OpenGAP is a framework-independent standard for defining AI agents as Git repositories, using files such as an agent manifest and identity document. It is intended for portable, version-controlled agents that can be adapted to systems such as Claude Code, OpenAI, LangChain, CrewAI, and AutoGen. The catalogue skills represent workflows and extensions built around this agent format.
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 open-gitagent/opengap --skill code-reviewgit clone --depth 1 https://github.com/open-gitagent/opengapWrote 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/open-gitagent/opengap/code-review)<a href="https://agentmods.dev/skills/open-gitagent/opengap/code-review"><img src="https://agentmods.dev/badge/skills/open-gitagent/opengap/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/open-gitagent/opengap/code-review"><img src="https://agentmods.dev/badge/skills/open-gitagent/opengap/code-review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00053 | $0.00342 |
| Opus 5.5 | $0.00021 | $0.00137 |
| Sonnet 5.5 | $0.00011 | $0.00068 |
| Haiku 4.5 | $0.00005 | $0.00034 |
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.
What it actually says
Code Review
Instructions
When reviewing code:
- Read the full diff or file provided
- Check for security vulnerabilities (OWASP Top 10)
- Evaluate error handling completeness
- Assess code complexity and readability
- Verify naming conventions and code style
- Look for performance issues
- Check for proper input validation
Output Format
## Review Summary
[1-2 sentence overview]
## Findings
### CRITICAL
- [Finding with line reference and fix]
### WARNING
- [Finding with line reference and fix]
### SUGGESTION
- [Finding with line reference and fix]
## What's Done Well
- [Positive observations]
Example Finding
### CRITICAL
- **Line 42**: SQL injection vulnerability — user input concatenated directly into query string.
Fix: Use parameterized queries instead of string concatenation.
```python
# Before (vulnerable)
cursor.execute(f"SELECT * FROM users WHERE id = {user_id}")
# After (safe)
cursor.execute("SELECT * FROM users WHERE id = %s", (user_id,))
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 · 57 lines · 53 tokens per session scan A f599cb8c5296
code-review is a skill published in the GitHub repository open-gitagent/opengap (2,979 stars, last pushed 3mo ago), licensed MIT. It adds 53 tokens to every session and 342 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
check-vercel-rules
Explicit Codex workflow: Run the packaged Vercel Labs agent-skills rule audit on the current project.
requesting-code-review
Pre-commit review: security scan, quality gates, auto-fix.
simplify-code
Parallel 3-agent cleanup of recent code changes.
opencode
Delegate coding to OpenCode CLI (features, PR review).
caveman-review
Ultra-compressed code review comments. Cuts noise from PR feedback while preserving the actionable signal. Each comment is one line: location, problem, fix. Use when user says "review this PR", "code review", "review the diff", "/review", or invokes /caveman-review. Auto-triggers when reviewing pull requests.
github-code-review
Review PRs: diffs, inline comments via gh or REST.