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 silennsong/Antigravity-CLI-Tool --skill gemini-delegation-routergit clone --depth 1 https://github.com/silennsong/Antigravity-CLI-ToolWrote 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/silennsong/antigravity-cli-tool/gemini-delegation-router)<a href="https://agentmods.dev/skills/silennsong/antigravity-cli-tool/gemini-delegation-router"><img src="https://agentmods.dev/badge/skills/silennsong/antigravity-cli-tool/gemini-delegation-router/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/silennsong/antigravity-cli-tool/gemini-delegation-router"><img src="https://agentmods.dev/badge/skills/silennsong/antigravity-cli-tool/gemini-delegation-router.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 | $0.00108 | $0.00982 |
| Opus 5 | $0.00054 | $0.00491 |
| Sonnet 5 | $0.00022 | $0.00196 |
| Haiku 4.5 | $0.00011 | $0.00098 |
Grade A, and why
gemini-delegation-router 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 10d 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.
How it starts
The opening of the file, as written. The whole thing — 69 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Gemini Delegation Router
Use Gemini as a selective worker, not as the owner of the overall task.
Route the work
- Identify independent subtasks before delegating. Prefer work that saves substantial context or produces an independently useful perspective.
- When terminal execution is available, use the Skill's
scripts/antigravity_delegate.py readinesslauncher before the first delegation in a new, moved, or renamed workspace. Resolve the script relative to thisSKILL.md, pass an absolute workspace, and consume its JSON output. - When terminal execution is available, use
scripts/antigravity_delegate.py delegateas the primary path. Supply the task with--task-fileor--task-stdinwhen quoting would be fragile. The command emits one JSON object and exits nonzero for rejected or incomplete onboarding. - If terminal execution is unavailable, the launcher is missing, or the host forbids local processes, use
check_antigravity_readinessanddelegate_to_antigravityas the compatibility path. Do not switch to MCP merely because a direct CLI request returned a project-policy or onboarding error; report that error. - If readiness is incomplete, report its checks and exact actions. Do not silently change authentication, global permissions, project policy, or an existing
AGENTS.md. - Delegate only a well-bounded subtask. Pass a self-contained task, absolute workspace, meaningful
task_kind, selectedmodel_tier, mode, and proportionate timeout. - Respect the closest
.codex/antigravity-policy.json. Treat a policy rejection as a project boundary, not as a reason to bypass either entrypoint. - Verify important Gemini claims against local files, commands, tests, or primary sources. Codex owns final decisions, edits, tests, and the user-facing answer.
Direct CLI examples
Resolve scripts/antigravity_delegate.py relative to this Skill, then run:
python3 /absolute/plugin/skill/scripts/antigravity_delegate.py readiness \
--workspace /absolute/project --model-tier flash
What ships with it
2 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.
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.
- 10d ago First seen · 69 lines · 108 tokens per session scan A 7cb7cc1536fb
gemini-delegation-router is a skill published in the GitHub repository silennsong/Antigravity-CLI-Tool (0 stars, last pushed 1mo ago), licensed MIT. It adds 108 tokens to every session and 982 once invoked, about $0.0005 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 2026-08-31.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
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…
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…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…