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 richardcb/oh-my-gemini --skill code-reviewgit clone --depth 1 https://github.com/richardcb/oh-my-geminiWrote 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/richardcb/oh-my-gemini/code-review)<a href="https://agentmods.dev/skills/richardcb/oh-my-gemini/code-review"><img src="https://agentmods.dev/badge/skills/richardcb/oh-my-gemini/code-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.
<a href="https://agentmods.dev/skills/richardcb/oh-my-gemini/code-review"><img src="https://agentmods.dev/badge/skills/richardcb/oh-my-gemini/code-review.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 | $0.00047 | $0.01784 |
| Opus 5.5 | $0.00019 | $0.00714 |
| Sonnet 5.5 | $0.00009 | $0.00357 |
| Haiku 4.5 | $0.00005 | $0.00178 |
Grade A, and why
code-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 1mo 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 — 271 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Code Review Skill
Goal
Perform a thorough code review of newly implemented features, comparing against the technical plan, checking for AI-specific risks, and providing actionable feedback.
Hook Integration
The after-tool hook now handles automatic verification (typecheck, lint) after every code change. This skill focuses on higher-level review:
- Architecture alignment
- AI-specific risk patterns
- Business logic correctness
- Code quality beyond what linters catch
Process
1. Load Context
# Find the technical plan
find . -name "tasks_*.md" -o -name "plan.md" 2>/dev/null | head -3
# Find the PRD
find . -name "*prd*.md" 2>/dev/null | head -3
# Get list of changed files
git diff --name-only HEAD~10 2>/dev/null | head -30
# Get diff statistics
git diff --stat HEAD~10 2>/dev/null | tail -10
2. Analyze Code vs Plan
For each file changed:
- Was it in the plan?
- Does it match the planned approach?
- Are there deviations?
3. Perform Deep Review
Check each area systematically.
Review Areas
1. Plan Implementation Assessment
Questions:
- Was the technical plan implemented correctly and completely?
- Were there deviations? If so, were they justified?
- Are all tasks marked complete actually complete?
2. Code Quality & Best Practices
Note: Basic linting is handled by the after-tool hook. Focus on:
- Readability: Is the code clean and understandable?
- Naming: Are names meaningful and consistent?
- Complexity: Is complexity appropriate for the problem?
- Patterns: Does code follow existing codebase patterns?
3. AI-Specific Risk Assessment
CRITICAL: AI-generated code has specific risk patterns.
Logic & Correctness
- Deep-dive into algorithms
- Check business logic against PRD invariants
- Verify edge cases are handled
# Look for common AI mistakes
grep -rn "TODO\|FIXME\|XXX" src/ | head -20
grep -rn "any" --include="*.ts" src/ | head -20
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.
- 1mo ago First seen · 271 lines · 47 tokens per session scan A 23ce7c781245
code-review is a skill published in the GitHub repository richardcb/oh-my-gemini (18 stars, last pushed 7mo ago), licensed MIT. It adds 47 tokens to every session and 1,784 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-08-30.
Other skills, from other repositories
execute
Execute an approved Maestro implementation plan using the shared session-state contract.
orchestrate
Run the full Maestro workflow for complex engineering tasks that need a mandatory design dialogue, approved implementation plan, and then execution with shared session state.
resume-session
Resume an interrupted Maestro session using the existing active-session file and shared phase tracking.
a11y-audit
Run a Maestro-style accessibility audit for WCAG compliance, ARIA usage, keyboard navigation, and screen reader compatibility.
compliance-check
Run a Maestro-style regulatory compliance review for GDPR/CCPA, cookie consent, data handling, and licensing.
debug-workflow
Run the Maestro debugging workflow for investigation-heavy tasks.