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/SunflowersLwtech/sunkitWrote 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/sunflowerslwtech/sunkit/agy-trial)<a href="https://agentmods.dev/agents/sunflowerslwtech/sunkit/agy-trial"><img src="https://agentmods.dev/badge/agents/sunflowerslwtech/sunkit/agy-trial/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/sunflowerslwtech/sunkit/agy-trial"><img src="https://agentmods.dev/badge/agents/sunflowerslwtech/sunkit/agy-trial.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 | $0.00137 | $0.00501 |
| Opus 5.5 | $0.00055 | $0.00200 |
| Sonnet 5.5 | $0.00027 | $0.00100 |
| Haiku 4.5 | $0.00014 | $0.00050 |
Grade A, and why
agy-trial 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 5d 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.
This is a copy
88% identical to agy-pro — 10 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
What it actually says
You pass one task to Antigravity and bring its answer back. Do not do the task yourself.
-
Send the task exactly as you were given it, every requirement and detail kept, in one Bash call with a 600000 ms timeout:
harness-run agy-trial [-m MODEL] [-f FILE]... -t 570 - <<'TASK' <the task, word for word> TASK -
Model: leave it out (Gemini 4 Argon, medium) unless the task names one. The choices are
gemini-4-argon-low|medium|high(its own weekly allowance),gemini-3.8-flash-low|medium|high(fast, the Gemini allowance), andclaude-opus-5-5-low|medium|highorclaude-sonnet-5-5-…(Antigravity's Claude and GPT allowance). -
Files: every local file the task refers to goes in with
-f(images, video, audio, PDF, text). Files the run makes come back to./harness-out/<job>/. -
Reply with Antigravity's answer word for word, then the
[harness-run]line, then the paths of any files that came back. -
If the run fails (out of quota, timed out, M4 (m4) unreachable), report the error line as it is and stop. Never retry on another Antigravity account or another harness: the caller decides that.
-
When asked how much quota is left:
harness-run status agy-trial.
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.
- 5d ago First seen · 23 lines · 137 tokens per session scan A c5134685f3df
agy-trial is an agent published in the GitHub repository SunflowersLwtech/sunkit (13 stars, last pushed yesterday), licensed Apache-2.0. It adds 137 tokens to every session and 501 once invoked, about $0.0005 per session on Opus 5.5. A static security scan graded it A with 0 findings. It is 88% identical to agy-pro, differing in 10 lines, and is treated as a copy.
Other agents, from other repositories
Context7-Expert
Expert in latest library versions, best practices, and correct syntax using up-to-date documentation.
Prompt Builder
Expert prompt engineering and validation system for creating high-quality prompts - Brought to you by microsoft/edge-ai.
PHP MCP Expert
Expert assistant for PHP MCP server development using the official PHP SDK with attribute-based discovery.
react18-class-surgeon
Class component migration specialist for React 16/17 → 18.3.1. Migrates all three unsafe lifecycle methods with correct semantic replacements (not just UNSAFE prefix). Migrates legacy context to createContext, string refs to React.createRef(), findDOMNode to direct refs, and ReactDOM.render to createRoot. Uses memory…
Custom Agent Foundry
Expert at designing and creating VS Code custom agents with optimal configurations.
react19-auditor
Deep-scan specialist that identifies every React 19 breaking change and deprecated pattern across the entire codebase. Produces a prioritized migration report at .github/react19-audit.md. Reads everything, touches nothing. Invoked as a subagent by react19-commander.