devs:code-review

devs:code-review is a skill for Claude Code, Codex from aaronbassett/agent-foundry. It costs 78 tokens per session (512 once invoked), scanned A, original, MIT.

A method for reviewing code changes such as diffs, branches, pull requests, or named files. It requires suspected problems to be checked against the actual code and ranks confirmed findings by severity.

In plain words
What is it for?
Use it for code reviews of proposed changes. Language-specific style, security, and dependency checks may require additional skills.
Why use it?
It reduces speculative review comments and helps focus attention on issues supported by evidence. It also defines how to scope the change and assess its wider effects.

Skill for Claude CodeCodex

Part of the devs plugin — 8 skills, 1 command, 7 agents 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/aaronbassett/agent-foundry/code-review
Any agent
npx skills add aaronbassett/agent-foundry --skill code-review
Clone the repo
git clone --depth 1 https://github.com/aaronbassett/agent-foundry

Made for: Claude Code, Codex.

Or install devs, the plugin that ships this one along with the rest of its 8 skills, 1 command, 7 agents.

Wrote 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.

agentmods badge for devs:code-review

README.md
[![agentmods](https://agentmods.dev/badge/skills/aaronbassett/agent-foundry/code-review.svg)](https://agentmods.dev/skills/aaronbassett/agent-foundry/code-review)
Your own site
<a href="https://agentmods.dev/skills/aaronbassett/agent-foundry/code-review"><img src="https://agentmods.dev/badge/skills/aaronbassett/agent-foundry/code-review.svg" alt="Measured on agentmods" height="20"></a>
Per session 78 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 512 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 $0.00078 $0.00512
Opus 5 $0.00039 $0.00256
Sonnet 5 $0.00016 $0.00102
Haiku 4.5 $0.00008 $0.00051

Measured 4d ago against content hash b39d0dddc8ee, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

devs: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 4d 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.

plugins/devs/skills/code-review/SKILL.md · 29 lines

What it actually says

Code Review — Method

The review method for producing evidence-based, severity-ranked findings. A finding that hasn't been checked against the actual code is a guess, not a finding.

This skill deliberately ships no analysis scripts: a reviewer that can read the diff, search the codebase, and run the project's own toolchain outperforms any metric-generating script — run the project's real commands instead.

Reference routing

Reference Use when
diff-scoping.md Getting the right change-set, reading order, blast radius, scope discipline
review-method.md The evidence bar per finding class; converting suspicion into verified finding
severity-taxonomy.md Blocking/Important/Minor tiers and the evidence each requires

Delegation

  • Security findings — the devs:security-core skill (its review-lens reference is the weighted security checklist).
  • Language-idiom findings — the matching language skill defines idiomatic: devs:rust-core, devs:python-core, devs:typescript-core, devs:react-core (+ devs:react-components for component house style). Load the skill for each language in the diff.
  • Dependency findings (new packages in the diff, lockfile changes) — the devs:deps-core skill.

The method in one paragraph

Scope the exact change-set and read it in dependency order. Judge every hunk in its real context — the whole function, its callers, the data it touches. For each candidate finding, attempt refutation against the code (guards, types, existing tests), verify by execution where cheap, and file only what survives — at the severity its verified impact supports, with file:line and a concrete failure scenario. Run the project's own gauntlet (its lint/typecheck/test commands, not a guessed list) and never flag what the project's tooling already enforces or explicitly disables.

Files

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.

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. 4d ago First seen · 29 lines · 78 tokens per session scan A b39d0dddc8ee

Subscribe to this mod's changes

devs:code-review is a skill published in the GitHub repository aaronbassett/agent-foundry (4 stars, last pushed 19d ago), licensed MIT. It adds 78 tokens to every session and 512 once invoked, about $0.0004 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.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

brainstorming

You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.

obra/superpowers · 37 tokens

auto-perf-optimize

Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.

microsoft/vscode · 62 tokens

chat-perf

Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.

microsoft/vscode · 51 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens