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 linegel/threejs-complete-set-of-skill --skill threejs-debugginggit 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/skills/linegel/threejs-complete-set-of-skill/threejs-debugging)<a href="https://agentmods.dev/skills/linegel/threejs-complete-set-of-skill/threejs-debugging"><img src="https://agentmods.dev/badge/skills/linegel/threejs-complete-set-of-skill/threejs-debugging/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/linegel/threejs-complete-set-of-skill/threejs-debugging"><img src="https://agentmods.dev/badge/skills/linegel/threejs-complete-set-of-skill/threejs-debugging.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 | $0.00061 | $0.01324 |
| Opus 5 | $0.00030 | $0.00662 |
| Sonnet 5 | $0.00012 | $0.00265 |
| Haiku 4.5 | $0.00006 | $0.00132 |
Grade A, and why
threejs-debugging 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 8d 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 — 139 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Three.js Debugging
Reproduce first. Treat installed source and official history as evidence, not as
background trivia. A domain skill defines the intended mechanism;
$threejs-visual-validation supplies formal image, timing, resource, or
regression proof when the diagnosis needs it.
Keep one case record with the symptom, expected behavior, exact environment, minimal reproduction, first failed contract, local evidence, upstream candidates, constant version matrix, conclusion, action, and limits. Record unknown values as unknown.
1. Reproduce the exact environment
Record every environment fact that can affect the failure: resolved package
version, runtime THREE.REVISION, lockfile resolution, import entrypoints,
browser/OS, seed, asset revisions, and exact command or interaction. For a
rendering or backend claim, also record renderer class, initialized backend,
GPU, and relevant capabilities. Build the smallest deterministic reproduction
that still fails.
A conclusion about the canonical WebGPU path requires an initialized
WebGPURenderer with renderer.backend.isWebGPUBackend === true. Otherwise
record that claim's blocker; reach $threejs-compatibility-fallbacks only when
the user explicitly requests that branch. Do not impose a renderer or backend
gate on a non-rendering API, export, asset, or version conclusion.
This step is complete when the relevant environment truth is recorded, the reproduction fails repeatedly under that environment, and another run can distinguish reproduced from not reproduced.
2. Name the violated contract and first failure
Separate API semantics, numerical invariants, render-state invariants, resource transitions, and visual expectations. Identify the earliest failing assertion, frame, pass, draw, dispatch, resource transition, or diagnostic—not merely the final symptom.
This step is complete when one observable boundary divides the last known-good state from the first bad state.
3. Minimize without replacing the mechanism
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.
- 8d ago First seen · 139 lines · 61 tokens per session scan A 6581e49fdb2c
threejs-debugging is a skill published in the GitHub repository linegel/threejs-complete-set-of-skill (6 stars, last pushed 1mo ago), licensed ISC. It adds 61 tokens to every session and 1,324 once invoked, about $0.0003 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 2026-08-31.
Other skills, from other repositories
systematic-debugging
4-phase root cause debugging: understand bugs before fixing.
triage-issues
Triage GitHub issues in the googleapis/mcp-toolbox repo: propose the correct labels (type / priority / product / status), check for duplicates, verify a bug has enough info to act on, and draft a triage comment. Use whenever a maintainer asks you to triage, label, categorize, prioritize, or "look at" an issue (or a…
copilotkit-debug
Use when diagnosing CopilotKit issues -- runtime connectivity failures, agent not responding, streaming errors, tool execution problems, transcription failures, version mismatches, and AG-UI event tracing.
agent-merge-conflict-arbiter
Neutral arbiter for merge conflicts between two agents.
python-debugpy
Debug Python: pdb REPL + debugpy remote (DAP).
sglang-diffusion-benchmark-profile
Use when benchmarking denoise latency or profiling a diffusion bottleneck in SGLang.