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/loserlab/eyes-peeled/agents-mdgit clone --depth 1 https://github.com/LoserLab/eyes-peeledWrote 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/instructions/loserlab/eyes-peeled/agents-md)<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>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 | $0.00310 | $0.00310 |
| Opus 5 | $0.00155 | $0.00155 |
| Sonnet 5 | $0.00062 | $0.00062 |
| Haiku 4.5 | $0.00031 | $0.00031 |
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.
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 patternscontrast_checker.py- Core WCAG validation logicfix_generator.py- Accessible color alternative generationtest_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.
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.
- 6d ago First seen · 36 lines · 310 tokens per session scan A 85a7da78df5e
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.
Other instructions, from other repositories
web-quality-skills CLAUDE.md
Instructions for addyosmani/web-quality-skills, covering claude.md, project summary, quick reference, available skills and key thresholds.
web-quality-skills AGENTS.md
Instructions for addyosmani/web-quality-skills, covering agents.md, project overview, live audit routing, directory structure and skill format.
design-skills CLAUDE.md
Instructions for cuellarfr/design-skills, covering claude.md, what this repo is, skill architecture, plugin packaging and the 10 skills.
SidewalkWebpage css.instructions.md
Instructions for ProjectSidewalk/SidewalkWebpage: --text- font shorthands (font: var(--text-body-regular);) — not raw --font- plus hand-picked size/weight. Flag hardcoded hex colors or hand-assembled font stacks where a token fits.
ship-it AGENTS.md
Instructions for LunkiBR/ship-it, covering agents.md, project context, repository layout, terminology and key components.
shadcn-htmx AGENTS.md
Instructions for productdevbook/shadcn-htmx, covering agent guide, hard rules, what's vendored, and when to read each, repos/htmx/ — htmx v4 source (branch: four-dev) and repos/tailwindcss/ — tailwind css v4 source (branch: main).