devteam-review

A coordinated code-review command that sends changes to multiple specialized reviewers. Code review is the process of checking code for bugs, security problems, performance issues, and design concerns.

In plain words
What is it for?
Use it to review current changes, specific files, a directory, or a pull request, with focus on security, performance, architecture, correctness, or all areas.
Why use it?
It brings several review perspectives together and lets you limit the review to selected files, areas, pull requests, or severity levels.

Command

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 commands/michael-harris/devteam/devteam-review
Clone the repo
git clone --depth 1 https://github.com/michael-harris/devteam
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 578 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 $0.00000 $0.00578
Opus 5 $0.00000 $0.00289
Sonnet 5 $0.00000 $0.00116
Haiku 4.5 $0.00000 $0.00058

Measured 2d ago against content hash 409cb011f344, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

devteam-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 2d 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.

commands/devteam-review.md · 92 lines

How it starts

The opening of the file, as written. The whole thing — 92 lines — stays where its author put it; the contents beside it link to each section on GitHub.

DevTeam Review Command

Command: /devteam:review [target] [options]

Run a coordinated code review across multiple reviewers. Launches the Code Review Coordinator to orchestrate language-specific and domain-specific reviewers.

Usage

# Review current changes (staged + unstaged)
/devteam:review

# Review specific files
/devteam:review "src/api/auth.ts" "src/models/user.ts"

# Review specific scope
/devteam:review --scope "src/api/"

# Review with specific focus
/devteam:review --focus security
/devteam:review --focus performance
/devteam:review --focus architecture

# Review a PR
/devteam:review --pr 42

Options

Option Description
--scope <path> Limit review to specific files/directories
--focus <area> Focus on: security, performance, architecture, correctness, all
--pr <number> Review a specific pull request
--severity <level> Minimum severity to report: critical, warning, info
--eco Cost-optimized execution

Your Process

Phase 0: Initialize Session

source scripts/state.sh
source scripts/events.sh

SESSION_ID=$(start_session "/devteam:review $*" "review")
log_session_started "/devteam:review $*" "review"

Phase 1: Launch Code Review Coordinator

Delegate to the orchestration:code-review-coordinator agent, which will:

  1. Detect languages and frameworks in the target files
  2. Select appropriate language-specific code reviewers
  3. Run database reviewers if schema changes are detected
  4. Aggregate findings across all reviewers
  5. Produce a unified review report with severity ratings
const result = await Task({
    subagent_type: "orchestration:code-review-coordinator",
    prompt: `Code review request:

        Target: ${target || 'current changes'}
        Scope: ${scope || 'auto-detect'}
        Focus: ${focus || 'all'}

        Coordinate reviewers to check:
        1. Code correctness and logic errors
        2. Security vulnerabilities
        3. Performance issues
        4. Code style and best practices
        5. Test coverage gaps
        6. Documentation needs`
})

Read the full file on GitHub · 92 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.

  1. 2d ago First seen · 92 lines · 0 tokens per session scan A 409cb011f344

Subscribe to this mod's changes

devteam-review is a command published in the GitHub repository michael-harris/devteam (18 stars, last pushed 6mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 578 tokens. 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.