Loom is a delivery harness that guides coding agents through defining, planning, implementing, checking, repairing, previewing, and handing off software changes. It is used with Claude Code, Codex, OpenCode, and other coding agents when work must be continued or inspected across sessions. The catalogue skills, hooks, commands, instructions, and plugin extend or operate this workflow.
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 valkor-ai/loom --skill threejs-debug-profilergit clone --depth 1 https://github.com/valkor-ai/loomWrote 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/valkor-ai/loom/threejs-debug-profiler)<a href="https://agentmods.dev/skills/valkor-ai/loom/threejs-debug-profiler"><img src="https://agentmods.dev/badge/skills/valkor-ai/loom/threejs-debug-profiler/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/valkor-ai/loom/threejs-debug-profiler"><img src="https://agentmods.dev/badge/skills/valkor-ai/loom/threejs-debug-profiler.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 | $0.00058 | $0.00515 |
| Opus 5.5 | $0.00023 | $0.00206 |
| Sonnet 5.5 | $0.00012 | $0.00103 |
| Haiku 4.5 | $0.00006 | $0.00052 |
Grade A, and why
threejs-debug-profiler 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 1mo 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 — 38 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Three.js Debug Profiler
Find root causes and optimize measured bottlenecks without breaking playability.
Follow the changed behavior's scope. Reuse the lead's existing reproduction and evidence; verify the affected path after a fix. A passing focused check only needs broader testing when shared behavior changed or an unresolved risk warrants it. Return measurements and defects to the lead for the consolidated verification pass.
Reference
references/debug-playbook.md — ordered triage for blank canvas, asset and audio loading, loop/animation/physics, input and mobile, the profiling sequence, and the __THREE_GAME_DIAGNOSTICS__ shape. Read it when debugging or profiling anything non-obvious.
Debug
- Reproduce locally with the same command and URL the user had.
- Read console, page, and network errors.
- Check canvas display size against drawing-buffer size.
- Check renderer, context, and loop ownership — more than one active loop is a common cause.
- Check camera aspect, near/far, lights, materials, fog, scene contents, transforms.
- Check asset paths, loaders, CORS, and base path.
- Check animation delta units, physics update order and fixed timestep, collider and body ownership, input listeners, pointer and touch behavior, resize, and audio context unlock when audio is involved.
- Fix the root cause in the module that owns it, then retest the exact broken path.
Profile
- Reproduce in the correct build mode — production preview when user-facing performance matters.
- Baseline the scenario: FPS and frame time, draw calls, triangles, geometries, textures, memory, bundle.
- Classify the bottleneck as CPU, GPU draw, GPU fragment, GPU vertex, memory, or network.
- Change one thing — instancing, shared resources, culling, LOD, DPR cap, cheaper shadows or post, texture discipline.
- Re-measure the same scenario and confirm visuals and playability held.
Report
Lead with the root cause or the measured bottleneck. Then files changed, baseline and post metrics, commands, screenshots, the broken path retested, and residual risks.
What ships with it
2 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.
- 1mo ago First seen · 38 lines · 58 tokens per session scan A d0f768904065
threejs-debug-profiler is a skill published in the GitHub repository valkor-ai/loom (1,251 stars, last pushed 3d ago), licensed Apache-2.0. It adds 58 tokens to every session and 515 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-09-15.
Other skills, from other repositories
minecraft-debug-mcp
Operate and debug the live Minecraft bot through its built-in MCP REPL server. Use when work requires starting the bot with pnpm dev, connecting to the local MCP endpoint, inspecting cognitive state/logs/history, injecting synthetic chat/events, or running targeted REPL code against the running brain during…
cli-anything-nsight-graphics
Windows-first CLI harness for Nsight Graphics capture, GPU Trace summary, and ngfx-replay analysis.
unity-console
Capture and query the Unity Editor console.
diagnosing-bgs-problems
A symptom-first guide for investigating crashes, frame-rate drops, stuttering, freezes, and startup failures in Bethesda Game Studios games with mods.
axiom-audit-spritekit
Use when the user wants to audit SpriteKit game code for common issues — physics bitmask issues, draw call waste, node accumulation, and action leaks.
performance-optimization
Find and fix game performance problems methodically — measure with the engine profiler first, reason about the frame-time budget, locate the CPU-vs-GPU bottleneck, then apply the right fix: object pooling, draw-call batching, fewer allocations/GC spikes, and asset budgets. Engine- neutral method that pairs with each…