SurfSense is an open-source desktop application that uses an AI agent to research, transform, and edit documents while keeping their index on the user's machine. It is intended for people working with documents they cannot upload, with a choice of local or remote models and no account required.
Borrowing it
Nothing to install: this file belongs to MODSetter/SurfSense. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/MODSetter/SurfSense/main/.agents/skills/frontend-workflow/color/SKILL.mdgit clone --depth 1 https://github.com/MODSetter/SurfSenseWrote 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/modsetter/surfsense/color)<a href="https://agentmods.dev/skills/modsetter/surfsense/color"><img src="https://agentmods.dev/badge/skills/modsetter/surfsense/color/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/modsetter/surfsense/color"><img src="https://agentmods.dev/badge/skills/modsetter/surfsense/color.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 | $0.00000 | $0.00925 |
| Opus 5.5 | $0.00000 | $0.00370 |
| Sonnet 5.5 | $0.00000 | $0.00185 |
| Haiku 4.5 | $0.00000 | $0.00093 |
Grade A, and why
color 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 — 87 lines — stays where its author put it; the contents beside it link to each section on GitHub.
name: color-system description: Applies and reviews SurfSense's canonical light and dark color palette, semantic design tokens, typography, charts, borders, shadows, and theme mappings. Use when creating or changing frontend colors, themes, component styling, data visualizations, or design tokens.
SurfSense Color System
Use PALETTE.css as the canonical palette contract. Preserve its token names and values unless the user explicitly requests a palette change.
Principles
- Use semantic tokens such as
background,foreground,primary,muted,accent,destructive,border, and their foreground pairs. Do not use raw hex values in components. - Use the matching foreground token for text and icons placed on a semantic
surface:
primary-foregroundonprimary,card-foregroundoncard, and so on. - Use
chart-1throughchart-5for data series. Do not repurpose chart colors as component state colors. - Use
ringfor focus indicators andborderorinputfor boundaries. Never remove a visible keyboard focus indicator. - Use
muted-foregroundonly for secondary text. Do not use it for small or essential text unless its contrast passes WCAG. - Use
destructiveonly for destructive actions, errors, or dangerous states. Do not use chart colors to communicate errors. - Support both
:rootand.dark; never add a light-only semantic token. - Prefer existing semantic tokens over creating new aliases. Add a token only when it represents a reusable semantic role that the palette does not cover.
Workflow
- Locate the active global CSS file from the target app's
components.json; this repository contains more than one frontend. - Compare the active theme with PALETTE.css. Do not overwrite unrelated CSS, animation, layout, or framework directives.
- Apply palette values at the global token layer, not inside individual components.
- In components, use the project's semantic utility classes or CSS variables,
for example
bg-background text-foreground,bg-card text-card-foreground, andborder-border. - Check affected foreground/background pairs in both themes. WCAG targets: 4.5:1 for normal text, 3:1 for large text and meaningful UI boundaries.
- Verify focus, hover, active, selected, disabled, destructive, chart, and sidebar states when affected.
What ships with it
1 file 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 · 87 lines · 0 tokens per session scan A ef7a1704a338
color is a skill published in the GitHub repository MODSetter/SurfSense (16,789 stars, last pushed today), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 925 tokens. 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 2026-09-19.
color compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| colorMODSetter/SurfSense | Skill | 17k | today | Apache-2.0 | A | 0 | Claude Code, Codex |
| agent-orchestration-multi-agent-optimizeranbot-ai/awesome-skills | Skill | 8 | yesterday | none | A | 38 | Claude Code, Codex |
| ai-pipeline-orchestrationranbot-ai/awesome-skills | Skill | 8 | yesterday | none | A | 39 | Claude Code, Codex |
| first-readerShubhamsaboo/awesome-llm-apps | Skill | 144k | yesterday | Apache-2.0 | A | 174 | Claude Code, Codex |
| mcp-apps-builderShubhamsaboo/awesome-llm-apps | Skill | 144k | yesterday | Apache-2.0 | A | 139 | Claude Code, Codex |
| project-graveyardShubhamsaboo/awesome-llm-apps | Skill | 144k | yesterday | Apache-2.0 | A | 127 | Claude Code, Codex |
| commit-archaeologistShubhamsaboo/awesome-llm-apps | Skill | 144k | yesterday | Apache-2.0 | A | 82 | Claude Code, Codex |