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/darellchua2/opencode-config-template/cad-implicit-skillnpx skills add darellchua2/opencode-config-template --skill cad-implicit-skillgit clone --depth 1 https://github.com/darellchua2/opencode-config-templateWrote 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/darellchua2/opencode-config-template/cad-implicit-skill)<a href="https://agentmods.dev/skills/darellchua2/opencode-config-template/cad-implicit-skill"><img src="https://agentmods.dev/badge/skills/darellchua2/opencode-config-template/cad-implicit-skill.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 | $0.00038 | $0.02483 |
| Opus 5 | $0.00019 | $0.01241 |
| Sonnet 5 | $0.00008 | $0.00497 |
| Haiku 4.5 | $0.00004 | $0.00248 |
Grade A, and why
cad-implicit-skill 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 3d 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
86% identical to implicit-cad — 64 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 — 175 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Implicit CAD
Use this skill for implicit CAD models that should run directly in CAD Viewer as browser JS modules. The primary artifact is a .implicit.js or .implicit.mjs.
This skill is experimental. ALWAYS prefer conventional STEP-first CAD workflows unless the user explicitly asks for an implicit model.
File Format
An implicit CAD file is an ES module exporting an implicit.js/0.1.0 object. The schema source of truth lives in the bundled package at scripts/packages/implicitjs/src/lib/implicitCad/schema.js; scripts/lib/implicit-cad.mjs re-exports it as SCHEMA for helper-authored modules.
export default {
schema: "implicit.js/0.1.0",
name: "rounded capsule block",
glsl: `
float sdf(vec3 p) {
float sphere = implicit_sphere(p, vec3(0.0), 22.0);
float block = implicit_box_centered(p, vec3(34.0, 18.0, 18.0), vec3(0.0));
return implicit_union_round(sphere, block, 3.0);
}
vec3 color(vec3 p, vec3 normal) {
return mix(vec3(0.20, 0.55, 0.95), vec3(0.95, 0.45, 0.20), smoothstep(-15.0, 20.0, p.z));
}
`,
};
Models may also declare params and animations. Parameter definitions use the implicitjs control schema: number, boolean, enum/select, color, string, and button. Number, boolean, color, and button params automatically become GLSL uniforms with the same name; do not add a separate uniforms object. bounds is optional and is estimated from the SDF when omitted; add explicit bounds only when the auto estimate is too broad, too slow, or misses an unusual field. bounds and render may be JavaScript functions that receive { ...params, params, animation, animationState, elapsedSec, progress, t }.
Built-in GLSL helpers use the implicit_* namespace, for example implicit_sphere, implicit_box_centered, and implicit_union_round.
export default {
schema: "implicit.js/0.1.0",
name: "breathing orb",
params: {
radius: {
type: "number",
label: "Radius",
min: 12,
max: 34,
default: 22,
unit: "mm",
},
},
animations: {
breathe: {
label: "Breathe",
duration: 3,
update({ progress, set }) {
set("radius", 18 + Math.sin(progress * Math.PI) * 10);
},
},
},
render: { steps: 224, epsilon: 0.004 },
glsl: `
float sdf(vec3 p) {
return length(p) - radius;
}
vec3 color(vec3 p, vec3 normal) {
return mix(vec3(0.10, 0.58, 0.95), vec3(1.0, 0.34, 0.12), smoothstep(-18.0, 18.0, p.z));
}
`,
};
What ships with it
44 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.
- LICENSE 1.1 KB
- scripts/export.mjs 723 B runs code
- scripts/lib/implicit-cad.mjs 13 KB runs code
- scripts/packages/implicitjs/package-lock.json 2.2 KB
- scripts/packages/implicitjs/package.json 1.6 KB
- scripts/packages/implicitjs/README.md 6.0 KB
- scripts/packages/implicitjs/scripts/export.mjs 4.1 KB runs code
- scripts/packages/implicitjs/scripts/run-tests.mjs 1.6 KB runs code
- scripts/packages/implicitjs/scripts/snapshot-runtime/render.html 635 B
- scripts/packages/implicitjs/scripts/snapshot.mjs 33 KB runs code
- scripts/packages/implicitjs/scripts/snapshot.test.mjs 8.5 KB runs code
- scripts/packages/implicitjs/scripts/verify-implicit-cad-exports.mjs 9.8 KB runs code
- scripts/packages/implicitjs/src/browser.js 611 B runs code
- scripts/packages/implicitjs/src/browser.test.js 974 B runs code
- scripts/packages/implicitjs/src/common/camera.js 11 KB runs code
- scripts/packages/implicitjs/src/common/implicitHeadlessRenderEntry.js 14 KB runs code
- scripts/packages/implicitjs/src/common/parameters.js 5.0 KB runs code
- scripts/packages/implicitjs/src/common/renderOptions.js 1.0 KB runs code
- scripts/packages/implicitjs/src/common/themeSettings.js 51 KB runs code
- scripts/packages/implicitjs/src/index.js 769 B runs code
- scripts/packages/implicitjs/src/index.test.js 525 B runs code
- scripts/packages/implicitjs/src/lib/implicitCad/animation.js 3.0 KB runs code
- scripts/packages/implicitjs/src/lib/implicitCad/export.js 3.6 KB runs code
- scripts/packages/implicitjs/src/lib/implicitCad/export.test.js 4.6 KB runs code
- scripts/packages/implicitjs/src/lib/implicitCad/exporters.js 19 KB runs code
- scripts/packages/implicitjs/src/lib/implicitCad/exportModel.js 8.6 KB runs code
- scripts/packages/implicitjs/src/lib/implicitCad/graphicsSettings.js 2.5 KB runs code
- scripts/packages/implicitjs/src/lib/implicitCad/loader.js 3.0 KB runs code
- scripts/packages/implicitjs/src/lib/implicitCad/loader.test.js 1.1 KB runs code
- scripts/packages/implicitjs/src/lib/implicitCad/mesh.js 8.4 KB runs code
- scripts/packages/implicitjs/src/lib/implicitCad/mesh.test.js 1.8 KB runs code
- scripts/packages/implicitjs/src/lib/implicitCad/meshQuality.js 8.3 KB runs code
- scripts/packages/implicitjs/src/lib/implicitCad/meshQuality.test.js 1.4 KB runs code
- scripts/packages/implicitjs/src/lib/implicitCad/model.js 20 KB runs code
- scripts/packages/implicitjs/src/lib/implicitCad/model.test.js 5.1 KB runs code
- scripts/packages/implicitjs/src/lib/implicitCad/render.js 71 KB runs code
- scripts/packages/implicitjs/src/lib/implicitCad/render.test.js 11 KB runs code
- scripts/packages/implicitjs/src/lib/implicitCad/schema.js 351 B runs code
- scripts/packages/implicitjs/src/lib/implicitCad/sdfEvaluator.js 39 KB runs code
- scripts/packages/implicitjs/src/lib/implicitCad/snapshot.js 2.4 KB runs code
- scripts/packages/implicitjs/src/lib/implicitCad/snapshot.test.js 824 B runs code
- scripts/packages/implicitjs/src/lib/viewer/stageTheme.js 364 B runs code
- scripts/packages/implicitjs/src/lib/viewer/surfaceMaterials.js 2.7 KB runs code
- scripts/snapshot.mjs 772 B 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.
- 3d ago First seen · 175 lines · 38 tokens per session scan A d299bffd7757
cad-implicit-skill is a skill published in the GitHub repository darellchua2/opencode-config-template (6 stars, last pushed 2d ago), licensed Apache-2.0. It adds 38 tokens to every session and 2,483 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. It is 86% identical to implicit-cad, differing in 64 lines, and is treated as a copy.
Other skills, from other repositories
use-agent-browser-for-airi
Test AIRI display-model imports with agent-browser across stage-tamagotchi Electron, stage-web, and stage-pocket mobile web layouts. Use when uploading and verifying contributor-supplied Live2D ZIP, VRM, or MMD ZIP/PMX/PMD files through AIRI's model selector, including onboarding bypass, format-specific import…
opencli-sitemap-author
Use when creating or maintaining OpenCLI site sitemaps: agent-facing navigation, page-state, action, workflow, API-reference, pitfall, and fallback knowledge for a website. Use after browser exploration discovers durable site context, when a sitemap is stale, or when promoting local site knowledge into the repo.
interactive-login
How to complete browser/interactive logins (aws / gh / glab / gcloud). The platform backgrounds the login poller so it survives the human's browser round-trip — and when that does NOT work.
pinchtab-mcp
Use this skill when a task requires browser automation through PinchTab's MCP server connected to a remote browser instance. Covers navigation, element interaction, data extraction, form filling, multi-step flows, and session management via MCP tools.
google-safe-browsing
Prevent and fix Google Safe Browsing "Dangerous site" flags. Use when launching a public web app, buying/picking a domain, building a login or signup page, or when any site shows a red "Dangerous site" / "Deceptive site" warning in Chrome, Brave, Safari, Firefox, or Edge. Triggers on "dangerous site", "deceptive…
web-browser
Automate and interact with web pages through Chrome or Chromium using the Chrome DevTools Protocol (CDP): navigate, click, fill forms, inspect content, take screenshots, and debug console or network activity. Use when an agent needs a real browser. Prefer headless Chrome unless visible browser interaction is required.