code-review

A code-review method that uses a separate reviewer with fresh context to assess changes. It also defines how review findings should be written.

In plain words
What is it for?
It is for reviewing diffs and changes, coordinating code, security, and documentation reviews, and producing structured findings.
Why use it?
It reduces the risk that the person or agent who wrote code overlooks its problems when checking it.

Skill for Claude CodeCodex

Part of the team plugin — 42 skills, 13 agents, 2 hooks shipped together

Install

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.

agentmods
npx agentmods add skills/bostonaholic/team/code-review
Any agent
npx skills add bostonaholic/team --skill code-review
Clone the repo
git clone --depth 1 https://github.com/bostonaholic/team

Made for: Claude Code, Codex.

Or install team, the plugin that ships this one along with the rest of its 42 skills, 13 agents, 2 hooks.

Per session 66 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,985 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00066 $0.02985
Opus 5 $0.00033 $0.01492
Sonnet 5 $0.00013 $0.00597
Haiku 4.5 $0.00007 $0.00298

Measured 3d ago against content hash 7133bbdbfc75, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

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 3d 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.

skills/code-review/SKILL.md · 274 lines

How it starts

The opening of the file, as written. The whole thing — 274 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Code Review

Reviews must be performed by agents with fresh context. The generator (the agent that wrote the code) must never evaluate its own output. This separation prevents self-evaluation bias — the tendency to see what you intended to write rather than what you actually wrote.

Write the prose this skill governs at a seventh-grade reading level, in STE-flavored mode. Full methodology: writing-prose. Call the Skill tool with writing-prose and apply its ## Self-lint checklist before you finalize.

When Invoked Directly

When a user asks for a review in the main session ("review this diff", /code-review), the session itself is not a valid reviewer — it holds the conversation history this skill forbids. Do not review inline. Dispatch the code-reviewer agent (or, if unavailable, a fresh read-only subagent instructed to follow this skill) against the requested diff, then present its report in full, in the shape ## Report Format pins — never a summary of it. Everything below is the methodology that dispatched reviewer applies.

Generator-Evaluator Separation

The cardinal rule: Do not let the same model grade its own exam.

  • Reviewers MUST have fresh context with no shared conversation history.
  • Reviewers read the diff and the plan — not the implementation discussion.
  • Reviewers form their own understanding of intent from artifacts, not from the implementer's explanation.
  • A reviewer needing clarification flags it as an open question. It never asks the implementer.

Veto Without Authorship

The separation runs both directions. A reviewer blocks the line and changes nothing. A producer changes the tree and casts no verdict.

  • You hold no write tool. Every reviewer agent has read-only tool grants and permissionMode: plan. Report the defect. Never fix it. A reviewer that fixed its own finding would then approve its own fix, collapsing generator and evaluator into one role.
  • The veto is bounded. Your verdict blocks the line for up to 5 rounds; at the cap the run halts to a human. Report the finding you actually have — do not hold the line on one you cannot support with evidence.

Read the full file on GitHub · 274 lines

Changes

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.

  1. 3d ago First seen · 274 lines · 66 tokens per session scan A 7133bbdbfc75

Subscribe to this mod's changes

code-review is a skill published in the GitHub repository bostonaholic/team (11 stars, last pushed 3d ago), licensed MIT. It adds 66 tokens to every session and 2,985 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.

Related

Other skills, from other repositories

tutti-workspace-app-factory

Create, convert, or repair one Tutti workspace app as either a self-contained publishable package under package/ or a Chrome-style local debug app under .tutti/dev-app/. Use for mention://workspace-app-factory/create handoffs, mention://workspace-app-factory handoffs, standalone app generation, adapting existing…

tutti-os/tutti · 138 tokens

tutti-app-release

Set up, review, run, or debug external repositories that publish a Tutti workspace app through the reusable Tutti App Release GitHub Actions workflow. Use for caller workflows, tutti.app.json manifests, @tutti-os/app-release-tools, S3/CloudFront release hosting, latest.json, versions.json, catalog.json, catalog-only…

tutti-os/tutti · 80 tokens

tutti-record-agent-session-replay

From a Tutti checkout, run, audit, freshly replay, publish, or diagnose Session Replay cassettes that are driven by case-repository scenario scripts (CDP), not by interactive UI recording. Use for real-Provider capture while a scenario.mjs executes, cassette transport or semantic-state mismatches, fresh replay…

tutti-os/tutti · 127 tokens

analyze-performance-traces

Analyze Chrome, Chromium, Electron, React DevTools, or Perfetto-compatible JSON traces and audit user-reported profiling findings without loading large artifacts into context; prove trigger-to-render/layout chains, separate measured facts from source inference, find exact code choke points, classify forced layout and…

tutti-os/tutti · 127 tokens

tutti-ui-system

Use when working with @tutti-os/ui-system components, replacing local UI with shared components, querying component ids or metadata, promoting UI into shared base or business components, or maintaining UI-system storyboard inventory.

tutti-os/tutti · 46 tokens

tutti-architecture-review

Review tutti git diffs for project structure, layering, module ownership, and duplicate event-center infrastructure by planning focused architecture review tasks, then having the main agent orchestrate sub-agents for only the changed areas.

tutti-os/tutti · 48 tokens