subagent-review

subagent-review is a skill for Claude Code, Codex from nmamano/isomux. It costs 39 tokens per session (213 once invoked), scanned A, original, MIT.

A review tool that asks another agent to inspect your uncommitted code changes before you commit them.

In plain words
What is it for?
Use it to review staged and unstaged changes, receive blockers and suggestions, then decide which feedback to apply before committing.
Why use it?
It can reveal bugs, questionable shortcuts, and smaller improvements while there is still time to change the code.

Skill for Claude CodeCodex

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/nmamano/isomux/subagent-review
Any agent
npx skills add nmamano/isomux --skill subagent-review
Clone the repo
git clone --depth 1 https://github.com/nmamano/isomux

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.

agentmods badge for subagent-review

README.md
[![agentmods](https://agentmods.dev/badge/skills/nmamano/isomux/subagent-review.svg)](https://agentmods.dev/skills/nmamano/isomux/subagent-review)
Your own site
<a href="https://agentmods.dev/skills/nmamano/isomux/subagent-review"><img src="https://agentmods.dev/badge/skills/nmamano/isomux/subagent-review.svg" alt="Measured on agentmods" height="20"></a>
Per session 39 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 213 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 $0.00039 $0.00213
Opus 5 $0.00019 $0.00106
Sonnet 5 $0.00008 $0.00043
Haiku 4.5 $0.00004 $0.00021

Measured 5d ago against content hash afe38dee3c4e, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

subagent-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 5d 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/subagent-review/SKILL.md · 9 lines

What it actually says

Spawn a subagent (smartest model available) to review the diff of uncommitted changes (both staged and unstaged). Explain to the subagent only the goal of the changes, not the rationale for the approach chosen. Ask the subagent to look for bugs and analyze if the changes are principled or hacky. It must either approve the changes for commit or surface a list of blockers, plus any smaller nits it noticed along the way. Let the user see the feedback before committing.

Then fix what came back - nits as well as blockers. Judge each point on whether acting on it makes the change better, not on whether it stands between you and the commit: the goal is quality, not reaching the finish line. If you think a point is wrong, say so and explain why rather than skipping it silently.

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. 5d ago First seen · 9 lines · 39 tokens per session scan A afe38dee3c4e

Subscribe to this mod's changes

subagent-review is a skill published in the GitHub repository nmamano/isomux (37 stars, last pushed yesterday), licensed MIT. It adds 39 tokens to every session and 213 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.

Related

Other skills, from other repositories

foundry-hosted-agent-validation

Step-by-step process for validating a Python Foundry hosted agent sample (under python/samples/04-hosting/foundry-hosted-agents/) end to end — running it locally (native runtime and azd ai agent run) and after deploying it to an Azure AI Foundry project with azd. Use this when asked to validate a hosted agent sample.

microsoft/agent-framework · 82 tokens

build-and-test

How to build and test .NET projects in the Agent Framework repository. Use this when verifying or testing changes.

microsoft/agent-framework · 26 tokens

python-feature-lifecycle

Guidance for package and feature lifecycle in the Agent Framework Python codebase, including stage meanings, feature-stage decorators, feature enums, and how to move APIs from one stage to the next.

microsoft/agent-framework · 43 tokens

python-development

Coding standards, conventions, and patterns for developing Python code in the Agent Framework repository. Use this when writing or modifying Python source files in the python/ directory.

microsoft/agent-framework · 35 tokens

foundry-config-setup

Resolve missing setup caused by a hardcoded Foundry project endpoint or model in a sample. Use when a sample fails because it uses a placeholder/hardcoded projectendpoint (for example "https://your-project.services.ai.azure.com") or a hardcoded model instead of reading them from the environment.

microsoft/agent-framework · 65 tokens

verification-planning

Verification planning for non-trivial coding work. Use before implementing a feature, bug fix, refactor, cross-system change, or high-confidence behavior change that needs a credible project-specific evidence path.

alvinunreal/oh-my-opencode-slim · 43 tokens