review-full

review-full is a command for Claude Code from ilyasibrahim/claude-agents-coordination. It costs 15 tokens per session (2,230 once invoked), scanned A, original, Unlicense.

A broad code-review command that checks code from several perspectives, including peer quality, architecture, security, and reliability. It can apply all review levels or selected checks.

In plain words
What is it for?
Use it to review a directory or other target, run a quick peer review, focus on security, or perform the full review process.
Why use it?
It helps catch different kinds of problems that a single reviewer may miss, from logic errors and missing tests to security and operational risks.

Command for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: reads .claude/ paths; positional $N argument; mentions Claude Code.

Good fit Use it to review a directory or other target, run a quick peer review, focus on security, or perform the full review process.

Compare 6 commands from other repositories ↓
Install with agentmods
npx agentmods add commands/ilyasibrahim/claude-agents-coordination/review-full
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.

Clone the repo
git clone --depth 1 https://github.com/ilyasibrahim/claude-agents-coordination

Made for: Claude Code.

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 review-full

README.md
[![agentmods](https://agentmods.dev/badge/commands/ilyasibrahim/claude-agents-coordination/review-full/github.svg)](https://agentmods.dev/commands/ilyasibrahim/claude-agents-coordination/review-full)
Your own site
<a href="https://agentmods.dev/commands/ilyasibrahim/claude-agents-coordination/review-full"><img src="https://agentmods.dev/badge/commands/ilyasibrahim/claude-agents-coordination/review-full/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 review-full

Your own site · 80×15
<a href="https://agentmods.dev/commands/ilyasibrahim/claude-agents-coordination/review-full"><img src="https://agentmods.dev/badge/commands/ilyasibrahim/claude-agents-coordination/review-full.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 15 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,230 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. 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 $0.00015 $0.02230
Opus 5 $0.00008 $0.01115
Sonnet 5 $0.00003 $0.00446
Haiku 4.5 $0.00002 $0.00223

Measured 9d ago against content hash e8c954995abd, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

review-full 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 9d 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.

Reads agent configuration directorieslowAgent snooping

.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.

!cat .claude/reports/_registry.md 2>/dev/null | grep -i "review\|security\|arch\|sre" | head -10 || echo "No prior reviews found"

Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.

claude-user/commands/review-full.md · 324 lines

How it starts

The opening of the file, as written. The whole thing — 324 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Full Review Protocol

Multi-level code review following enterprise engineering standards.

Before proceeding: Read the agent-coordination skill at .claude/skills/agent-coordination/SKILL.md for registry management, verification scripts, and coordination protocols.

Review Target

Path to review: $1
Options: $ARGUMENTS

Quick Reference

  • /review-full src/ — Full 4-level review
  • /review-full src/ --quick — L1 only (peer review)
  • /review-full src/ --security — L1 + L3 (peer + security)
  • /review-full src/ --all — Force all 4 levels

Pre-Review Analysis

Before starting, analyze the target to determine which review levels apply:

<prior_work> !cat .claude/reports/_registry.md 2>/dev/null | grep -i "review|security|arch|sre" | head -10 || echo "No prior reviews found" </prior_work>


Review Levels

Level 1: Peer Review (Always Required)

Invoke the code-quality agent with mode=review:

Task(code-quality, "
Mode: review
Target: $1

Focus areas:
- Code correctness and logic errors
- Style consistency with project conventions
- Test coverage gaps
- Error handling completeness
- Documentation quality

Severity classification:
- BLOCKING: Must fix before merge
- NON-BLOCKING: Should fix, can defer
- NIT: Nice to have improvements

Output: .claude/reports/review/L1-peer-YYYYMMDD.md
")

After completion: Update _registry.md with L1 report entry.


Level 2: Architecture Review

Trigger when ANY of these apply:

  • Change exceeds 200 lines
  • New API endpoints added
  • Database schema modifications
  • New services or modules introduced
  • Cross-cutting concerns affected

Invoke the architect agent with mode=system:

Task(architect, "
Mode: system
Target: $1

Context from L1: [Include key findings from peer review]

Assessment criteria:
- Alignment with existing architecture
- Pattern consistency across codebase
- Dependency appropriateness and direction
- API design quality and versioning
- Scalability implications

Output: .claude/reports/review/L2-arch-YYYYMMDD.md
")

Read the full file on GitHub · 324 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. 9d ago First seen · 324 lines · 15 tokens per session scan A e8c954995abd

Subscribe to this mod's changes

review-full is a command published in the GitHub repository ilyasibrahim/claude-agents-coordination (83 stars, last pushed 3mo ago), licensed Unlicense. It adds 15 tokens to every session and 2,230 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.