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 skills add TerminalSkills/skills --skill code-reviewergit clone --depth 1 https://github.com/TerminalSkills/skillsWrote 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/terminalskills/skills/code-reviewer)<a href="https://agentmods.dev/skills/terminalskills/skills/code-reviewer"><img src="https://agentmods.dev/badge/skills/terminalskills/skills/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/terminalskills/skills/code-reviewer"><img src="https://agentmods.dev/badge/skills/terminalskills/skills/code-reviewer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00061 | $0.01957 |
| Opus 5.5 | $0.00024 | $0.00783 |
| Sonnet 5.5 | $0.00012 | $0.00391 |
| Haiku 4.5 | $0.00006 | $0.00196 |
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 19d 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 — 259 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Code Reviewer
Overview
Perform structured code reviews that identify bugs, security issues, performance problems, and maintainability concerns. Provides prioritized, actionable feedback with specific fix suggestions.
Instructions
When a user asks you to review code, a file, a diff, or a pull request, follow this process:
Step 1: Understand the context
Before reviewing, determine:
- What does this code do? (feature, bugfix, refactor)
- What language and framework is it using?
- Are there tests included?
- Is this a full file or a diff/patch?
Read surrounding files if needed to understand the broader codebase context. Get the change itself with git diff main...HEAD (local branch) or gh pr diff 482 (pull request), and run the project's own linter and test command first so the review does not repeat what tooling already reports.
Step 2: Review using this checklist
Evaluate the code against each category in order of severity:
Correctness (Critical)
- Logic errors, off-by-one mistakes, wrong conditions
- Unhandled null/undefined/empty cases
- Race conditions or concurrency issues
- Incorrect error handling (swallowed exceptions, wrong error types)
- Missing input validation
Security (Critical)
- SQL injection, XSS, command injection
- Hardcoded secrets, API keys, passwords
- Improper authentication/authorization checks
- Unsafe deserialization, path traversal
- Missing rate limiting on public endpoints
Performance (High)
- N+1 queries in database loops
- Unnecessary re-renders in UI components
- Missing indexes for frequent queries
- Unbounded memory growth (loading entire datasets)
- Blocking operations on the main thread
Reliability (High)
- Missing error handling for external calls (network, file I/O)
- No retry logic for transient failures
- Missing timeouts on HTTP requests
- Resource leaks (unclosed connections, file handles)
Readability (Medium)
- Unclear variable or function names
- Functions doing too many things (> 30 lines is a smell)
- Deeply nested conditionals (> 3 levels)
- Missing or misleading comments
- Inconsistent naming conventions
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.
- 19d ago Changed · +4 lines 7edbe9e8668e
- 1mo ago First seen · 255 lines · 61 tokens per session scan A d0c7915377f5
code-reviewer is a skill published in the GitHub repository TerminalSkills/skills (177 stars, last pushed today), licensed Apache-2.0. It adds 61 tokens to every session and 1,957 once invoked, about $0.0002 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 2026-09-05.
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"…
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…
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…