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 agentmods add skills/nirholas/three.ws/coach-leonpx skills add nirholas/three.ws --skill coach-leogit clone --depth 1 https://github.com/nirholas/three.wsWrote 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/nirholas/three.ws/coach-leo)<a href="https://agentmods.dev/skills/nirholas/three.ws/coach-leo"><img src="https://agentmods.dev/badge/skills/nirholas/three.ws/coach-leo.svg" alt="Measured on agentmods" 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 | $0.00010 | $0.00087 |
| Opus 5 | $0.00005 | $0.00044 |
| Sonnet 5 | $0.00002 | $0.00017 |
| Haiku 4.5 | $0.00001 | $0.00009 |
Grade A, and why
Coach Leo 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 2d 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
Coach Leo: Capabilities
- Wave at users on greetings (via the
waveskill). - Read glTF/body data to comment on your avatar.
- Remember user context across sessions (memory is local by default).
- Speak aloud when voice mode is on.
Further skills can be added by setting skills: in manifest.json.
What ships with it
3 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.
- 2d ago First seen · 14 lines · 10 tokens per session scan A 4ae3938aeb7f
Coach Leo is a skill published in the GitHub repository nirholas/three.ws (110 stars, last pushed yesterday), licensed Apache-2.0. It adds 10 tokens to every session and 87 once invoked, about $0.0001 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 2026-09-03.
Other skills, from other repositories
blender-mcp
Drive Blender via the catalog blender MCP, with bpy recipes.
blender-mcp
Control Blender directly from Gauss via socket connection to the blender-mcp addon. Create 3D objects, materials, animations, and run arbitrary Blender Python (bpy) code. Use when user wants to create or modify anything in Blender.
emercoin-identity
Give an AI agent a verifiable on-chain identity and durable memory on the Emercoin blockchain, via the emercoin-agent MCP tools. Use when an agent needs to register its identity, store hashes of research/memories/artifacts on-chain, prove who it is by signature, or read another agent's on-chain identity or records.
threejs-docs
Comprehensive Three.js reference covering core API (objects, cameras, lights, materials, geometries, renderers, scenes, textures, math, animation, audio, loaders, helpers, nodes), all addons (controls, postprocessing, loaders, exporters, geometries, shaders, WebXR, physics), TSL (Three.js Shading Language) functions…
agent-memory-profiles
Design durable user, project, persona, and task memory profiles for local agents.
self-improving-agent
Closed-loop learning system — captures errors, corrections, and discoveries into structured logs, promotes recurring patterns to project memory, and extracts reusable skills.