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-exposure-color-gradinggit 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-exposure-color-grading)<a href="https://agentmods.dev/skills/linegel/threejs-complete-set-of-skill/threejs-exposure-color-grading"><img src="https://agentmods.dev/badge/skills/linegel/threejs-complete-set-of-skill/threejs-exposure-color-grading/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-exposure-color-grading"><img src="https://agentmods.dev/badge/skills/linegel/threejs-complete-set-of-skill/threejs-exposure-color-grading.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 | $0.00050 | $0.01609 |
| Opus 5 | $0.00025 | $0.00805 |
| Sonnet 5 | $0.00010 | $0.00322 |
| Haiku 4.5 | $0.00005 | $0.00161 |
Grade A, and why
threejs-exposure-color-grading 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 12d 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 — 170 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Exposure And Color Grading
Keep the photographed signal scene-linear until the final image chain. One declared owner controls each exposure group, tone map, and output conversion.
1. Lock the color contract
Name the scene-linear working primaries, radiance scale, alpha convention, and every producer that enters the photographed signal. Convert irradiance through the material/lighting model before metering radiance. Apply one shared physical or perceptual radiance scale to lights, environment, atmosphere, emissive materials, bloom sources, and optical effects.
Partition targets or views into exposure-control groups. A group may share GPU state only when its radiance basis, exposure policy, and reset history are identical; an automatic group also requires the same meter mask, key, and sample schedule. Assign exactly one exposure owner, one tone-map owner, and one output-conversion owner per group.
Complete when: every photographed input has one basis and scale, and every group names its members, exposure/tone-map/output owners, and state-sharing policy.
2. Choose the cheapest meter that meets the image requirement
Choose in dependency order:
- fixed EV for a controlled or calibrated view;
- a stratified grid or tile sampler for ordinary global auto exposure;
- exact full-pixel hierarchical reduction when every pixel or exact mask must contribute;
- a log-luminance pyramid only when another feature consumes its levels or spatial statistics;
- a histogram only when percentile clipping fixes a demonstrated outlier or bimodal-lighting failure.
Tap resolved, pre-bloom HDR by default. This keeps temporal noise out of the meter and avoids bloom/exposure feedback. A different tap is an authored image policy with a regression fixture.
Read the color-pipeline reference when implementing sampled, exact, pyramid, or histogram metering; it contains the weighted-log equations, traffic model, and small-emitter failure tests.
What ships with it
4 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.
- 12d ago First seen · 170 lines · 50 tokens per session scan A bd0a8feafc35
threejs-exposure-color-grading is a skill published in the GitHub repository linegel/threejs-complete-set-of-skill (6 stars, last pushed 1mo ago), licensed ISC. It adds 50 tokens to every session and 1,609 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
subagent-driven-development
Execute plans via delegatetask subagents (2-stage review).
duckduckgo-search
Free keyless web, news, and image search via ddgs.
mcporter
List, auth, and call MCP servers/tools from the terminal.
article-writing
Write articles, guides, blog posts, tutorials, newsletter issues, and other long-form content in a distinctive voice derived from supplied examples or brand guidance. Use when the user wants polished written content longer than a paragraph, especially when voice consistency, structure, and credibility matter.
mem0-oss-to-platform
Plan and then execute a migration of a project from the mem0 open-source / self-hosted SDK (the local Memory class) to the mem0 Platform / hosted / managed SDK (the MemoryClient class). Use this whenever a developer wants to move, switch, or migrate their mem0 usage off OSS/self-hosted to the hosted API — e.g.…
deploy-docker-compose
Run the Omnigent server as a Docker compose stack (server + Postgres) on any Docker host — your laptop, a VPS, EC2 by hand, or as the base layer of any container-platform deploy. Invoke when the user wants to build the image, bring up the compose stack, debug the stack on a host they already have, or extend the stack…