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 valtterimelkko/agent-workflow-skills --skill agy-pgit clone --depth 1 https://github.com/valtterimelkko/agent-workflow-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/valtterimelkko/agent-workflow-skills/agy-p)<a href="https://agentmods.dev/skills/valtterimelkko/agent-workflow-skills/agy-p"><img src="https://agentmods.dev/badge/skills/valtterimelkko/agent-workflow-skills/agy-p/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/valtterimelkko/agent-workflow-skills/agy-p"><img src="https://agentmods.dev/badge/skills/valtterimelkko/agent-workflow-skills/agy-p.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 | $0.00128 | $0.03781 |
| Opus 5 | $0.00064 | $0.01891 |
| Sonnet 5 | $0.00026 | $0.00756 |
| Haiku 4.5 | $0.00013 | $0.00378 |
Grade B, and why
agy-p scanned grade B with 2 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 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.
- Global settings: `~/.gemini/settings.json` Runs shell commandslowCapability
Expected in a hook, worth knowing in a rule or an instructions file.
import { spawn } from "node:child_process"; How it starts
The opening of the file, as written. The whole thing — 540 lines — stays where its author put it; the contents beside it link to each section on GitHub.
agy-p
Use this skill when the task is not “how do I use the Antigravity TUI manually?”, but rather:
- “How do I call
agyfrom code?” - “Can another agent/script use my Google-backed Antigravity subscription?”
- “How do I run Antigravity headlessly?”
- “How do I resume an
agyconversation programmatically?” - “Why is
agy -phanging / asking for permissions / printing weird extra output?”
This skill is about the CLI subprocess integration path.
Mental model
agy has two distinct modes:
- Interactive TUI mode — plain
agy - Headless one-shot print mode —
agy -p/agy --print
For programmatic integrations, prefer print mode unless you truly need the live TUI.
The key idea: agy authenticates using the same user’s local Antigravity credentials, so a script can usually reuse the existing Google-backed login without needing a separate API key.
Fast answer
For a one-shot scripted call, start here:
agy \
--dangerously-skip-permissions \
--print-timeout 10m \
-p "Summarise the repo and suggest the next 3 actions"
Good defaults for integrations:
- set the working directory deliberately
- add
--dangerously-skip-permissionsif the task may use tools - set
--print-timeoutexplicitly - optionally set
--model - capture
stdoutandstderr - treat the command as a subprocess, not an API
Verified local facts
These were verified locally on this machine with agy 1.0.6:
- Binary path:
<AGY_BIN> agy --helpexposes:--print,--prompt,--dangerously-skip-permissions,--print-timeout,--model,--conversation,--continue,--sandbox,--add-dir,--log-file,--prompt-interactiveagy --helpalso lists shell subcommands:changelog,help,install,models,plugin,plugins,updateagy modelsworks non-interactively and currently lists:Gemini 3.5 Flash (Medium)Gemini 3.5 Flash (High)Gemini 3.5 Flash (Low)Gemini 3.1 Pro (Low)Gemini 3.1 Pro (High)Claude Sonnet 4.6 (Thinking)Claude Opus 4.6 (Thinking)GPT-OSS 120B (Medium)
- A fresh print call like
agy -p "Reply with exactly: AGY_OK"returned clean stdout - Output redirection to a file worked locally on Linux in testing
--conversation <id>and--continueboth worked for follow-up turns- Important integration caveat (local observation, not promised contract): in local testing, resumed print-mode calls emitted prior assistant replies on stdout before the newest reply. Do not assume resumed output is only the latest turn.
What ships with it
1 file 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 · 540 lines · 128 tokens per session scan B 8886bbe787dc
agy-p is a skill published in the GitHub repository valtterimelkko/agent-workflow-skills (2 stars, last pushed 2mo ago), licensed MIT. It adds 128 tokens to every session and 3,781 once invoked, about $0.0006 per session on Opus 5. A static security scan graded it B with 2 findings (reads agent configuration directories, runs shell commands). 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…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
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…