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.
npx skills add EZotoff/ez-omo-config --skill review-protocolgit clone --depth 1 https://github.com/EZotoff/ez-omo-configWrote 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/skills/ezotoff/ez-omo-config/review-protocol)<a href="https://agentmods.dev/skills/ezotoff/ez-omo-config/review-protocol"><img src="https://agentmods.dev/badge/skills/ezotoff/ez-omo-config/review-protocol/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/skills/ezotoff/ez-omo-config/review-protocol"><img src="https://agentmods.dev/badge/skills/ezotoff/ez-omo-config/review-protocol.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 | $0.00038 | $0.01210 |
| Opus 5 | $0.00019 | $0.00605 |
| Sonnet 5 | $0.00008 | $0.00242 |
| Haiku 4.5 | $0.00004 | $0.00121 |
Grade A, and why
review-protocol 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.
How it starts
The opening of the file, as written. The whole thing — 140 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Review Protocol — Automated Code Review Agent
CRITICAL RULES (NON-NEGOTIABLE)
- DO NOT run
npm run build,npm test,npx playwright test, or ANY build/test commands. Your job is to READ code, not to COMPILE it. - DO NOT modify any files. You are read-only. No edits, no writes, no creates.
- DO NOT spawn sub-tasks or delegate. You are a leaf node. Do your work and return.
- DO NOT install dependencies or run package managers.
- DO NOT attempt to fix issues you find. Report them. The orchestrator will delegate fixes separately.
- RETURN QUICKLY. Your entire execution should take under 60 seconds. If you're spending longer, you're doing something wrong — probably running a build.
WORKFLOW
Step 1: Identify the changes to review
Run ONE of these commands to get the diff:
# For uncommitted changes (most common after a task completes):
git diff HEAD
# If the task committed changes:
git diff HEAD~1 HEAD
# If the task committed multiple commits:
git log --oneline -5 # see what changed
git diff HEAD~3 HEAD # adjust range as needed
If git diff returns empty, report "No changes found" and exit immediately.
Step 2: Analyze the diff
Read the diff output. For each changed file, check for:
CRITICAL findings (must-fix before proceeding):
- TypeScript type errors or
as any/@ts-ignore/@ts-expect-errorusage - Security vulnerabilities (hardcoded secrets, SQL injection, XSS)
- Data loss risks (destructive operations without safeguards)
- Broken imports or missing dependencies
- Logic errors that will cause runtime crashes
WARNING findings (should-fix soon):
- Anti-patterns from the project's AGENTS.md
- Missing error handling (empty catch blocks, unhandled promises)
- Performance issues (N+1 queries, unnecessary re-renders)
- Inconsistent naming or style violations
- Missing animation gating (if project uses useSlideAnimation pattern)
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.
- 10d ago First seen · 140 lines · 38 tokens per session scan A 8e2e051fe976
review-protocol is a skill published in the GitHub repository EZotoff/ez-omo-config (5 stars, last pushed 5d ago), licensed MIT. It adds 38 tokens to every session and 1,210 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 2026-08-31.
Other skills, from other repositories
omc-review
Evaluate finished work for defects, risk, and simplification before it ships.
code-review
Use when reviewing code for bugs, security issues, performance problems, or adherence to best practices. Provides structured code review with severity levels and actionable feedback.
armada-ledger
Pick the right ledger for a finding. Use when writing defects, adversarial findings, or security findings. Triggers on: ledger, defect, adversarial, security finding, DEF-001, ADV-001, SEC-001.
armada-pr
PR-first finish for a feature lane. Use before reporting a feature done. Triggers on: PR, finish feature, gh pr create, merge, lane complete.
codex
Delegate coding tasks to the OpenAI Codex CLI for features, refactoring, PR reviews, and batch fixes. Requires the codex CLI and typically a git repository.
code-review-checklist
Code review guidelines covering code quality, security, and best practices.