A multi-pass code-review workflow that examines local changes and asks an independent read-only reviewer to check them as well. It focuses on real defects in logic, state changes, persistence, concurrency, security, user-visible behavior, and tests.

Use it before merging code or after a significant refactor, especially when changes affect asynchronous work, stored data, terminal interfaces, tools, secrets, or network boundaries.

It provides a second review of important changes and helps identify failures that a single inspection may overlook. It keeps unrelated work in the repository untouched.

code-review — Skill by FTShare-Lab

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/ftshare-lab/agent-claim-network/code-review

Any agent

npx skills add FTShare-Lab/agent-claim-network --skill code-review

Clone the repo

git clone --depth 1 https://github.com/FTShare-Lab/agent-claim-network

Made for: Claude Code, Codex.

Per session 41 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,091 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.

Model	Per session	Once invoked
Fable 5	$0.00041	$0.01091
Opus 5	$0.00020	$0.00545
Sonnet 5	$0.00008	$0.00218
Haiku 4.5	$0.00004	$0.00109

Measured 3d ago against content hash b24c890c3e76, 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.

.agents/skills/code-review/SKILL.md · 91 lines

How it starts

The opening of the file, as written. The whole thing — 91 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Multi-Pass Code Review

1. Define the review range

Inspect git status, the relevant diff, and the surrounding implementation. Preserve unrelated working-tree changes. Review the code that actually runs; do not substitute an old PRD for the current behavior.

2. Perform the local review

Follow the repository's AGENTS.md and focus on actionable defects:

business-logic and state-transition gaps;
persistence, recovery, compatibility, and protocol-boundary problems;
async blocking, cancellation, locking, process-lifecycle, and resource leaks;
tool authorization, path handling, secrets, and network exposure;
user-visible TUI errors, misleading status, and broken interaction flows;
missing tests for realistic failure paths.

Do not report formatting already covered by rustfmt, speculative low-probability crashes without a credible trigger, or style preferences that do not affect correctness or maintainability.

Unless the user explicitly requests a broader review, use this default severity boundary:

Ignore extreme edge cases and crashes, layout shifts, or state mismatches assessed as extremely unlikely. Do not inflate them into actionable findings.
Keep the actionable and automatic-fix set to P0 and P1 findings with a realistic trigger and material impact.
Prioritize real business-logic, security/data-integrity, and user-visible TUI defects. Do not automatically fix P2/P3 findings; mention a lower-severity item only when it materially affects a decision, and leave it deferred unless the user expands the scope.

3. Obtain an external Codex review

Run one direct, read-only codex exec --json review pass. The external prompt must forbid invoking this skill, running another codex process, calling delegation tools, or modifying files.

Requirements:

Require codex to be available on PATH; do not source a personal shell startup file.
Create a run directory with mktemp -d outside the repository.
Save JSONL, stderr, and the final response so partial output survives interruption.
Use the Codex CLI's configured default model. Only pass -m when REVIEW_MODEL is explicitly set by the caller.
Default the external timeout to 30 minutes (1800 seconds), overridable through REVIEW_TIMEOUT_SECONDS.
If the review times out, inspect partial artifacts, split the diff into smaller review units, and retry. Do not declare the external pass complete without a usable result.

Read the full file on GitHub · 91 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.

3d ago First seen · 91 lines · 41 tokens per session scan A b24c890c3e76

Subscribe to this mod's changes

code-review is a skill published in the GitHub repository FTShare-Lab/agent-claim-network (41 stars, last pushed 3d ago), licensed Apache-2.0. It adds 41 tokens to every session and 1,091 once invoked, about $0.0002 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.

Code review LLM ai-agents knowledge-sharing mcp multi-agent-systems

adk-style

Python style and codebase conventions for ADK (Agent Development Kit): private-by-default file visibility, imports, type hints, Pydantic v2 models, formatting, docstrings, logging, async I/O, file and test layout, and unit test structure. Use when writing or editing ADK source or tests, deciding whether a new file or…

google/adk-python · 187 tokens

adk-unit-design

Writes an as-built architecture document for one ADK code unit — purpose, execution flow, data flow, cross-class dependencies, extension points, and the parts that must not change — to docs/design/{topic}/{unit}/index.md. It describes the code as implemented, not a proposed design, and its reader is a developer about…

google/adk-python · 181 tokens

bigquery-ai-ml

Skill for BigQuery AI and Machine Learning queries using standard SQL and AI. functions (preferred over dedicated tools).

google/adk-python · 31 tokens

code-review-skill

Reviews code with feedback tailored to the developer's profile in session state.

google/adk-python · 19 tokens

adk-verify-snippets

Checks that every Python code block in a Markdown file actually compiles and runs, by extracting each block to a temporary file, executing it in an isolated subprocess, and writing a pass/fail report with per-snippet coverage. Use when the user asks to verify, test, or validate the code samples in a README, a guide…

google/adk-python · 149 tokens

adk-setup

Sets up a local ADK Python development environment in a git clone of the open-source adk-python repository: a uv virtual environment, all dependency extras, pre-commit hooks, and a first unit-test run. Runs only when explicitly requested, never on its own. Use when asked to set up, bootstrap, or repair a development…

google/adk-python · 146 tokens