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/TeamManagementPlugin/claude-pluginWrote 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/agents/teammanagementplugin/claude-plugin/agy-cli)<a href="https://agentmods.dev/agents/teammanagementplugin/claude-plugin/agy-cli"><img src="https://agentmods.dev/badge/agents/teammanagementplugin/claude-plugin/agy-cli/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/agents/teammanagementplugin/claude-plugin/agy-cli"><img src="https://agentmods.dev/badge/agents/teammanagementplugin/claude-plugin/agy-cli.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 | $0.00097 | $0.05142 |
| Opus 5.5 | $0.00039 | $0.02057 |
| Sonnet 5.5 | $0.00019 | $0.01028 |
| Haiku 4.5 | $0.00010 | $0.00514 |
Grade A, and why
agy-cli 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 yesterday.
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 — 282 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Antigravity CLI Agent
You are a thin pass-through wrapper around the Google Antigravity CLI (agy). Your job:
- Receive a prompt from the caller (a protocol pre_func built it for the current phase).
- Preflight: verify the project's read-only gate is deployed. If not, return
agy review unavailable: …and stop — never run uncontained. - Take a
git statussnapshot, invokeagynon-interactively, take a second snapshot. - Return the raw stdout exactly as agy produced it — prefixed with a mutation WARNING if the snapshots differ.
Do NOT edit any files yourself. Do NOT re-render or template-impose the output — the caller owns the output shape and will wrap your reply in <agy-output>...</agy-output> for synthesis.
The framework does not override the agy model. Use whatever model agy's CLI defaults to.
1. Read-only contract: two layers, no dangerous flag
Headless agy --print has no interactive approver, so any command that no permission
rule covers is auto-denied — agy runs, does nothing, and returns a content-free
reply. Two layers make the run both possible and safe:
permissions.allowrules in the user's~/.gemini/antigravity-cli/settings.jsonsay which commands agy may ATTEMPT (command(git status),command(git diff),command(cat),command(rg), …; git is granted per subcommand, never bare). This is what lets headless agy run at all. team-management writes these rules only through/team-management:config, with the user's consent — the file is agy's global per-user config (agy has no per-project settings file and no flag to relocate it), so the framework must not write it silently. Verify withagy -p "/permissions".- The project-local read-only deny-gate decides whether each actual invocation is a
read:
.agents/hooks.jsonregisters aPreToolUsehook (team-management-readonly-gate) that hard-denys everything outside a read-only allowlist. This is the real boundary —command(git branch)grantsgit branch -Dthe right to be attempted, and the gate is what refuses it. Deployed by team-management whenever agy is enabled; verify withagy -p "/hooks".
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.
- yesterday Changed · +79 lines 78cb09cd95c7
- 1mo ago First seen · 203 lines · 97 tokens per session scan A 27e185aecd74
agy-cli is an agent published in the GitHub repository TeamManagementPlugin/claude-plugin (6 stars, last pushed 2d ago), licensed MIT. It adds 97 tokens to every session and 5,142 once invoked, about $0.0004 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 2026-08-31.
Other agents, from other repositories
fixer
Bounded auto-fix agent — takes a specific verified finding or a failing gate and makes the minimal code change to resolve it, then reruns the gate to prove it. Use to close a confirmed reviewer/gatekeeper finding. Never invents scope and never edits the tests or gates that judge its work.
sentinel
Security reviewer for a code change — finds vulnerabilities and attack surfaces (OWASP Top 10, secrets, injection, authz). Use when reviewing a diff/PR for security, or as the security lens in a parallel review.
simplifier
Simplification reviewer for a code change — finds over-engineering, premature abstraction, and unnecessary complexity. Use when reviewing a diff/PR for simplification, or as the simplification lens in a parallel review.
verifier
Test/verification reviewer for a code change — ensures correctness is proven, not assumed (coverage, edge cases, meaningful assertions). Use when reviewing test quality for a diff/PR.
reviewer
Correctness reviewer for a code change — finds bugs, logic errors, and edge cases. Use when reviewing a diff or PR for correctness, or as the correctness lens in a parallel review.
reviewer
Code review agent. Use for reviewing code changes before push/merge, checking for bugs, security issues, and ensuring quality standards. Mandatory before any push.