewer/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/clafollett/lafollettlabs-claude-plugins/code-reviewer"><img src="https://agentmods.dev/badge/skills/clafollett/lafollettlabs-claude-plugins/code-reviewer.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 | $0.00128 | $0.05950 |
| Opus 5.5 | $0.00051 | $0.02380 |
| Sonnet 5.5 | $0.00026 | $0.01190 |
| Haiku 4.5 | $0.00013 | $0.00595 |
Grade A, and why
code-reviewer 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 1mo 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 — 596 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Expert Code Review
Lean, pragmatic code reviews with scope discipline. Stack-specific PE sub-agents do the heavy lifting; the parent skill orchestrates dispatch and consolidates findings.
Phase 1: Scope Analysis
Determine review type from the user's request:
| User Request | Review Type | What to Review |
|---|---|---|
| "Review my branch" / "Review this PR" | Branch Diff | git diff main...HEAD |
| GitHub PR URL or "Review PR #N" | PR Review | git diff <target>...<source> (auto-checkouts source branch) |
| "Review staged changes" | Staged Diff | git diff --cached |
| "Review these files: X, Y, Z" | Specific Files | Read and review entire files |
| "Review the src/services folder" | Folder | Read and review all files in folder |
| "Review this code" + pasted code | Ad-hoc | Review the provided code |
Branch / Staged
git diff main...HEAD # branch diff
git diff --cached # staged changes
if current_branch == "main":
ask user which branch to review (do NOT proceed)
PR
gh pr view <PR_NUMBER> --json number,url,headRefName,baseRefName,author
git checkout <source_branch>
git pull
git diff <target_branch>...<source_branch>
Capture: source branch, target branch, PR number, PR URL, author. Store for Phase 6.
Critical: Review files MUST be committed to the source branch, never to main.
Files / Folders / Ad-hoc
Read the files directly. No diff context — review entire content.
Review Name (used for output filename)
if branch matches "<type>/<issue-id>-<description>":
name = issue_id # e.g., "983"
elif on a branch (no issue ID):
name = slugify(branch) # e.g., "fix-code-reviewer-cleanup"
else:
ask user for a short descriptive name
PE Routing
git diff main...HEAD --stat | tail -1 # branch reviews (informational)
git diff <target>...<source> --stat | tail -1 # PR reviews (informational)
matching_pes = PEs whose Stack Map paths intersect with files in the diff
if matching_pes is empty:
approach = "generic" # primary runs generic three-pass (no PE expertise available)
elif len(matching_pes) == 1:
approach = "single_pe" # dispatch the one matching PE
else:
approach = "multi_pe" # dispatch all matching PEs in parallel
What ships with it
3 files 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.
- 1mo ago First seen · 596 lines · 128 tokens per session scan A 1d5718e4784f
code-reviewer is a skill published in the GitHub repository clafollett/lafollettlabs-claude-plugins (2 stars, last pushed 2mo ago), licensed MIT. It adds 128 tokens to every session and 5,950 once invoked, about $0.0005 per session on Opus 5.5. 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
Structured code review through the shared OpenClaw agent-skills installation.
omh-code-review
This is an OMH code-review workflow skill, projected for Agent Skills hosts (Claude Code, Codex, Cursor, opencode, OpenClaw, pi).
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"…
re0-merge
Review and land an external contribution the way this suite does: gate it against the thesis, land it with the author's credit intact, complete a new skill rather than merging it raw, then approve, credit, and explain before closing. Use when reviewing a pull request, as any collaborator or maintainer, not only the…
explore-unknowns
Guide the user through a quadrant walk that maps the unknowns of a task — open by listing the known knowns, then work through known unknowns, unknown knowns, and unknown unknowns one stage at a time, ending with a complete four-quadrant map in the user's hands. Use when a request is ambiguous or underspecified, the…
asplos-writing-style
Use when drafting or revising ASPLOS prose — engineering the first two pages that rapid review actually reads, stating the cross-layer insight as one quotable sentence, structuring per-layer mechanism sections, writing bounded claims, and fitting everything into 11 self-contained pages that include figures and…