A workflow for reviewing code changed with AI and preparing a compliant pull request. It includes running tests and code checks, scanning for secrets, and following project standards.

Use it to review AI-generated changes, run the project's checks, investigate secrets, and prepare a pull request after a feature or bug fix.

It catches broken code, quality problems, and accidentally exposed credentials before changes are merged.

code-review — Skill for Claude Code and Codex by GSA-TTS: A workflow for reviewing code changed with AI and…

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/gsa-tts/agentic-coding-playbook/code-review

Any agent

npx skills add GSA-TTS/agentic-coding-playbook --skill code-review

Clone the repo

git clone --depth 1 https://github.com/GSA-TTS/agentic-coding-playbook

Made for: Claude Code, Codex.

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/gsa-tts/agentic-coding-playbook/code-review.svg)](https://agentmods.dev/skills/gsa-tts/agentic-coding-playbook/code-review)

Your own site

<a href="https://agentmods.dev/skills/gsa-tts/agentic-coding-playbook/code-review"><img src="https://agentmods.dev/badge/skills/gsa-tts/agentic-coding-playbook/code-review.svg" alt="Measured on agentmods" height="20"></a>

Per session 16 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,920 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 1 finding. 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.

Model	Per session	Once invoked
Fable 5	$0.00016	$0.01920
Opus 5	$0.00008	$0.00960
Sonnet 5	$0.00003	$0.00384
Haiku 4.5	$0.00002	$0.00192

Measured 4d ago against content hash c4b61b803239, 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 1 finding 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.

Runs shell commandslowCapability

Expected in a hook, worth knowing in a rule or an instructions file.

| 5.5 | No eval/exec with external data | No `eval()`, `exec()`, `Function()`, `child_process.exec(untrusted)` |

.agents/skills/code-review/SKILL.md · 190 lines

How it starts

The opening of the file, as written. The whole thing — 190 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Code Review and PR Workflow

Review AI-assisted code changes and create compliant pull requests.

Context loading: When writing code, load docs/CODING_STANDARDS_COMPACT.md (~500 words). When reviewing code, load the full docs/CODING_PRACTICES.md (~4,100 words). This skill references both.

When to Use

Before creating a pull request with AI-assisted changes
When reviewing code that an AI agent generated or modified
When a user asks "review this code" or "create a PR"
After completing a feature or bug fix, before merge

Step 1: Pre-PR Checks

Run automated checks before creating the PR. Fix all failures before proceeding.

1.1 Linter, Formatter, and Tests

Run the project's linter and full test suite. Detect the toolchain from config files (e.g., npm run lint && npm test, ruff check . && pytest, go vet ./... && go test ./...). All tests MUST pass before proceeding. If no linter is configured, flag this as a gap.

1.2 Secrets Scan

Run gitleaks detect --no-git -v (or grep the diff for key/secret/token/password patterns as a fallback). Any match MUST be investigated and real secrets removed immediately. See docs/CODING_PRACTICES.md Section 4.

1.3 Size and Complexity

Verify the changes respect project limits (per docs/CODING_PRACTICES.md Section 13.3):

Functions: 50 lines or fewer
Files: 400 lines or fewer (400-600 acceptable with justification)
Cyclomatic complexity: 10 or fewer per function
Parameters: 5 or fewer per function

Flag violations in the PR description with justification if they are intentional.

Step 2: Attribution

All AI-generated code MUST be attributed per AGENTS.md Section 2.1.

2.1 Co-authored-by Trailer

Every commit that includes AI-generated or AI-modified code MUST include a Co-authored-by: trailer (note: lowercase "authored"):

Co-authored-by: OpenCode Agent <[email protected]>

Format:

Appears after a blank line following the commit body
Uses lowercase Co-authored-by: (matches GitHub standard)
Email should match the user's verified email
One line per co-author

Read the full file on GitHub · 190 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.

4d ago First seen · 190 lines · 16 tokens per session scan A c4b61b803239

Subscribe to this mod's changes

code-review is a skill published in the GitHub repository GSA-TTS/agentic-coding-playbook (23 stars, last pushed 2d ago), licensed CC0-1.0. It adds 16 tokens to every session and 1,920 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 1 finding (runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Code review

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

code-review