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 lucaspmarie-a11y/claude-skills-vault --skill antigravity-skill-orchestratorgit clone --depth 1 https://github.com/lucaspmarie-a11y/claude-skills-vaultWrote 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/lucaspmarie-a11y/claude-skills-vault/antigravity-skill-orchestrator)<a href="https://agentmods.dev/skills/lucaspmarie-a11y/claude-skills-vault/antigravity-skill-orchestrator"><img src="https://agentmods.dev/badge/skills/lucaspmarie-a11y/claude-skills-vault/antigravity-skill-orchestrator/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/lucaspmarie-a11y/claude-skills-vault/antigravity-skill-orchestrator"><img src="https://agentmods.dev/badge/skills/lucaspmarie-a11y/claude-skills-vault/antigravity-skill-orchestrator.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 | $0.00042 | $0.01550 |
| Opus 5 | $0.00021 | $0.00775 |
| Sonnet 5 | $0.00008 | $0.00310 |
| Haiku 4.5 | $0.00004 | $0.00155 |
Grade A, and why
antigravity-skill-orchestrator 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 8d 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.
This is a copy
97% identical to antigravity-skill-orchestrator — 9 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 124 lines — stays where its author put it; the contents beside it link to each section on GitHub.
antigravity-skill-orchestrator
Overview
The skill-orchestrator is a meta-skill designed to enhance the AI agent's ability to tackle complex problems. It acts as an intelligent coordinator that first evaluates the complexity of a user's request. Based on that evaluation, it determines if specialized skills are needed. If they are, it selects the right combination of skills, explicitly tracks these combinations using @agent-memory-mcp for future reference, and guides the agent through the execution process. Crucially, it includes strict guardrails to prevent the unnecessary use of specialized skills for simple tasks that can be solved with baseline capabilities.
When to Use This Skill
- Use when tackling a complex, multi-step problem that likely requires multiple domains of expertise.
- Use when you are unsure which specific skills are best suited for a given user request, and need to discover them from the broader ecosystem.
- Use when the user explicitly asks to "orchestrate", "combine skills", or "use the best tools for the job" on a significant task.
- Use when you want to look up previously successful combinations of skills for a specific type of problem.
Core Concepts
Task Evaluation Guardrails
Not every task requires a specialized skill. For straightforward issues (e.g., small CSS fixes, simple script writing, renaming a variable), DO NOT USE specialized skills. Over-engineering simple tasks wastes tokens and time.
Additionally, the orchestrator is strictly forbidden from creating new skills. Its sole purpose is to combine and use existing skills provided by the community or present in the current environment.
Before invoking any skills, evaluate the task:
- Is the task simple/contained? Solve it directly using the agent's ordinary file editing, search, and terminal capabilities available in the current environment.
- Is the task complex/multi-domain? Only then should you proceed to orchestrate skills.
Skill Selection & Combinations
When a task is deemed complex, identify the necessary domains (e.g., frontend, database, deployment). Search available skills in the current environment to find the most relevant ones. If the required skills are not found locally, consult the master skill catalog.
What ships with it
1 file 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.
- 8d ago First seen · 124 lines · 42 tokens per session scan A e799e917dee8
antigravity-skill-orchestrator is a skill published in the GitHub repository lucaspmarie-a11y/claude-skills-vault (5 stars, last pushed 3mo ago), licensed MIT. It adds 42 tokens to every session and 1,550 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. It is 97% identical to antigravity-skill-orchestrator, differing in 9 lines, and is treated as a copy.
Other skills, from other repositories
antigravity-skill-orchestrator
A meta-skill that understands task requirements, dynamically selects appropriate skills, tracks successful skill combinations using agent-memory-mcp, and prevents skill overuse for simple tasks.
torchforge-rl-training
Provides guidance for PyTorch-native agentic RL using torchforge, Meta's library separating infra from algorithms. Use when you want clean RL abstractions, easy algorithm experimentation, or scalable training with Monarch and TorchTitan.
llamaguard
Meta's 7-8B specialized moderation model for LLM input/output filtering. 6 safety categories - violence/hate, sexual content, weapons, substances, self-harm, criminal planning. 94-95% accuracy. Deploy with vLLM, HuggingFace, Sagemaker. Integrates with NeMo Guardrails.
skill-authoring
Author SKILL.md skills: frontmatter, validator limits, structure.
pentest-playbook
7-phase pentest pipeline from passive recon to exploitation.
recon-playbook
Use when starting or restructuring an authorized external web and API assessment.