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 patrick-fu/awesome-skills --skill antigravity-coding-agentgit clone --depth 1 https://github.com/patrick-fu/awesome-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/patrick-fu/awesome-skills/antigravity-coding-agent)<a href="https://agentmods.dev/skills/patrick-fu/awesome-skills/antigravity-coding-agent"><img src="https://agentmods.dev/badge/skills/patrick-fu/awesome-skills/antigravity-coding-agent/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/patrick-fu/awesome-skills/antigravity-coding-agent"><img src="https://agentmods.dev/badge/skills/patrick-fu/awesome-skills/antigravity-coding-agent.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 | $0.00026 | $0.00479 |
| Opus 5.5 | $0.00010 | $0.00192 |
| Sonnet 5.5 | $0.00005 | $0.00096 |
| Haiku 4.5 | $0.00003 | $0.00048 |
Grade A, and why
antigravity-coding-agent scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 3d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
Antigravity Coding Agent
Scope
Check the selected launcher's --version, --help, and models. Tiered model
IDs already carry effort; add --effort only when needed. Honor explicit
choices and compare requested settings with emitted values. Keep wrappers
opaque: source, arguments and environment may contain credentials.
Fix workspace, permitted actions and acceptance evidence; isolate experiments and parallel writers. Boundary: before file-only work, confined writes or permission recovery, read Boundaries. API: before key/endpoint setup or route verification, read API mode. The skill grants no extra authorization.
Run
Use agy_run.py as the only supported entry point:
python3 "$SKILL_DIR/scripts/agy_run.py" \
--cwd "$WORKSPACE" --prompt-file "$PROMPT_FILE" \
--label review --print-timeout 45m --agy-bin "$LAUNCHER" \
-- --model "$MODEL"
SKILL_DIR is this skill's directory. Choose the CLI deadline deliberately;
0 is unbounded. Pass other authorized launcher arguments unchanged after --.
| Owner | Responsibility |
|---|---|
| Script | G0 duration, G1 cwd, G2 prompt, G3 unique captures, G4 child exit, G5 typed receipt |
| Agent | Model, permissions, required tool evidence, artifact acceptance, recovery |
Retain the host process handle. The script prints run_dir, then the final
receipt. Use python3 "$SKILL_DIR/scripts/agy_run.py" inspect "$RUN_DIR" for
compact evidence while waiting. Quiet output alone is not failure.
Accept
SUCCESS is an evidence verdict, not artifact acceptance. Read answer.txt;
check required completed tools and actual artifacts/diff against Scope; report
unperformed checks. Recover: for failed/incomplete evidence, timeout,
cancellation, raw-stream diagnosis or resume, read
Recovery before another attempt.
What ships with it
12 files 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.
- agents/openai.yaml 245 B
- evals/check_ablation.py 6.4 KB runs code
- evals/check_cancel.py 8.8 KB runs code
- evals/check_launch_guards.py 12 KB runs code
- evals/check_stream_parser.py 11 KB runs code
- evals/evidence.json 5.9 KB
- evals/fixtures/denied.jsonl 213 B
- evals/fixtures/success-1.3.6.jsonl 1007 B
- evals/stub_agy.py 1.9 KB runs code
- references/api-mode.md 3.3 KB
- references/monitoring.md 5.9 KB
- scripts/agy_run.py 14 KB runs code
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.
- 3d ago Changed · -37 lines · -4 tokens per session 0e2bd21a62cd
- 8d ago Changed · +10 lines 8d7907abe54d
- 15d ago Changed · -63 lines f1c9ca136db7
- 26d ago Changed · +5 lines 3a03dbb23381
- 27d ago Changed · +18 lines 2055c1d86722
- 29d ago First seen · 118 lines · 30 tokens per session scan A 18de38b9fbd6
antigravity-coding-agent is a skill published in the GitHub repository patrick-fu/awesome-skills (69 stars, last pushed 4d ago), licensed MIT. It adds 26 tokens to every session and 479 once invoked, about $0.0001 per session on Opus 5.5. 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 2026-09-27.
Other skills, from other repositories
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…
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
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…
next-cache-components-optimizer
Optimize the meaningful UI available immediately from a Next.js route on an initial load (hard navigation) or named client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route and entry point at a time; the shipped test then guards…