agy-native
Use an explicitly selected AGY runtime for one provided packet or fresh validator context. Triggers: "agy", "antigravity", "AGY evidence".
Install
npx skills add https://github.com/boshu2/agentops/tree/main/images/gemini/skills/agy-native
claude plugin marketplace add https://llmmart.ai/marketplace.json && claude plugin install boshu2-agentops@llmmart
git clone https://github.com/boshu2/agentops.git
The skills CLI installs just this skill, for any of its supported agents. Claude Code installs the whole boshu2/agentops collection as a plugin from our marketplace. Git is the plain clone.
Skill manifest
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
agyruns interactively and prompts for each tool permission. --dangerously-skip-permissionsauto-approves every tool call — use it only when the packet's declared effects and the caller's authorization cover that blast radius.--sandboxrestricts 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 -pthrough an AGY wrapper.
Return evidence to the caller and stop. Installation, plugin mutation, and recurring scheduling require separate explicit authorization.
Files (agentops)
-
SKILL.md 3.1 KB
--- name: agy-native description: 'Run a supplied task in AGY Antigravity and collect its result. Use when: the caller selects AGY; never a fallback for native coding.' practices: [team-topologies, design-by-contract] hexagonal_role: driving-adapter consumes: [explicit-packet] produces: [agy-run-evidence] context_rel: - kind: separate-ways with: codex-exec skill_api_version: 1 user-invocable: true metadata: tier: cross-vendor dependencies: [] capabilities: [dispatch_explicit_packet, provide_fresh_context] effects: [start_agy_session] canonical_status: canonical disposition: keep_optional_adapter output_contract: AGY runtime evidence --- # 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. Return evidence to the caller and stop. Installation, plugin mutation, and recurring scheduling require separate explicit authorization.
Comments (0)
Sign in to join the conversation.
Reviews (0)
No reviews yet.
No comments yet.