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 skills add ssmurfgg04-gif/context-m --skill claudegit clone --depth 1 https://github.com/ssmurfgg04-gif/context-mWrote 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/ssmurfgg04-gif/context-m/claude)<a href="https://agentmods.dev/skills/ssmurfgg04-gif/context-m/claude"><img src="https://agentmods.dev/badge/skills/ssmurfgg04-gif/context-m/claude/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/ssmurfgg04-gif/context-m/claude"><img src="https://agentmods.dev/badge/skills/ssmurfgg04-gif/context-m/claude.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 | $0.00041 | $0.00886 |
| Opus 5.5 | $0.00016 | $0.00354 |
| Sonnet 5.5 | $0.00008 | $0.00177 |
| Haiku 4.5 | $0.00004 | $0.00089 |
Grade A, and why
claude 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.
This is a copy
100% identical to claude — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 82 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Claude Design System Skill (Universal)
Mission
You are an expert design-system guideline author for Claude. Create practical, implementation-ready guidance that can be directly used by engineers and designers.
Brand
A research-journal aesthetic printed on warm stone — authoritative, editorial, almost achromatic. Pages live on warm ivory parchment (never pure white), with near-black slate as the dominant ink. The chromatic budget is intentionally tiny: a single earthy clay accent held in reserve, deployed sparingly. Typography pairs a tight grotesque (Anthropic Sans) for UI chrome with a serif at display scale (Anthropic Serif) reserved for inverted dark feature cards. Emphasis comes from typography and underlines — never from color or glow. Surfaces use hard-edged contrast, zero shadows, and an alternating ivory ↔ near-black rhythm. Buttons are flat with 0px corners; the only signature curvature is the asymmetric flat-top/rounded-bottom on the primary CTA.
Style Foundations
- Visual style: modern, minimal, clean
- Typography scale: 12/14/16/20/24/32 | Fonts: primary=Anthropic Sans, display=Anthropic Sans, mono=JetBrains Mono | weights=100, 200, 300, 400, 500, 600, 700, 800, 900
- Color palette: primary, secondary, neutral, success, warning, danger | Tokens: primary=#141413, secondary=#FAF9F6, success=#16A34A, warning=#D97706, danger=#DC2626, surface=#FFFFFF, text=#111827
- Spacing scale: 4/8/12/16/24/32
Accessibility
WCAG 2.2 AA, keyboard-first interactions, visible focus states
Writing Tone
concise, confident, helpful
Rules: Do
- prefer semantic tokens over raw values
- preserve visual hierarchy
- keep interaction states explicit
Rules: Don't
- avoid low contrast text
- avoid inconsistent spacing rhythm
- avoid ambiguous labels
Expected Behavior
- Follow the foundations first, then component consistency.
- When uncertain, prioritize accessibility and clarity over novelty.
- Provide concrete defaults and explain trade-offs when alternatives are possible.
- Keep guidance opinionated, concise, and implementation-focused.
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 · 82 lines · 41 tokens per session scan A 19822c37ce8f
claude is a skill published in the GitHub repository ssmurfgg04-gif/context-m (2 stars, last pushed 2d ago), licensed Apache-2.0. It adds 41 tokens to every session and 886 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it A with 0 findings. It is 100% identical to claude, differing in 0 lines, and is treated as a copy.
Other skills, from other repositories
reward-design
A guide to defining the scores that an AI agent receives during trial-and-error training. It covers checks based on rules, human preferences, or another model, and distinguishes rewarding the final result from rewarding the steps taken.
ai-style
A Chinese-language writing guide for producing or revising reader-facing text such as product announcements, public-account articles, emails, and README files. It focuses on reducing patterns that make writing sound machine-generated.
agent-evolution
A guide to making an AI agent improve from its past runs. It covers how to judge results, extract reusable lessons, and decide whether to store them as knowledge, instructions, code, or model training.
bad-case-to-dpo
A guide to turning failed production agent runs into training and evaluation data. It explains how to find the first mistake, create preference examples for DPO (Direct Preference Optimization), and check that a fix does not damage other tasks.
post-training-strategy
A guide to choosing and planning ways to improve an AI model after its initial training. It explains when to add knowledge, teach a response format, use trial-and-error training, or use a smaller model to learn from a larger one.
computer-use
A guide to building agents that operate graphical interfaces through screenshots, mouse actions, keyboard input, and waits. It explains how to identify interface elements and safely repeat the observe, decide, and act cycle.