agentmods.dev

team-review

team-review is a skill for Claude Code, Codex from OXI-717/ai-native-toolkit. It costs 80 tokens per session (1,774 once invoked), scanned A, original, MIT.

A structured code-review workflow that can use several focused review passes and repeat the review after fixes. It covers finding issues, deciding which findings matter, optionally applying fixes, and running builds and tests.

In plain words
What is it for?
Reviewing staged, unstaged, all, or unpushed changes; checking selected aspects; fixing findings; running tests; and reporting risks that remain.
Why use it?
It gives a repeatable way to inspect code from different angles and verify that changes still work after problems are fixed. It also separates ordinary reviews from explicitly requested multi-agent reviews.

Skill for Claude CodeCodex

Written for Claude Code and Codex: ${CLAUDE_PLUGIN_ROOT} variable, but also agents/openai.yaml present. Also seen: mentions CLAUDE.md; mentions subagents; names the AskUserQuestion tool.

Runs only inside its plugin — its command needs a path that Claude Code sets for a plugin’s own hooks and for nothing else. Install the plugin, not this.

Part of the team-review plugin — 1 skill, 1 command shipped together

not rated 8repo +1 17d ago A scan 80 tokens original MIT

Good fit Reviewing staged, unstaged, all, or unpushed changes; checking selected aspects; fixing findings; running tests; and reporting risks that remain.

Compare 6 skills from other repositories ↓
View source ↗ OXI-717/ai-native-toolkit
Install

Getting it into your agent

This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.

Claude Code
/plugin marketplace add OXI-717/ai-native-toolkit
Claude Code
/plugin install team-review

Made for: Claude Code, Codex.

Or install team-review, the plugin that ships this one along with the rest of its 1 skill, 1 command.

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 team-review

README.md
[![agentmods](https://agentmods.dev/badge/skills/oxi-717/ai-native-toolkit/team-review/github.svg)](https://agentmods.dev/skills/oxi-717/ai-native-toolkit/team-review)
Your own site
<a href="https://agentmods.dev/skills/oxi-717/ai-native-toolkit/team-review"><img src="https://agentmods.dev/badge/skills/oxi-717/ai-native-toolkit/team-review/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for team-review

Your own site · 80×15
<a href="https://agentmods.dev/skills/oxi-717/ai-native-toolkit/team-review"><img src="https://agentmods.dev/badge/skills/oxi-717/ai-native-toolkit/team-review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 80 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,774 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00080 $0.01774
Opus 5 $0.00040 $0.00887
Sonnet 5 $0.00016 $0.00355
Haiku 4.5 $0.00008 $0.00177

Measured 10d ago against content hash c23447f84b0e, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

team-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 10d 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/team-review/skills/team-review/SKILL.md · 202 lines

How it starts

The opening of the file, as written. The whole thing — 202 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Review

Run a rigorous code review with optional fix loop:

  1. Detect scope.
  2. Review through specialized roles.
  3. Score and filter findings.
  4. Optionally fix.
  5. Build/test.
  6. Re-review fixed changes.
  7. Report remaining risks.

Runtime Selection

Claude Code: if the slash command /team-review is available, it remains the canonical implementation — follow ${CLAUDE_PLUGIN_ROOT}/commands/team-review.md. If the command file is not found, fall back to this SKILL.md.

Codex or portable skill mode: follow this SKILL.md. If the user explicitly asked for team-review, /team-review, "multi-agent review", "team review", "серия субагентов", or equivalent delegation, use Codex subagents for independent review roles when available. For a plain "review this" request, do not delegate; run the roles as local passes in this session.

Do not use Claude-only TeamCreate/TaskCreate/AskUserQuestion APIs in Codex.

Arguments

Accept the same user-facing shape as /team-review:

review [scope] [aspects] [--ask] [--no-fix]

Scopes:

  • staged: git diff --cached
  • unstaged: git diff
  • all: git diff HEAD
  • unpushed: git diff @{u}..HEAD
  • last or HEAD: git diff HEAD~1..HEAD
  • pr or pr N: gh pr diff [N]
  • full or project: whole-codebase review
  • paths: review only those files/directories

Auto-detect scope when omitted:

  1. unstaged changes
  2. staged changes
  3. unpushed commits
  4. last commit
  5. current PR
  6. otherwise stop with "No changes to review."

Aspects:

  • code: conventions, maintainability, local instructions
  • bugs: logic bugs, regressions, security-adjacent defects
  • tests: missing behavioral coverage
  • errors: swallowed errors, weak error handling, silent failure
  • simplify: needless complexity and duplication
  • adversarial: design challenges, hidden assumptions, tradeoffs
  • all: all except adversarial

Review Workflow

First gather:

  • relevant diff or file list
  • changed file paths
  • latest commit context
  • root and nested AGENTS.md / CLAUDE.md instructions when present
  • test/build hints from package manager files, Makefile, pyproject.toml, go.mod, Cargo.toml, etc.

Read the full file on GitHub · 202 lines

Files

What ships with it

1 file 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. 10d ago First seen · 202 lines · 80 tokens per session scan A c23447f84b0e

Subscribe to this mod's changes

team-review is a skill published in the GitHub repository OXI-717/ai-native-toolkit (8 stars, last pushed 17d ago), licensed MIT. It adds 80 tokens to every session and 1,774 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.

Claude CodeCode reviewagent-skillsai-agentscodexdeveloper-tools
Related

Other skills, from other repositories

rework-rate

Measure and interpret PR rework rate — the emerging 5th DORA metric.

bradygaster/squad · 20 tokens

go-testing

Trigger: Go tests, go test coverage, Bubbletea teatest, golden files. Apply focused Go testing patterns.

Gentleman-Programming/gentle-ai · 26 tokens

security-review

Perform a focused security review of pending git changes to identify high-confidence security vulnerabilities with real exploitation potential. Use this skill when the user asks for a security review, security audit, vulnerability scan, or wants to check pending changes on a branch for security issues before merging.…

waybarrios/opencode-power-pack · 64 tokens

huggingface-llm-trainer

Train or fine-tune language models with TRL or Unsloth on Hugging Face Jobs, including SFT, DPO, GRPO, reward models, and GGUF conversion. Use for cloud LLM training; use huggingface-vision-trainer for vision tasks.

waybarrios/opencode-power-pack · 65 tokens

feature-dev

Guide a feature implementation through a structured seven-phase workflow with deep codebase understanding, clarifying questions, parallel architecture design, and quality review. Use this skill when the user asks to build a new feature, add functionality, or wants a methodical approach to implementation rather than…

waybarrios/opencode-power-pack · 62 tokens

review

Validate plans, execution, or PRs against wish criteria — returns SHIP / FIX-FIRST / BLOCKED with severity-tagged gaps.

automagik-dev/genie · 29 tokens