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 palmier-io/palmier-skills --skill color-gradinggit clone --depth 1 https://github.com/palmier-io/palmier-skillsWrote 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/palmier-io/palmier-skills/color-grading)<a href="https://agentmods.dev/skills/palmier-io/palmier-skills/color-grading"><img src="https://agentmods.dev/badge/skills/palmier-io/palmier-skills/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/palmier-io/palmier-skills/color-grading"><img src="https://agentmods.dev/badge/skills/palmier-io/palmier-skills/color-grading.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00083 | $0.02987 |
| Opus 5 | $0.00042 | $0.01494 |
| Sonnet 5 | $0.00017 | $0.00597 |
| Haiku 4.5 | $0.00008 | $0.00299 |
Grade A, and why
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 11d 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 — 106 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Grade in the colorist's order, scopes-first — never skip to a look, since a look on top of a cast just bakes it in. One apply_color call merges onto the current grade (only the params you pass change), so build up across calls and verify with inspect_color between stages. Ranges live in the reference tables below; prose names the knob, not the number.
Workflow
- [ ] 1. inspect_color — read scopes BEFORE touching anything
- [ ] 2. Normalize — exposure + white balance to neutral
- [ ] 3. Primary — black/white points, contrast, saturation
- [ ] 4. Match — pull each shot toward the reference (if matching)
- [ ] 5. Secondary — hue curves for skin/sky/foliage
- [ ] 6. Look — wheels split-tone and/or LUT
- [ ] 7. inspect_color again — confirm scopes moved as intended
1. Read first. inspect_color(clipId). Check luma.black/luma.white (near 0/1? clipLowPct/clipHighPct flag crush/clip), balance.warmCool + balance.greenMagenta (nonzero = a cast to neutralize), zones (where the cast lives), and hueHistogram12 (orange bins 1–2 = skin, cyan/blue bins 6–8 = sky).
2. Normalize. exposure for global brightness (prefer it over gamma). temperature to correct warmCool — higher = warmer, so lower it if too warm. tint to correct greenMagenta, pushing opposite the cast. Re-inspect: both balances near 0 before moving on.
3. Primary. blacks/whites to set the points, contrast + highlights/shadows to shape roll-off, saturation for overall sat — reach for vibrance instead when you want to boost muted color without clobbering skin.
4. Match shots. Grade the hero fully, then for each other shot call inspect_color(clipId, reference: <hero>), read the returned gap and its hints (e.g. "warmer than ref → cooler temperature"), apply the nudges, and repeat until the gap is small. Close it numerically — don't eyeball it.
5. Secondary. Adjust specific hues via hueCurves.targets (each targetHue affects ~±22°): hueShift rotates, satScale mutes/pops, lumShift darkens/brightens — e.g. deepen a sky without touching skin. Per-channel redCurve/greenCurve/blueCurve are tone-selective: tame a blown sky with blueCurve: [[0,0],[0.7,0.7],[1,0.85]].
6. Look. Split-tone with the wheels (*Hue+*Amount per zone, e.g. teal/orange = shadowsHue:210,shadowsAmount:0.2 + highsHue:30,highsAmount:0.15), add a film toe via masterCurve ([[0,0.06],[1,0.95]]), or fold in a lut:{path,strength} (.cube, absolute path; copied into project storage; pass strength alone to re-blend). For named stocks, build by hand — see Film looks below.
7. Confirm. Re-inspect_color: points near 0/1 without heavy clipping, neutral balance unless intentionally toned, skin in the orange bins.
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.
- 11d ago First seen · 106 lines · 83 tokens per session scan A 0f7245c4236e
color-grading is a skill published in the GitHub repository palmier-io/palmier-skills (64 stars, last pushed 10d ago), licensed Apache-2.0. It adds 83 tokens to every session and 2,987 once invoked, about $0.0004 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 2026-08-30.
Other skills, from other repositories
webgl-holographic-foil
A self-contained WebGL2 hero: thin-film interference over a crushed-foil surface whose palette shifts with the viewing angle; move the cursor to tilt the film.
general-video
Author or edit a custom HyperFrames composition when no specialized workflow fits, or when BRIEF.md sets flow: companion. Use for longer or multi-scene pieces, brand and sizzle reels, montages, static loops, static title cards, footage remixes, and freeform builds. Use motion-graphics instead for a short unnarrated…
html-ppt-hermes-cyber-terminal
OpenDesign + BYOK: choosing and wiring your own model, hands-on — cost, quality, and the routing decision. Built as a decision-grade AI literacy deck for engineers, IT, applied-AI teams.
html-ppt-taste-brutalist
16:9 HTML deck in tactical-telemetry / CRT-terminal taste. Deactivated-CRT charcoal slides, white-phosphor monospace, hazard-red accent, scanline overlay, ASCII syntax, density over decoration. Distilled from Leonxlnx/taste-skill brutalist-skill (Tactical Telemetry mode).
chengfeng-check-updates
An environment manager for a video-editing system. It checks whether its skills and runtime—the software needed to run them—are installed and compatible.
diagnostic-stem-delivery
Audio production with diagnostic analysis, timecode parsing from documents, and verified export workflow.