Agy cli agent

Skill ImL1s/agent-cli-skills/skills/agy-cli-agent

Run Google Antigravity CLI (agy) headlessly via agy-exec.sh / agy-task.sh / agy-explore.sh. Use when the user asks for agy, Antigravity, Gemini CLI agent, or to execute a plan with agy. Always allocates a PTY (agy -p is silent without TTY). Prefer -f for long prompts; --no-git and orchestrator-owned commits. -r plan/sandbox; -T teamwork/subagent preamble.From its SKILL.md

Install

npx -y skills add ImL1s/agent-cli-skills --skill agy-cli-agent

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

One thing to look at

2 stars2 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

SKILL.md

2.8 KB, 719 tokens by cl100k_base, as published. Nobody here has run it

Antigravity CLI (`agy`) Executor

When to use

User wants agy / Antigravity as the coding agent
Orchestrator needs a headless agy run (pipes, CI, council seats)
Plan-executor / explore helpers (agy-task.sh, agy-explore.sh)

Prefer other *-cli-agent skills when the user names Claude, Codex, Grok, Kimi, or Qwen. For multi-provider parallel opinions, use multi-cli-spawn.

Wrapper

# From this skill directory (or after ./install.sh):
./agy-exec.sh -C /path/to/repo -t 900s "Implement the task; stop when done."
./agy-exec.sh -r -C /path/to/repo "Where is auth handled?"   # read-only
./agy-exec.sh -T -C /path/to/repo "Large refactor…"          # native multi-agent hint
./agy-task.sh -C /path/to/repo -v "npm test" "Do task X"
./agy-explore.sh -C /path/to/repo "How does routing work?"

Shared flags: -m model · -t print-timeout · -C cwd · -f prompt-file · -r read-only · -s sandbox · -T teamwork/subagent preamble · --agent · --mode · --effort · --add-dir · --no-git · -- passthrough to agy.

Default model: gemini-3.5-flash-high. Discover ids with agy models. -C is absolutized before use (relative paths are safe).

Critical: PTY required

agy -p prints nothing unless stdout is a real TTY (gemini-cli#76). This wrapper always uses lib/pty_run.py. Do not call bare agy -p from pipes/subprocesses.

Native multi-agent

Interactive: /teamwork-preview (Ultra plan preview), /agents panel, custom agents under .agents/agents/
Headless: -T adds a teamwork/subagent preamble; also --agent NAME
We do not reimplement teamwork — we ask agy to use its own orchestration when available

Git hazard

Prompts that mention git show / git diff / git checkout can cause agy to move HEAD. Prefer pre-computed diffs pasted into the prompt. Use --no-git. Orchestrator owns commits.

Discipline

Exit code is untrusted — verify with git diff + your done-criteria
Prefer disposable git worktrees for autonomous --dangerously-skip-permissions runs
One task = one agy -p (headless resume is unreliable)

Raw surface (pass after `--`)

agy --help: --add-dir, --agent, --continue, --conversation, --dangerously-skip-permissions, --effort, --mode, --model, --print/-p, --print-timeout, --sandbox, subcommands models, agent(s), plugin, update.

What ships with it: 6 files

20.2 KB alongside SKILL.md, 6 of them executable

lib/

common.shruns6.8 KB
parse_stream_json.pyruns3.5 KB
pty_run.pyruns1.7 KB

agy-exec.shruns4.6 KB
agy-explore.shruns1.7 KB
agy-task.shruns1.8 KB

Gives 0 of the 12 instructions most context ai engineering skills give in 719 tokens

Counted across 1,328 of the 2,349 authors here whose files we hold, read 2026-09-06

Dispatch a fresh subagent for each taskin 76 of 1328, across 59 files
Perform spec compliance review before code quality reviewin 44 of 1328, across 34 files
Dispatch a final code reviewer after all tasksin 38 of 1328, across 26 files
Answer subagent questions before allowing implementationin 36 of 1328, across 26 files
Use the least powerful model capable of the taskin 33 of 1328, across 26 files
Create a TodoWrite list for all tasksin 32 of 1328, across 22 files
Perform a task review after each implementationin 31 of 1328, across 24 files
Extract all tasks and context from the planin 29 of 1328, across 20 files
Provide full task text to subagentsin 28 of 1328, across 20 files
Use git worktrees for isolated workspacesin 25 of 1328, across 20 files
Specify the model explicitly when dispatching a subagentin 23 of 1328, across 18 files
Execute all tasks from the plan without stoppingin 21 of 1328, across 16 files

Said here and by no other author read

Use -r for read-only reviews
Allocate a PTY for all agy executions
Use agy-exec.sh for headless task execution
Use -f for long prompts
Use --no-git to prevent unintended commits
Use -T for teamwork or subagent preambles

Grouped from the skills themselves: near-identical wordings counted once, and counted by distinct author, so one author publishing three of these counts once. Length counted with cl100k_base; the agent that loads this file may tokenize it differently.