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-aaa-graphics-buildergit 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-aaa-graphics-builder)<a href="https://agentmods.dev/skills/valkor-ai/loom/threejs-aaa-graphics-builder"><img src="https://agentmods.dev/badge/skills/valkor-ai/loom/threejs-aaa-graphics-builder/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-aaa-graphics-builder"><img src="https://agentmods.dev/badge/skills/valkor-ai/loom/threejs-aaa-graphics-builder.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 | $0.00091 | $0.00952 |
| Opus 5.5 | $0.00036 | $0.00381 |
| Sonnet 5.5 | $0.00018 | $0.00190 |
| Haiku 4.5 | $0.00009 | $0.00095 |
Grade A, and why
threejs-aaa-graphics-builder 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 — 50 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Three.js AAA Graphics Builder
Own the production graphics pass: turn basic screenshots into authored, high-density, performance-aware visuals.
References
| File | Read it when |
|---|---|
references/visual-scorecard.md |
scoring visuals or making any premium/AAA/showcase claim |
references/authoring-recipes.md |
building hero, obstacle, reward, world-kit, or prop models; changing lighting, tone mapping, shadows, fog, post, or graphics architecture |
references/technical-art.md |
render budgets, material kits, VFX systems, instancing/LOD, imported asset cleanup, anything that could affect browser performance |
references/shader-cookbook.md |
custom shaders, onBeforeCompile, skies, or post-processing; use recipes as tested starting points and verify them against the project's Three.js version |
For a broad "still looks basic" or premium pass, read all four before implementing. A narrow graphics edit loads only its relevant references and checks; the requested style and scope override recipe defaults.
Core rule
Glow does not make primitives look AAA. Build authored forms first, then materials, then lighting, then effects — in that order.
Workflow
- Capture or inspect active-play screenshots on the target viewports when a playable scene exists.
- For an existing game, score the affected views and pick the weakest surfaces. For a new game, establish art direction, camera scale, material roles, and the hero target first; do not invent a before screenshot.
- Add the graphics architecture the game is missing: material library, procedural textures and decals, model factories, world prop kit, VFX system, render pipeline, diagnostics.
- Choose a source per high-value surface: procedural Three.js, a
threejs-image-generatorreference or texture, athreejs-3d-generatormodel, or an image-to-3D hybrid chain. Run the credential probe when external generation is in scope. Inspect the concept/model before dependent generation or rigging. Finish one representative playable scene with actual assets and feedback before expanding the content kit. - Upgrade every weak visible surface, not only the hero: hazards, rewards, ground and track, foreground props, background layers, telegraphs, material variation, state VFX.
- Add lighting, tone mapping, and render polish once authored forms exist.
- Add event-driven VFX tied to gameplay state.
- Re-score against the calibration anchors, citing the inspector's measured metrics. Keep going until every premium category is at least 2, or name the exact blocker.
What ships with it
8 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.
- agents/openai.yaml 268 B
- assets/scorecard-anchors/scene-1.jpg 30 KB
- assets/scorecard-anchors/scene-2.jpg 61 KB
- assets/scorecard-anchors/scene-3.jpg 66 KB
- references/authoring-recipes.md 11 KB
- references/shader-cookbook.md 16 KB
- references/technical-art.md 5.3 KB
- references/visual-scorecard.md 5.8 KB
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 · 50 lines · 91 tokens per session scan A 811c5890ba6a
threejs-aaa-graphics-builder is a skill published in the GitHub repository valkor-ai/loom (1,251 stars, last pushed 3d ago), licensed Apache-2.0. It adds 91 tokens to every session and 952 once invoked, about $0.0004 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
playtest-report
Structured playtest report template, or turn existing playtest notes into structured feedback.
godot-signals-groups
Build event-driven, decoupled Godot 4.7 gameplay with signals and node groups: declare and emit custom signals, connect with Callables (incl. bind/one-shot), and broadcast to many nodes via groups and callgroup. Use when wiring node communication in a Godot project, replacing tight references with signals…
motion
Reconstruct a skeleton from calibrated mesh projections and sequential VLM joint annotations, then fit joints and skin weights. Generate motion from joint-position trajectories, rhythm and contact constraints through IK; refine bone orientation against the action, then export, retarget and validate on the target mesh.
unity-addressables
Manage Addressables groups, entries, profiles and content builds (com.unity.addressables, reflection-based).
unity-manual-component
Manually add, configure, reorder, and copy components on GameObjects using Unity Editor UI. For one-off Inspector workflows that do not need REST automation.
threejs-exposure-color-grading
Build a measured exposure and grading path in Three.js. Use for a 64x36 encoded luminance meter, asynchronous readback, weighted log-average exposure, asymmetric adaptation, single tone-map ownership, and a generated 32-cube post-tone-map LUT.