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 eins78/agent-skills --skill ai-reviewgit clone --depth 1 https://github.com/eins78/agent-skillsWrote 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/eins78/agent-skills/ai-review)<a href="https://agentmods.dev/skills/eins78/agent-skills/ai-review"><img src="https://agentmods.dev/badge/skills/eins78/agent-skills/ai-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/eins78/agent-skills/ai-review"><img src="https://agentmods.dev/badge/skills/eins78/agent-skills/ai-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 | $0.00069 | $0.01958 |
| Opus 5 | $0.00034 | $0.00979 |
| Sonnet 5 | $0.00014 | $0.00392 |
| Haiku 4.5 | $0.00007 | $0.00196 |
Grade B, and why
ai-review scanned grade B with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 12d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
# Set auth type in gemini settings (~/.gemini/settings.json) How it starts
The opening of the file, as written. The whole thing — 186 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AI Code Review
Request code reviews from a second AI model mid-session via CLI.
Prerequisites
geminiCLI installed (run${CLAUDE_SKILL_DIR}/scripts/install-dependencies.sh)- Auth: either
GEMINI_API_KEYenv var (recommended — see "Paid API" below) or Google Account OAuth (geminiinteractively once) - Optional:
codexCLI for OpenAI reviews:brew install codex
CRITICAL: Never Skip Reviews
Quality over speed. When a review is requested, you MUST wait for the result. Do NOT:
- Skip the review because of rate limits or timeouts
- Proceed without the review and say "we can review later"
- Substitute your own review instead of calling the external model
The gemini CLI handles rate limit retries automatically. If the script exits with a timeout (exit code 2), ask your human partner for help — do not silently continue.
Rate Limits (Free Tier — Google Account Auth)
| Metric | Limit |
|---|---|
| Requests per minute | 60 RPM |
| Requests per day | 1,000 RPD |
| Capacity (tokens/time) | Very low — the real bottleneck |
| Model | Auto-selected by Google (upgrades over time) |
| Cost | $0 |
Important: The RPM/RPD limits are rarely the issue. Google also enforces a capacity quota (total tokens processed per rolling time window) that is much more restrictive. Large review payloads (code + auto-context) can exhaust this quota in just a few requests, triggering a TerminalQuotaError with a multi-hour reset (typically 1-3 hours). This is especially tight on newer auto-selected models (e.g., Gemini 2.5 Pro).
To reduce quota pressure:
- Use
--no-contextfor small/focused reviews to cut token usage - Split large reviews into smaller chunks
- Use a paid API key to avoid capacity limits entirely (see below)
The CLI retries automatically on per-minute rate limit hits (resets in seconds). The capacity quota does NOT retry — it requires waiting for the reset window. The script has a 1-hour timeout — if exceeded, it aborts and you should ask the user for help.
What ships with it
3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 12d ago First seen · 186 lines · 69 tokens per session scan B 448617e402dd
ai-review is a skill published in the GitHub repository eins78/agent-skills (2 stars, last pushed yesterday), licensed MIT. It adds 69 tokens to every session and 1,958 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
refactoring-patterns
Apply named refactoring transformations to improve code structure without changing behavior. Use when the user mentions "refactor this", "code smells", "extract method", "replace conditional", "technical debt", "move method", "inline variable", "decompose conditional", or "clean up this messy code". Also trigger when…
solid-principles
SOLID principles checklist with Java examples. Use when a class has too many responsibilities, an abstraction leaks, or a dependency points the wrong way, and when the user asks about Single Responsibility, Open/Closed, Liskov, Interface Segregation or Dependency Inversion. For naming, duplication and method length…
architecture-review
Analyze Java project architecture at macro level - package structure, module boundaries, dependency direction, and layering. Use when user asks "review architecture", "check structure", "package organization", or when evaluating if a codebase follows clean architecture principles.
java-code-review
Systematic code review for Java with null safety, exception handling, concurrency, and performance checks. Use when user says "review code", "check this PR", "code review", or before merging changes.
boundaries
Analyze Phoenix context boundaries and module coupling via mix xref. Use when checking cross-context calls, validating dependencies, before splitting modules, or reviewing architecture.
triage
Triage review findings interactively — approve, skip, or prioritize each issue. Use after /phx:review to filter findings before fixing.