Borrowing it
Nothing to install: this file belongs to nirholas/three.ws. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/nirholas/three.ws/main/.agents/skills/build-an-agent-skill/SKILL.mdgit 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/build-an-agent-skill)<a href="https://agentmods.dev/skills/nirholas/three.ws/build-an-agent-skill"><img src="https://agentmods.dev/badge/skills/nirholas/three.ws/build-an-agent-skill/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/nirholas/three.ws/build-an-agent-skill"><img src="https://agentmods.dev/badge/skills/nirholas/three.ws/build-an-agent-skill.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 | $0.00148 | $0.02523 |
| Opus 5.5 | $0.00059 | $0.01009 |
| Sonnet 5.5 | $0.00030 | $0.00505 |
| Haiku 4.5 | $0.00015 | $0.00252 |
Grade A, and why
build-an-agent-skill scanned grade A with 1 finding 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 14d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
| Network | `ctx.fetch(uri, opts)` (normal CORS rules apply) | 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.
Build a three.ws agent skill
A three.ws skill is a directory served from any URL. The agent runtime fetches it, injects its instructions into the system prompt, exposes its tools to the LLM, and runs its handlers in a Web Worker sandbox. Because a skill is just files behind a URL, the same bundle installs into every agent without copying code.
Do not confuse this with the Claude skill you are reading: that one teaches an external model how to use three.ws. This one teaches a three.ws agent a new capability.
The four files
| File | Required | Purpose |
|---|---|---|
manifest.json |
yes | Identity, version, what it provides, config defaults |
SKILL.md |
yes | Instructions injected into the agent's system prompt |
tools.json |
yes, if it exposes tools | JSON Schema tool definitions the LLM can call |
handlers.js |
no | ES module implementing each tool |
A bundle with no handlers.js is valid and always trusted: it is a declarative skill
that only shapes behavior (an accent, a house style, a refusal policy).
Assets (clips/, morphs/, prompts/, assets/) sit beside those files and are
resolved against ctx.skillBaseURI.
A complete, working bundle
Copy this shape. The repo's starter is examples/skills/wave/
and the runtime contract is docs/skills.md.
manifest.json
{
"spec": "skill/0.1",
"name": "weather-report",
"version": "0.1.0",
"description": "Look up the current temperature and wind for any named place and say it out loud.",
"license": "MIT",
"tags": ["weather", "voice"],
"requires": { "runtime": ">=0.1.0", "capabilities": [] },
"provides": { "tools": ["reportWeather"], "triggers": [] },
"config": { "units": "metric" }
}
tools.json
{
"tools": [
{
"name": "reportWeather",
"description": "Report the current temperature and wind speed for a named place, and speak the result.",
"input_schema": {
"type": "object",
"properties": {
"place": { "type": "string", "description": "City, town, or landmark name" }
},
"required": ["place"]
}
}
]
}
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.
- 14d ago Changed · +1 lines · +148 tokens per session 2569dc89a057
- 1mo ago First seen · 232 lines · 0 tokens per session scan A 0a1e49c876aa
build-an-agent-skill is a skill published in the GitHub repository nirholas/three.ws (269 stars, last pushed yesterday), licensed Apache-2.0. It adds 148 tokens to every session and 2,523 once invoked, about $0.0006 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-21.
build-an-agent-skill compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| build-an-agent-skillnirholas/three.ws | Skill | 269 | yesterday | Apache-2.0 | A | 148 | Claude Code |
| cesiumjsznlgis/opengis-skills | Skill | 76 | 10d ago | MIT | A | 93 | Claude Code, Codex |
| decision-avatarellmos-ai/skills | Skill | 9 | 4d ago | MIT | A | 49 | Claude Code, Codex |
| sheleg-designssheleg/sheleg-design-skill | Skill | 4 | 4d ago | MIT | A | 80 | Cursor |
| p5jsmateaix/mateclaw | Skill | 1.2k | yesterday | Apache-2.0 | A | 20 | Claude Code, Codex |
| threejs-docspledgeandgrow/pledge-skills | Skill | 10 | 3mo ago | MIT | A | 112 | Claude Code, Codex |
| 3d-website-architectdeveshpunjabi/3d-website-skill | Skill | 8 | 8mo ago | MIT | A | 240 | Claude Code, Codex |