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 skills/ethanyoq/skill-hub/github-readme-visualsnpx skills add EthanYoQ/Skill-hub --skill github-readme-visualsgit clone --depth 1 https://github.com/EthanYoQ/Skill-hubWrote 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/ethanyoq/skill-hub/github-readme-visuals)<a href="https://agentmods.dev/skills/ethanyoq/skill-hub/github-readme-visuals"><img src="https://agentmods.dev/badge/skills/ethanyoq/skill-hub/github-readme-visuals.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 | $0.00097 | $0.02574 |
| Opus 5 | $0.00048 | $0.01287 |
| Sonnet 5 | $0.00019 | $0.00515 |
| Haiku 4.5 | $0.00010 | $0.00257 |
Grade A, and why
github-readme-visuals 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 3d 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 — 91 lines — stays where its author put it; the contents beside it link to each section on GitHub.
GitHub README Visuals
Create a fast, trustworthy visual explanation of the product without replacing its factual README content.
Runtime Copy And Default Profile
Before production, identify the resolved Skill path. A path inside a sibling directory ending in -workspace/skill-snapshot is an evaluation baseline, not a production Skill. Do not use it to create repository assets. Resolve and load the canonical installed or source copy instead. If no canonical copy is available, stop and report that the Skill installation must be synchronized.
For any GUI desktop or web application, use the Product-proof split v1 profile unless the user explicitly requests a different direction after seeing or naming it. Read the complete profile specification and start from the bundled deterministic HTML template.
This default is intentionally screenshot-led: the left side explains the product and the right side proves it with complete, real interface captures. A request to “use github-readme-visuals”, “replace the current hero with the Skill”, or “make it consistent with the established README visual style” selects this profile and supersedes an earlier unreviewed moodboard, illustration, or concept-art proposal.
Do not silently reinterpret the default as editorial artwork, a decorative cover, or a generated scene. Pure illustration is an opt-out path that requires an explicit user request such as “use an abstract/conceptual hero” or a non-GUI product for which real interface evidence does not exist.
Workflow
- Inspect the repository before designing.
- Read the README, product notes, local instructions, existing assets, and available screenshots.
- For application repositories, prioritize real product screenshots as proof. Do not present generated UI as a real screen.
- Determine how to run or open the real application and list four to six distinct, user-relevant states to capture. The first/default screen is always the primary state unless the user names another workflow.
- Record screenshot provenance, locale, dimensions, and whether the complete application window is visible in
docs/readme-visuals/visual-manifest.jsonusing the schema in the profile specification. - Identify the user journey a first-time visitor should understand in one glance.
- Build a visual-claim ledger before writing hero copy: every product, pricing, privacy, credential, provider, and deployment claim must be supported by the README, source, or user-confirmed facts. Omit ambiguous claims instead of guessing.
What ships with it
14 files 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.
- agents/openai.yaml 334 B
- assets/product-proof-split-v1-data.example.js 1.5 KB runs code
- assets/product-proof-split-v1-manifest.example.json 1.3 KB
- assets/product-proof-split-v1.html 8.9 KB
- evals/evals.json 5.2 KB
- evals/files/readme-fixture/app/index.html 7.2 KB
- evals/files/readme-fixture/docs/images/hero-en.png 7.8 KB
- evals/files/readme-fixture/docs/images/hero-zh.png 7.8 KB
- evals/files/readme-fixture/README_zh.md 44 B
- evals/files/readme-fixture/README.md 41 B
- references/product-proof-split-v1.md 5.8 KB
- references/visual-checklist.md 5.5 KB
- scripts/tests/test_verify_readme_visuals.py 6.3 KB runs code
- scripts/verify_readme_visuals.py 15 KB runs code
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.
- 3d ago First seen · 91 lines · 97 tokens per session scan A 7328be60a831
github-readme-visuals is a skill published in the GitHub repository EthanYoQ/Skill-hub (9 stars, last pushed 5d ago), licensed MIT. It adds 97 tokens to every session and 2,574 once invoked, about $0.0005 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 skills, from other repositories
watch
File sentinel that monitors the working directory for changes and marker comments, then auto-triggers appropriate skills. Poll-based via git diff against the last scan commit. Writes intake items for batch processing and routes marker actions through /do. Use for automatic reactions to file changes; do NOT use for…
pr-watch
Local PR watcher. Monitors CI status, automatically fixes failing checks by reading failure logs and applying targeted fixes, then optionally merges when all checks pass. Local CLI analog to Claude Code's cloud auto-fix feature.
review
5-pass structured code review — correctness, security, performance, readability, consistency.
live-preview
Mid-build visual verification loop. Takes screenshots of components during construction, not just after. Catches visual regressions and invisible features before they compound. Requires Playwright or similar screenshot tool.
marshal
Meta-orchestrator that takes any direction — broad, specific, or vague — and autonomously chains skills and context into actionable work. Gathers context from codebase, docs, and memory. Only asks the user when it genuinely cannot proceed. Single-session orchestrator.
systematic-debugging
4-phase root cause analysis: observe, hypothesize, verify, fix. Enforces investigation before any code changes. Emergency stop after 2 failed fixes. Prevents shotgun debugging and fix cascades.