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 ustc-fyk/antigravity-codex-mcp --skill agy-project-assistantgit clone --depth 1 https://github.com/ustc-fyk/antigravity-codex-mcpWrote 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/ustc-fyk/antigravity-codex-mcp/agy-project-assistant)<a href="https://agentmods.dev/skills/ustc-fyk/antigravity-codex-mcp/agy-project-assistant"><img src="https://agentmods.dev/badge/skills/ustc-fyk/antigravity-codex-mcp/agy-project-assistant/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/ustc-fyk/antigravity-codex-mcp/agy-project-assistant"><img src="https://agentmods.dev/badge/skills/ustc-fyk/antigravity-codex-mcp/agy-project-assistant.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 | $0.00067 | $0.00869 |
| Opus 5 | $0.00034 | $0.00434 |
| Sonnet 5 | $0.00013 | $0.00174 |
| Haiku 4.5 | $0.00007 | $0.00087 |
Grade A, and why
agy-project-assistant 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 9d 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 — 58 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGY Project Assistant
Use the globally available Antigravity MCP as an idle bridge. Never initialize, authorize, or call AGY unless the user explicitly requests AGY or Antigravity in the current request.
Resolve the project
- Use the current Codex project root as
project_root. - If the current root is unavailable or ambiguous, ask for the exact directory.
- Never substitute a parent directory, drive root, user home, or another saved project.
Enable AGY on explicit request
- Call
antigravity_project_statuswith the exact project root. - If disabled, explain that enabling AGY grants read access to that exact project and may send relevant content to the Google model.
- Treat the explicit request as authorization for that exact read scope, then call
antigravity_enable_project. - If the request only asks to load AGY and no active conversation exists, call
antigravity_start_session. - If the request includes a substantive task, call the appropriate task tool directly; its conversation becomes active.
Delegate work
- Use
antigravity_askfor a new analysis conversation. - Before a follow-up, use
antigravity_sync_conversationwhen the user may have interacted through AGY CLI.antigravity_continuealso synchronizes before and after its model call. - Use
antigravity_continuefor follow-ups in the active conversation. InspecttranscriptSync.before.recordsfor messages added through AGY CLI. - Use
antigravity_reviewfor an independent correctness, regression, security, or test-gap review. - Use
antigravity_executefor implementation. It may modify only an isolated copy and must never merge automatically. Keepverification: "none"unless the user explicitly accepts execution of AGY-influenced code; only then setallow_untrusted_verification: truewith a bounded verification timeout. - Prefer Codex itself for small tasks whose delegation overhead would exceed the work.
After every model call, report the exact project_root and conversation_id. After implementation, also report run_id, isolated workspace path, changed files, and verification status. Verify AGY conclusions independently before applying anything to source.
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.
- 9d ago First seen · 58 lines · 67 tokens per session scan A 516c0f7fbf53
agy-project-assistant is a skill published in the GitHub repository ustc-fyk/antigravity-codex-mcp (0 stars, last pushed 21d ago), licensed MIT. It adds 67 tokens to every session and 869 once invoked, about $0.0003 per session on Opus 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 skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…