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.
git clone --depth 1 https://github.com/ilyasibrahim/claude-agents-coordinationWrote 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.
[](https://agentmods.dev/commands/ilyasibrahim/claude-agents-coordination/review-full)<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.
<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>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 5.1 | $0.00015 | $0.02230 |
| Opus 5 | $0.00008 | $0.01115 |
| Sonnet 5 | $0.00003 | $0.00446 |
| Haiku 4.5 | $0.00002 | $0.00223 |
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.
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
")
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.
- 9d ago First seen · 324 lines · 15 tokens per session scan A e8c954995abd
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 $0.0001 per session on Opus 5. A static security scan graded it A with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other commands, from other repositories
sdd-init
Initialize SDD context — detects project stack and bootstraps persistence backend.
review-branch
Review the current branch's diff against base by dispatching atomic-reviewer. No orchestration loop, no spec required — pre-flight before /commit pr or /commit merge.
init
Install the formatters this repository needs, with every command visible before it runs.
merge-conflict-analysis
You are analyzing merge conflicts for PR #${{ pr-number }}.
repo-audit
Audit a codebase (local or remote GitHub/GitLab) against architecture principles and requirements, surfacing drift, risk, and missing decisions.
argos
A command for checking whether an implementation matches its design deliverables. Its Korean description compares the work to the design as part of a completion inspection.