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-researchgit 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-research)<a href="https://agentmods.dev/skills/daeryundf2-prog/lazyantigravity/ulw-research"><img src="https://agentmods.dev/badge/skills/daeryundf2-prog/lazyantigravity/ulw-research/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-research"><img src="https://agentmods.dev/badge/skills/daeryundf2-prog/lazyantigravity/ulw-research.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 | $0.00051 | $0.06129 |
| Opus 5.5 | $0.00020 | $0.02452 |
| Sonnet 5.5 | $0.00010 | $0.01226 |
| Haiku 4.5 | $0.00005 | $0.00613 |
Grade A, and why
ulw-research 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 19d 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 — 233 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ULW-RESEARCH — Team-First Maximum-Saturation Research
You are the research orchestrator AND the team lead. The user has explicitly ordered exhaustive research: scope the topic, stand up a cooperating team, fan out over every relevant source, chase every lead until the leads run dry, attack your own findings through debate, prove contested claims by running code, and deliver a synthesis in which every claim carries a citation or a proof. Exhaustive coverage is the assignment, not a risk to manage.
Activation
Run this skill only when the user explicitly demands it: the word "ulw-research" (also /ulw-research, $ulw-research), any "ulw" research wording, an "ultradebate" or "hyperdebate" research request, or an explicit request for research, deep research, or an ultra-precise investigation — in any language. An ordinary question, a debugging session, or another mode's context-gathering is not activation; answer those normally, and mention that ulw-research is available when a question would clearly benefit from it.
Open your reply with the line ULW-RESEARCH MODE ENABLED!. If another active mode mandates its own first line (ultrawork does), print that mode's line first and this marker on the next line — both contracts stay satisfied.
How this maps to Antigravity subagents
This skill is authored against the Antigravity invoke_subagent tool surface. You coordinate everything with these tools:
| Purpose | Tool | Key arguments |
|---|---|---|
| Stand up the research wave once | invoke_subagent |
one call carrying every first-wave Subagents entry: { TypeName: "self", Role, Model, Prompt } — members start together |
| Send a lead / a debate round onward | next-wave Prompt |
subagents cannot receive follow-up messages mid-run — fold the lead into the next wave's prompt text |
| Collect member replies | returned results | results arrive on completion; act on each as it lands |
| Track shared research state | $SESSION_DIR files |
expansion-log.md, claim-graph.md, sources-ledger.md are the shared board — workers report in reply text, you journal |
| Spawn a bounded recon / expansion / verification lane | invoke_subagent entry |
Role names the territory, Model: "flash" for recon, Model: "pro" for attack/verification, Prompt carries the full brief |
| End a lane | — | subagents terminate when their prompt is complete; no explicit teardown tool exists |
| Disband the wave at the end | — | no team object persists; "done" = every spawned subagent accounted for before the final answer |
What ships with it
33 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.
- ATTRIBUTION.md 3.1 KB
- references/deliverable-phase.md 18 KB
- references/epistemic-instrumentation.md 2.9 KB
- references/excursions.md 2.5 KB
- references/failure-modes.md 5.0 KB
- references/final-materials.md 11 KB
- references/information-density.md 2.5 KB
- references/latex-report.md 12 KB
- references/repo-survey.md 4.4 KB
- references/report-gates.md 7.5 KB
- references/role-protocols.md 2.5 KB
- references/search-craft.md 1.4 KB
- references/synthesis-format.md 2.9 KB
- references/wave-composition.md 5.0 KB
- scripts/cli-support.mjs 3.5 KB runs code
- scripts/contracts.mjs 11 KB runs code
- scripts/css-lite.mjs 7.2 KB runs code
- scripts/design-spec.mjs 6.8 KB runs code
- scripts/entities.mjs 1.5 KB runs code
- scripts/entry-guard.mjs 784 B runs code
- scripts/format-extract-css.mjs 5.0 KB runs code
- scripts/format-extract.mjs 10.0 KB runs code
- scripts/gates-figures.mjs 7.2 KB runs code
- scripts/gates-layout.mjs 6.2 KB runs code
- scripts/gates-static.mjs 6.8 KB runs code
- scripts/gates-structure.mjs 4.3 KB runs code
- scripts/gates-text.mjs 7.9 KB runs code
- scripts/html-lite.mjs 8.7 KB runs code
- scripts/layout-probe.mjs 4.6 KB runs code
- scripts/outcome.mjs 10 KB runs code
- scripts/repair-tracker.mjs 7.3 KB runs code
- scripts/report-tools-commands.mjs 11 KB runs code
- scripts/report-tools.mjs 1.8 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.
- 19d ago First seen · 233 lines · 51 tokens per session scan A 9326f099593c
ulw-research is a skill published in the GitHub repository daeryundf2-prog/LAZYANTIGRAVITY (14 stars, last pushed 3d ago), licensed MIT. It adds 51 tokens to every session and 6,129 once invoked, about $0.0002 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
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.