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/arcobaleno64/agy-plugin-ccWrote 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/plugins/arcobaleno64/agy-plugin-cc/gemini)<a href="https://agentmods.dev/plugins/arcobaleno64/agy-plugin-cc/gemini"><img src="https://agentmods.dev/badge/plugins/arcobaleno64/agy-plugin-cc/gemini/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/plugins/arcobaleno64/agy-plugin-cc/gemini"><img src="https://agentmods.dev/badge/plugins/arcobaleno64/agy-plugin-cc/gemini.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
gemini 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
{
"name": "gemini",
"version": "0.25.0",
"description": "agy-plugin-cc is a Claude Code companion for running Gemini CLI or Antigravity CLI (agy) as a cross-model task delegate and code reviewer, with pragmatic and adversarial review, MCP tools, and background jobs.",
"author": {
"name": "arcobaleno64",
"email": "[email protected]",
"url": "https://github.com/arcobaleno64"
},
"homepage": "https://github.com/arcobaleno64/agy-plugin-cc",
"repository": "https://github.com/arcobaleno64/agy-plugin-cc",
"license": "MIT"
}
What it installs
The manifest is a name and a version. 3 skills, 8 commands, 1 agent, 3 hooks, 1 MCP server travel with it, and installing the plugin installs all of them — 241 tokens a session between them. Each is measured on its own page, and each can be installed alone.
- Skill gemini-cli-runtime A 19 tokens
- Skill gemini-prompting A 31 tokens
- Skill gemini-result-handling A 17 tokens
- Command adversarial-review A 15 tokens
- Command review A 10 tokens
- Command transfer A 22 tokens
- Command result A 13 tokens
- Command cancel A 9 tokens
- Command status A 15 tokens
- Command setup C 17 tokens
- Command rescue A 19 tokens
- Agent gemini-rescue A 54 tokens
- Hook Stop A not measured
- Hook SessionStart A not measured
- Hook SessionEnd A not measured
- MCP server gemini A not measured
What ships with it
1 file beside plugin.json 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.
- 1mo ago Changed f066737f6df8
- 1mo ago Changed 37a0bf171d6f
- 1mo ago First seen · 14 lines scan A 52f7c10ad039
gemini is a plugin published in the GitHub repository arcobaleno64/agy-plugin-cc (14 stars, last pushed 2d ago), licensed MIT. Its token cost is not measured: this kind of file is read by the harness, not the model. 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 plugins, from other repositories
review-all
Comprehensive, project-agnostic, multi-agent code review for Claude Code with verification to eliminate false positives.
logic-lens
Logic-first code review using semi-formal execution tracing. Surfaces behavioral bugs, type contract breaches, boundary blindspots, and interprocedural semantic mismatches — the logic errors that cause production incidents in syntax-clean code.
logic-lens
Logic-first code review using semi-formal execution tracing. Surfaces behavioral bugs, semantic errors, and runtime failures that linters miss.
river-review
Turn review into an organizational judgment asset. Review Judgment as Code for AI-assisted development, delivered as a capability pack for Claude Code: your team's review criteria as versioned, repo-owned skills (a Skill Registry), driven by a review agent that runs perspective-based reviewer roles (code, security…
harness-engineering-skills
Two Claude Code engineering skills bundled as one plugin: review-loop (cross-LLM iterative code review with Codex or Gemini as peer) and harness (cybernetics-based Planner→Generator→Evaluator→Retro orchestration for complex tasks).
review-gate
Native Claude Code AI code review + blocking pre-push gate on your Claude subscription. Isolated headless reviewer, severity/confidence verdicts, fails closed. open-code-review, done compliantly.