agy-native

A guide for running tasks in the AGY, or Antigravity, coding-agent runtime when that runtime is explicitly requested.

In plain words
What is it for?
Use it to discover the current AGY commands, run a scoped packet or validator session, and choose interactive, sandboxed, or headless execution.
Why use it?
It helps avoid relying on outdated command options and makes the session's permissions, workspace, and time limit clear.

Skill for Claude CodeCodex

Install

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.

agentmods
npx agentmods add skills/boshu2/agentops/agy-native
Any agent
npx skills add boshu2/agentops --skill agy-native
Clone the repo
git clone --depth 1 https://github.com/boshu2/agentops

Made for: Claude Code, Codex.

Per session 35 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 711 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00035 $0.00711
Opus 5 $0.00017 $0.00356
Sonnet 5 $0.00007 $0.00142
Haiku 4.5 $0.00003 $0.00071

Measured 2d ago against content hash 52e47f076561, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

agy-native 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 2d 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.

images/gemini/skills/agy-native/SKILL.md · 73 lines

How it starts

The opening of the file, as written. The whole thing — 73 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGY Native

Use AGY only when the caller explicitly selects that runtime. Discover its live command surface with agy --help (and agy models for the current model set) before acting, and scope every session to the supplied workspace and packet.

Discovering the live command surface before acting works because AGY's CLI changes faster than any skill text: a remembered flag is a guess, while a freshly listed one is evidence.

Permission posture (disclose it; never assume it)

The posture a run gets is chosen by flags, so name it explicitly:

  • Default agy runs interactively and prompts for each tool permission.
  • --dangerously-skip-permissions auto-approves every tool call — use it only when the packet's declared effects and the caller's authorization cover that blast radius.
  • --sandbox restricts the session's terminal access.
  • Print mode (agy -p / --print) is the sanctioned headless path and carries a built-in --print-timeout (default 5m); a run that exceeds it is killed and reported as timed out, not as a result.

A reader who sets none of these gets AGY's interactive default, not a scoped run. Match the posture to the declared effects and disclose which one was used.

When AGY is unavailable

If agy is not installed or its command surface cannot be discovered, report the absence as a disclosed fact and stop. Do not fall back to another runtime, do not guess a command surface, and never route through claude -p.

Named failure mode — wrapper drift: invoking AGY through remembered syntax that silently changed, producing runs that look scoped but are not.

Anti-pattern: reusing one AGY session for both author and validator roles because starting a second session is slower. Corrective: keep the identities distinct; a shared session forfeits the fresh-judgment guarantee that makes the validator's evidence usable.

  • Keep author and validator sessions distinct when AGY supplies both roles.
  • Persist the runtime conversation/context identity and artifact references.
  • Validators remain read-only and hand judgment to Validate; they do not write the core verdict directly.
  • AGY plugin, memory, permission, retry, and session state remain substrate facts and never become AgentOps phase, queue, or completion state.
  • Never invoke claude -p through an AGY wrapper.

Read the full file on GitHub · 73 lines

Changes

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.

  1. 2d ago First seen · 73 lines · 35 tokens per session scan A 52e47f076561

Subscribe to this mod's changes

agy-native is a skill published in the GitHub repository boshu2/agentops (431 stars, last pushed 4d ago), licensed Apache-2.0. It adds 35 tokens to every session and 711 once invoked, about $0.0002 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 2026-08-30.

Related

Other skills, from other repositories

enhance

Audit and tighten agent/plugin surfaces. Use when the user asks to enhance a plugin config, agent definition, skill, or CLAUDE.md.

OutlineDriven/odin-claude-plugin · 32 tokens

contexts

Use when the user says "get context on X", "how does X work", or wants architectural orientation before coding.

OutlineDriven/odin-claude-plugin · 26 tokens

mcp-developer

Use when building, debugging, or extending MCP servers or clients that connect AI systems with external tools and data sources. Invoke to implement tool handlers, configure resource providers, set up stdio/HTTP/SSE transport layers, validate schemas with Zod or Pydantic, debug protocol compliance issues, or scaffold…

Jeffallan/claude-skills · 79 tokens

shipping-artifacts

The durable documentation set that makes an AI-built (vibe-coded) app reviewable before shipping. A small core every app needs — architecture, user/permission flows, permissions, variables/secrets, and a test-coverage map — plus conditional docs added only when they apply: emails, scheduled work, SEO, and embedded…

phuryn/pm-skills · 120 tokens

implement-factory

Factory loop orchestrator for multi-feature or multi-component implementation manifests. Use for high-complexity work with parallel-eligible workstreams and holdout-scenario evaluation.

rsmdt/the-startup · 37 tokens

reflect-tree

Visualize a Claude Code session as a quest/skill tree — a navigable SVG graph where nodes are turns and edges show flow, with distinct visual encoding for normal flow, dead-ends, corrections, retries, reversals, and backtracking. Sibling to /reflect (which produces an incidents+recommendations dashboard); this one…

NikiforovAll/claude-code-rules · 115 tokens