Best for
- Installing, updating, or smoke-testing the agy binary
- Driving non-interactive agy --print / agy -p one-shots
- Debugging Antigravity auth, sandbox, permissions, or plugin state
NousResearch/hermes-agent/optional-skills/autonomous-ai-agents/antigravity-cli/SKILL.md
Operate the Antigravity CLI (agy): plugins, auth, sandbox.
Decision brief
Operator guide for the Antigravity CLI, invoked as agy. Run all agy commands through the Hermes terminal tool; inspect its config and logs with readfile. This skill is reference + procedure — it does not wrap a network API, so there is nothing to authenticate from Hermes itself.
Compatibility matrix
| Platform | Status | Evidence | What to check |
|---|---|---|---|
| Codex | Not declared | No explicit evidence | Portability before use |
| Claude Code | Declared | Source record | Install path and trigger |
| Cursor | Not declared | No explicit evidence | Portability before use |
| Gemini CLI | Not declared | No explicit evidence | Portability before use |
Installation
The source command is displayed only when detected. A safe inspection prompt is always available so your agent can explain every action before execution.
npx skills add https://github.com/NousResearch/hermes-agent --skill "optional-skills/autonomous-ai-agents/antigravity-cli"Inspect the Agent Skill "antigravity-cli" from https://github.com/NousResearch/hermes-agent/blob/f5be9236e00ddf2f2a412697f267078fc4ee068e/optional-skills/autonomous-ai-agents/antigravity-cli/SKILL.md at commit f5be9236e00ddf2f2a412697f267078fc4ee068e. List every install step, command, network request, credential, file read/write, external action, and rollback step. Explain whether it fits my task. Do not install or execute anything until I approve.
Workflow
Invoke every agy command through the terminal tool. Examples:
For a conversational session, launch agy -i (or bare agy) under pty=true with tmux for capture-pane / send-keys, exactly the pattern documented in the codex / claude-code skills. Resume later with --continue / -c or a specific --conversation .
Confirm the install is real and usable, all through the terminal tool (read files with readfile):
Installing, updating, or smoke-testing the agy binary
Antigravity has two layers — keep them distinct or the guidance will be wrong:
Permission review
The documentation asks the agent to run terminal commands or scripts.
`agy update`, `agy changelog`. Run these through the `terminal` tool.The documentation asks the agent to run terminal commands or scripts.
Invoke every `agy` command through the `terminal` tool. Examples:Evidence record
| Signal | Value | Evidence type | Meaning |
|---|---|---|---|
| Quality score | 89/100 | Computed | Documentation, specificity, maintenance, and trust rules |
| Repository stars | 225,255 | Source | Repository attention, not individual Skill quality |
| Compatibility | 1 platforms | Source | Declared in the catalog source record |
| Usage guide | automated source guide | Editorial | Generated or reviewed according to the visible evidence level |
Pinned source
agy)Operator guide for the Antigravity CLI, invoked as agy. Run all agy
commands through the Hermes terminal tool; inspect its config and logs with
read_file. This skill is reference + procedure — it does not wrap a network
API, so there is nothing to authenticate from Hermes itself.
agy binaryagy --print / agy -p one-shotsAntigravity has two layers — keep them distinct or the guidance will be wrong:
agy help, agy install, agy plugin,
agy update, agy changelog. Run these through the terminal tool./config, /permissions,
/skills, /agents, etc. These only exist inside a running agy TUI
session, not on the shell wrapper.agy help shows the shell wrapper surface, NOT the in-session slash commands.
agy binary on PATH. Verify through the terminal tool:
command -v agy && agy --version.Invoke every agy command through the terminal tool. Examples:
terminal(command="agy --version")
terminal(command="agy help")
terminal(command="agy plugin list")
terminal(command="agy --print 'Summarize the repo in 3 bullets'", workdir="/path/to/project")
For an interactive multi-turn TUI session, launch agy with pty=true (and
tmux for capture/monitoring), the same pattern the codex / claude-code
skills use. For one-shot smoke tests and scripted prompts, prefer
agy --print (non-interactive).
To inspect Antigravity's own files, use read_file on the paths under Core
paths below — do not cat them through the terminal.
agy is a coding-agent backend in the same family as codex / claude-code,
so the same delegation shapes apply. Use these when handing real work (features,
fixes, reviews, second opinions) to Antigravity rather than just smoke-testing.
terminal(command="agy -p 'Review this diff for bugs and security issues' --model 'Gemini 3.1 Pro (High)'", workdir="/path/to/repo", timeout=300)
-p is non-interactive: it runs the prompt and exits. Pick the engine with
--model (run agy models for the exact display strings, e.g.
'Gemini 3.1 Pro (High)', 'Claude Opus 4.6 (Thinking)'). Add extra context
roots with repeatable --add-dir.
Background it and get notified on completion, the same as the codex skill:
terminal(command="agy -p 'Implement the change described in TASK.md and run the tests' --dangerously-skip-permissions", workdir="/path/to/repo", background=true, notify_on_complete=true)
# then: process(action="poll"/"log"/"wait", session_id=<id>)
For a conversational session, launch agy -i (or bare agy) under pty=true
with tmux for capture-pane / send-keys, exactly the pattern documented in
the codex / claude-code skills. Resume later with --continue / -c or a
specific --conversation <id>.
Create one git worktree per task and launch an independent agy -p in each
(background), then collect results — same worktree fan-out the codex skill
uses for batch issue fixing. Bound concurrency to what the machine and your
review capacity can absorb.
agy -p returns plain text — there is no --output-format json and
no result envelope with session_id / cost / turn count. Parse stdout
directly; don't expect a JSON object.--max-turns. A print run is bounded by --print-timeout
(default 5m). Raise it for long tasks: --print-timeout 20m. Pair with the
terminal timeout= so the outer call doesn't cut the run short.Antigravity is a worker execution backend or third-opinion reviewer — an
execution detail owned by the agent/profile running a task, NOT a first-class
orchestration primitive. Do not put agy on a kanban board as its own card or
treat it as a coordination layer; route work through the normal task graph and
let the assigned worker choose agy (vs. codex/claude-code/direct tools) as its
method. Reach for it explicitly only when the user asks, when a worker is
configured to wrap it, or when you want a Gemini-family cross-check against
another agent's plan or diff.
agy~/.gemini/antigravity-cli/~/.gemini/antigravity-cli/settings.json~/.gemini/antigravity-cli/keybindings.json~/.gemini/antigravity-cli/log/cli-*.log~/.gemini/antigravity-cli/conversations/~/.gemini/antigravity-cli/brain/~/.gemini/antigravity-cli/history.jsonl~/.gemini/antigravity-cli/plugins/<plugin_name>/agy changelogagy helpagy installagy plugin / agy pluginsagy update--add-dir--continue / -c--conversation--dangerously-skip-permissions--print / -p--print-timeout--prompt--prompt-interactive / -i--sandbox--log-file--versionagy plugin --help)list, import [source], install <target>, uninstall <name>,
enable <name>, disable <name>, validate [path], link <mp> <target>,
helpagy install --help)--dir, --skip-aliases, --skip-path/resume (/switch), /rewind (/undo),
/rename <name>, /clear, /fork, /reset, /new/config, /settings, /permissions, /model,
/keybindings, /statusline, /tasks, /skills, /mcp, /open <path>,
/usage, /logout, /agents@ path autocomplete, esc esc clears the prompt (when
not streaming), ! runs a terminal command directly, ? opens helpsettings.json)allowNonWorkspaceAccesscolorSchemepermissions.allowtrustedWorkspacesrequest-review, always-proceed, strict, proceed-in-sandbox.
enableTerminalSandbox is a boolean in settings.json; default false.--sandbox, --dangerously-skip-permissions) can
supersede persistent settings for the current session./logout removes saved credentials.~/.gemini/antigravity-cli/plugins/<plugin_name>/.agy plugin list returning no imported plugins is a valid empty state.agy help shows wrapper commands, not interactive slash commands.agy --version is the safe non-interactive version check; agy version is
interactive and can fail without a real TTY.~/.gemini/antigravity-cli/log/cli-*.log
(read with read_file).~/.gemini/antigravity-cli/bin/agentapi is a thin wrapper to agy agentapi..antigravitycli
project marker.agy -p prints plain text only — no --output-format json, no result
envelope. Don't try to parse a JSON object out of it (unlike claude-code).--print-timeout (default 5m), not --max-turns
(which does not exist on agy).Confirm the install is real and usable, all through the terminal tool (read
files with read_file):
terminal(command="command -v agy")terminal(command="agy --version")terminal(command="agy help")terminal(command="agy plugin list")read_file on ~/.gemini/antigravity-cli/settings.jsonread_file on the latest ~/.gemini/antigravity-cli/log/cli-*.logread_file on ~/.gemini/antigravity-cli/keybindings.jsonreferences/cli-docs.md — condensed notes from the getting-started, usage,
and features docs.Alternatives
narrative-io/narrative-skills-marketplace
Translate a fuzzy analytical question into a rigorous investigation plan. Interrogates the ask, grounds the plan in the available data dictionary, applies analytical best practices, and produces a structured brief of query specifications for a downstream query-writing skill. Plans, does not write SQL. Use when: "why did X drop", "is there a relationship between A and B", "who are our highest-value customers", "what's driving the change in Y", "investigate this trend", "design an analysis for", "
luongnv89/claude-howto
Comprehensive Claude Code self-assessment and learning path advisor. Runs a multi-category quiz covering 10 feature areas, produces a detailed skill profile with per-topic scores, identifies specific gaps, and generates a personalized learning path with prioritized next steps. Use when asked to "assess my level", "take the quiz", "find my level", "where should I start", "what should I learn next", "check my skills", "skill check", or "level up".
PramodDutta/qaskills
Generate optimized test combinations using pairwise (all-pairs) testing algorithms to achieve maximum coverage with minimum test cases across multiple input parameters
PramodDutta/qaskills
Gate RAG pipelines in CI with versioned golden eval sets, per-metric thresholds, baseline drift detection, and a build that fails when retrieval or answer quality regresses.