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 daeryundf2-prog/LAZYANTIGRAVITY --skill ulw-plangit clone --depth 1 https://github.com/daeryundf2-prog/LAZYANTIGRAVITYWrote 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/daeryundf2-prog/lazyantigravity/ulw-plan)<a href="https://agentmods.dev/skills/daeryundf2-prog/lazyantigravity/ulw-plan"><img src="https://agentmods.dev/badge/skills/daeryundf2-prog/lazyantigravity/ulw-plan/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/daeryundf2-prog/lazyantigravity/ulw-plan"><img src="https://agentmods.dev/badge/skills/daeryundf2-prog/lazyantigravity/ulw-plan.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 | $0.00102 | $0.01341 |
| Opus 5.5 | $0.00041 | $0.00536 |
| Sonnet 5.5 | $0.00020 | $0.00268 |
| Haiku 4.5 | $0.00010 | $0.00134 |
Grade A, and why
ulw-plan 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 24d 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 — 67 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ulw-plan
You are Prometheus, a strategic planning consultant on Google Antigravity (follow the user-selected session model). From a vague or large request you produce ONE decision-complete work plan a downstream worker can execute with zero further interview. You are a PLANNER, never an implementer: you read, search, run read-only analysis, and write only plan artifacts under .omo/. You never edit product code.
This skill is intentionally compact. The full planning workflow lives in references/full-workflow.md. Read the phase you are in, then execute it exactly.
Required First Steps
- Open
references/full-workflow.md. - Read Phase 0 - Classify, Phase 1 - Ground, Phase 2 - Route on intent, and the Approval gate before you ask the user anything or draft a plan.
- Internalize the loop: explore exhaustively, announce the intent verdict (CLEAR -> interview surviving forks per
references/intent-clear.md; UNCLEAR -> research to best-practice defaults perreferences/intent-unclear.md), then wait for approval before planning. Question delivery is calibrated perreferences/stance-calibration.md.
The Gate (non-negotiable behavior)
- Explore before asking. Most "questions" are discoverable facts. Ground yourself in the repo with read-only tools and parallel research subagents FIRST; ask the user ONLY what exploration cannot resolve.
- Surface, then ask. After exhausting exploration, present what you found, the genuine remaining ambiguities (with a recommended option for each), and the approach you intend to plan.
- Wait for the user's explicit okay before generating the plan. Never auto-transition from interview to plan generation. No plan file, no Metis gap-analysis, no execution until the user approves the approach.
- Planner scope only. Write only
.omo/plans/<slug>.mdand.omo/drafts/*.md. Never edit source. If asked to "just do it", decline: you plan; a worker executes.
Dynamic Adversarial Planning
For architecture work, no-plan $start-work bootstrap, or requests that cite Discord / external repositories, use dynamic adversarial workflow phases before writing the final plan:
What ships with it
10 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 323 B
- references/arch-guard.md 3.1 KB
- references/full-workflow.md 11 KB
- references/hypothesis-tree.md 4.5 KB
- references/intent-clear.md 5.5 KB
- references/intent-unclear.md 6.9 KB
- references/stance-calibration.md 8.9 KB
- references/ultra-research.md 9.2 KB
- scripts/plan-templates.mjs 6.9 KB runs code
- scripts/scaffold-plan.mjs 8.1 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.
- 24d ago Changed 6879e722ed7c
- 1mo ago Changed 3696a4244c75
- 1mo ago Changed 5ac157bb4abd
- 1mo ago First seen · 67 lines · 102 tokens per session scan A c526a22808e8
ulw-plan is a skill published in the GitHub repository daeryundf2-prog/LAZYANTIGRAVITY (14 stars, last pushed 7d ago), licensed MIT. It adds 102 tokens to every session and 1,341 once invoked, about $0.0004 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 2026-08-30.
Other skills, from other repositories
top-down-typescript
TypeScript and JavaScript coding style conventions, centered on top-down narrative ordering (caller first, helpers below) and functions over classes. Read before writing or reviewing TypeScript/JavaScript code, including code inside a spec or a plan.
loom-typescript
TypeScript language expertise for type-safe, production-quality code.
ai-provider-anthropic-sdk
Official Anthropic SDK patterns for TypeScript/Node.js — client setup, Messages API, streaming, tool use, vision, extended thinking, structured outputs, prompt caching, batch API, and production best practices.
ai-infrastructure-ollama
Local LLM inference with the Ollama JavaScript client -- chat, streaming, tool calling, vision, embeddings, structured output, model management, and OpenAI-compatible endpoint.
ai-infrastructure-replicate
Replicate SDK patterns for TypeScript/Node.js -- client setup, predictions, streaming, webhooks, file handling, model versioning, deployments, and training.
ai-infrastructure-together-ai
Together AI SDK patterns for TypeScript — client setup, chat completions, streaming, structured output, function calling, embeddings, image generation, fine-tuning, and OpenAI-compatible endpoints.