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 agentmods add instructions/itmeo/webgradients/agents-mdgit clone --depth 1 https://github.com/itmeo/webgradientsWhat 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 | $0.01579 | $0.01579 |
| Opus 5 | $0.00790 | $0.00790 |
| Sonnet 5 | $0.00316 | $0.00316 |
| Haiku 4.5 | $0.00158 | $0.00158 |
Grade A, and why
webgradients AGENTS.md 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 3d 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 — 102 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Guidance for AI coding agents (Claude, Cursor, Copilot, etc.) working with this repo. This is a static data repository — 180 curated gradients, no build step, no dependencies.
Files and what they're for
| File | Gradients | Use it for |
|---|---|---|
webgradients.css |
180 (complete, canonical) | Ready-to-use CSS classes. Source of truth for the full set. |
gradients.json |
180 (complete) | Structured metadata regenerated from webgradients.css: name, angle, color stops. Preferred source for programmatic use. |
gradients-parsed.json |
174 | Older structured dataset (site-internal history). Missing the same 6 entries as before (blend-mode composites); its 2 name typos (Arielles Smile, October Silenceiver) have been fixed. Prefer gradients.json for the complete set. |
Fixed: two gradients used to share the name/class Deep Blue (now resolved)
webgradients.css used to define .deep_blue{} twice — index 016 (#e0c3fc→#8ec5fc) and index
039 (#6a11cb→#2575fc) — both commented /*NNN Deep Blue*/. In CSS the later rule wins, so
.deep_blue always rendered index 039's colors; index 016's gradient was unreachable through that class
name. gradients-parsed.json originally called index 039 "Blue Velvet" — a leftover from before it
was renamed to Deep Blue in the CSS without updating this file, which is what caused it to look like a
missing/orphaned entry.
Resolved by keeping the class that was actually live (.deep_blue / index 039, so nothing that already
depended on that class name changes) and giving the previously-unreachable index 016 a new, unique
name: Lilac Sky / .lilac_sky. Applied consistently across webgradients.css, gradients.json,
and gradients-parsed.json. Blue Velvet is retired — index 039 is Deep Blue in all three files now.
Why gradients.json only had 11 entries until now
It was an abandoned 2019 prototype (see git log -- gradients.json) — the real data work happened in
gradients-parsed.json instead, which itself topped out at 174/180 because 6 gradients
(Coup de Grace, Loon Crest, Sharp Glass, Chemic Aqua, Slick Carbon, Earl Gray) use layered
background-blend-mode effects that don't reduce to a single {deg, gradient} pair, so the original
pipeline silently dropped them. gradients.json is now regenerated directly from webgradients.css
(the canonical, complete source) to close that gap:
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.
- 3d ago First seen · 102 lines · 1,579 tokens per session scan A 2658613ede9e
webgradients AGENTS.md is an instructions file published in the GitHub repository itmeo/webgradients (2,471 stars, last pushed 1mo ago), licensed MIT. It adds 1,579 tokens to every session, about $0.0079 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 instructions, from other repositories
gradio AGENTS.md
AGENTS.md instructions for gradio-app/gradio, covering agents.md, repository structure, pull request rules, code style and agentic contribution policy.
ui AGENTS.md
AGENTS.md instructions for nuxt/ui, covering agents.md, project overview, project structure, commands and cli for scaffolding.
ui-components AGENTS.md
Instructions for starc007/ui-components, covering beui v2 — agent guide, commands, layout, component catalog and components (motion category — primitives).
core AGENTS.md
Instructions for ReactUnity/core, covering release workflow, write changelog files, example, fix button hover state and package references.
claudecodeui AGENTS.md
AGENTS.md instructions for siteboon/claudecodeui, covering repository guidance, backend code and frontend code.
skelet AGENTS.md
Instructions for Selekkt/skelet, covering agents.md — developing skelet.css, what skelet is, source of truth, repo map and rules of engagement (framework dev).