eyes-peeled AGENTS.md

eyes-peeled AGENTS.md is an instructions file for Codex, OpenCode from LoserLab/eyes-peeled. It costs 310 tokens per session, scanned A, original, MIT.

A color-accessibility checker for WCAG, the web standard for making content usable by people with disabilities. It checks contrast between colors and suggests accessible alternatives.

In plain words
What is it for?
Use it to check color pairs, audit a palette, compare AA and AAA compliance, or generate alternatives for failing colors.
Why use it?
It helps find text and interface colors that are difficult to read and provides replacements that meet accessibility targets.

Instructions file for CodexOpenCode

Written for Codex and OpenCode: the file is AGENTS.md.

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/eyes-peeled/agents-md
Clone the repo
git clone --depth 1 https://github.com/LoserLab/eyes-peeled

Made for: Codex, OpenCode.

Wrote 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.

agentmods badge for eyes-peeled AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/loserlab/eyes-peeled/agents-md.svg)](https://agentmods.dev/instructions/loserlab/eyes-peeled/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/loserlab/eyes-peeled/agents-md"><img src="https://agentmods.dev/badge/instructions/loserlab/eyes-peeled/agents-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 310 This file is loaded in full into every session.
When invoked 310 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 5.1 $0.00310 $0.00310
Opus 5 $0.00155 $0.00155
Sonnet 5 $0.00062 $0.00062
Haiku 4.5 $0.00031 $0.00031

Measured 6d ago against content hash 85a7da78df5e, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

eyes-peeled 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 6d 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.

AGENTS.md · 36 lines

What it actually says

Eyes Peeled

WCAG contrast and accessibility validator for Claude Skills. Validates color accessibility and generates compliant alternatives.

When to suggest this skill

  • User asks to check color contrast or WCAG compliance
  • User has a color palette and wants to verify accessibility
  • User gets feedback about failing contrast ratios
  • User needs accessible alternatives for brand colors
  • User is using Hexed output and wants to validate before building components
  • User mentions "WCAG", "contrast ratio", "accessibility", "color compliance"

What it produces

  • WCAG 2.1 compliance check (AA/AAA for normal text, large text, UI components)
  • Exact contrast ratios for any color pair
  • Fix suggestions with 3 strategies (darken fg, lighten bg, balanced)
  • Full palette audit matrix (all foreground/background combinations)
  • Accessible color variants preserving design intent
  • Delta E scores showing perceptual color shift

Key files

  • SKILL.md - Full skill instructions with implementation patterns
  • contrast_checker.py - Core WCAG validation logic
  • fix_generator.py - Accessible color alternative generation
  • test_eyes_peeled.py - Test script

Suite context

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

Eyes Peeled serves as the quality gate between color extraction and component generation.

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. 6d ago First seen · 36 lines · 310 tokens per session scan A 85a7da78df5e

Subscribe to this mod's changes

eyes-peeled AGENTS.md is an instructions file published in the GitHub repository LoserLab/eyes-peeled (5 stars, last pushed 5mo ago), licensed MIT. It adds 310 tokens to every session, about $0.0015 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.