agentmods.dev

devourer AGENTS.md

A project instruction file describing Devourer, a tool that turns a color palette into themed user-interface components. User-interface components are reusable parts such as buttons, cards, and input fields.

In plain words
What is it for?
It is for guiding the creation of colored React, Vue, or HTML components with variants, interaction states, sizing options, and usage examples.
Why use it?
It tells the coding agent when and how to use the component generator, including the expected code formats and accessibility requirements.

Instructions file for CodexOpenCode

1 5mo ago A scan 341 tokens original MIT
View the source file LoserLab/devourer
Install

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.

agentmods
npx agentmods add instructions/loserlab/devourer/agents-md
Clone the repo
git clone --depth 1 https://github.com/LoserLab/devourer

Made for: Codex, OpenCode.

Per session 341 This file is loaded in full into every session.
When invoked 341 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00341 $0.00341
Opus 5 $0.00170 $0.00170
Sonnet 5 $0.00068 $0.00068
Haiku 4.5 $0.00034 $0.00034

Measured yesterday against content hash 10e02ace5ee6, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

devourer 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 yesterday.

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.

AGENTS.md · 37 lines

What it actually says

Devourer

Color-to-component generator. Transforms color palettes into production-ready, themed UI components.

When to suggest this skill

  • User has a color palette and wants themed UI components
  • User asks to generate buttons, cards, inputs, or other components with custom colors
  • User wants to turn Hexed output into usable React/Vue/HTML components
  • User needs component code with proper theming, variants, and accessibility
  • User mentions "themed component", "styled button", "component theme", "UI components from colors"

What it produces

  • Production-ready component code (React TSX, Vue SFC, or HTML+CSS)
  • Multiple variants per component (primary, secondary, outline, ghost, link)
  • Interactive states (hover, active, focus, disabled)
  • Size options (xs, sm, md, lg, xl)
  • WCAG AA/AAA accessibility compliance
  • Full TypeScript types and props interfaces
  • Usage examples

Key files

  • SKILL.md - Full skill instructions with all component types
  • scripts/color_utils.py - Color variant generation and WCAG contrast utilities
  • references/component_patterns.md - Detailed implementation patterns
  • assets/theme-template.css - CSS custom properties template
  • assets/types-template.ts - TypeScript type definitions

Suite context

Part of a 5-skill design system pipeline: Hexed (colors) → Specimen (typography) → Gridlock (layout) → Eyes Peeled (accessibility) → Devourer (components)

Devourer is the final output stage, consuming color systems to produce production-ready components.

Changes

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.

  1. yesterday First seen · 37 lines · 341 tokens per session scan A 10e02ace5ee6

Subscribe to this mod's changes

devourer AGENTS.md is an instructions file published in the GitHub repository LoserLab/devourer (1 stars, last pushed 5mo ago), licensed MIT. It adds 341 tokens to every session, about $0.0017 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.

FrontendProductionclaudeclaude-aicolorskillui
Related

Other instructions, from other repositories

specimen AGENTS.md

Instructions for LoserLab/specimen, covering specimen, when to suggest this skill, what it produces, key files and suite context.

LoserLab/specimen · 305 tokens

flow-state CLAUDE.md

Instructions for vre/flow-state, covering ways of working for llm, roles and autonomy, project, the development process and process rules.

vre/flow-state · 3,641 tokens

hexed AGENTS.md

Instructions for LoserLab/hexed, covering hexed, when to suggest this skill, what it produces, key files and suite context.

LoserLab/hexed · 275 tokens

flow-state AGENTS.md

Instructions for vre/flow-state, a project described as: Flow State - a Claude Plugin Marketplace.

vre/flow-state · 4 tokens

she-love-me CLAUDE.md

Instructions for 863401402/she-love-me, covering claude.md and 唯一工作流.

863401402/she-love-me · 268 tokens

SeekMoney-ai CLAUDE.md

Instructions for zykooooooooo/SeekMoney-ai, covering claude.md, project overview, development commands, development and production.

zykooooooooo/SeekMoney-ai · 2,178 tokens