Borrowing it
Nothing to install: this file belongs to linegel/threejs-complete-set-of-skill. 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/linegel/threejs-complete-set-of-skill/main/AGENTS.mdgit clone --depth 1 https://github.com/linegel/threejs-complete-set-of-skillWrote 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/instructions/linegel/threejs-complete-set-of-skill/agents-md)<a href="https://agentmods.dev/instructions/linegel/threejs-complete-set-of-skill/agents-md"><img src="https://agentmods.dev/badge/instructions/linegel/threejs-complete-set-of-skill/agents-md/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/instructions/linegel/threejs-complete-set-of-skill/agents-md"><img src="https://agentmods.dev/badge/instructions/linegel/threejs-complete-set-of-skill/agents-md.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 | $0.01461 | $0.01461 |
| Opus 5 | $0.00731 | $0.00731 |
| Sonnet 5 | $0.00292 | $0.00292 |
| Haiku 4.5 | $0.00146 | $0.00146 |
Grade C, and why
threejs-complete-set-of-skill AGENTS.md scanned grade C 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 10d 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.
Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
- Never execute `rm -rf`, `rm -fr`, or an equivalent recursive forced-delete How it starts
The opening of the file, as written. The whole thing — 134 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Three.js WebGPU/TSL skill repository
This checkout is the authoritative local source for the installable skills under
skills/, plus their repository examples, validation harnesses, and generated
documentation.
Codex state and workflow
- Do not read, write, retrieve, summarize, or rely on Codex memory files, databases, tools, or features on this machine.
- Repo-local Superpowers exposure under
.agents/skills/superpowersis allowed when a documented repository workflow calls for it. Do not assume a global Superpowers installation path.
Destructive deletion safety
- Never execute
rm -rf,rm -fr, or an equivalent recursive forced-delete command, including for generated, cached, temporary, or sandboxed paths. - Before any other command that invokes
rm, first obtain two independent reviews: one arguing that the exact deletion is necessary and safe, and one challenging it with non-destructive alternatives. - Report the conclusion and obtain the user's explicit approval for the exact command before executing it. Prior command approvals and inferred consent do not satisfy this requirement.
- If the required independent reviews are unavailable, do not execute
rm.
Skill routing
- When a task names or matches a
threejs-*skill, read that repo-localskills/<skill>/SKILL.mdbefore acting. The copy in this repository wins over a global copy. - When a task spans multiple rendering systems, start with
skills/threejs-choose-skills/SKILL.mdand load only the smallest set it selects. - Follow references and scripts named by the selected skill. Do not load every skill or demo as general context.
- Checked-in source, examples, tests, manifests, and skill instructions are the source of truth. Treat older notes and generated docs as evidence only when they still match current source.
Technical standard
Write for experienced graphics, computer-science, and physics readers. Be concise and falsifiable: distinguish measured fact, source-backed mechanism, inference, and recommendation. Include units, coordinate/frame conventions, resource costs, invalidation rules, and failure conditions when they affect the result. Avoid motivational filler, credentials, emotional pressure, or vague demands for "maximum quality."
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.
- 10d ago First seen · 134 lines · 1,461 tokens per session scan C 3c2acdf900f9
threejs-complete-set-of-skill AGENTS.md is an instructions file published in the GitHub repository linegel/threejs-complete-set-of-skill (6 stars, last pushed 1mo ago), licensed ISC. It adds 1,461 tokens to every session, about $0.0073 per session on Opus 5. A static security scan graded it C with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other instructions, from other repositories
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.