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 pedroiff0/awesome-skills --skill markdown-static-site-sourcegit clone --depth 1 https://github.com/pedroiff0/awesome-skillsWrote 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/pedroiff0/awesome-skills/markdown-static-site-source)<a href="https://agentmods.dev/skills/pedroiff0/awesome-skills/markdown-static-site-source"><img src="https://agentmods.dev/badge/skills/pedroiff0/awesome-skills/markdown-static-site-source.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 | $0.00075 | $0.01017 |
| Opus 5 | $0.00037 | $0.00508 |
| Sonnet 5 | $0.00015 | $0.00203 |
| Haiku 4.5 | $0.00007 | $0.00102 |
Grade A, and why
markdown-static-site-source 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 4d 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 — 45 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Markdown as the source of truth for a JS-data-driven static site
When to use
- A static site (plain HTML/CSS/JS, no build framework) renders content from a data object in a JS file, e.g.
window.PORTFOLIO_DATA = {...}consumed by a render script (main.js) that builds the DOM. - The user wants to edit content in Markdown / Obsidian and have the site update, WITHOUT touching the HTML/template/CSS.
- The render must stay EXACTLY the same (pixel/semantics identical to today).
Core idea
Find the "data seam": the single JS object the render engine reads. Make a Markdown file with YAML frontmatter the SOURCE OF TRUTH. Write a tiny generator that emits that same JS object. The render engine never changes → output is identical by construction. Verify the emitted object is semantically equal to the original, NOT byte-equal (formatting differs, meaning must not).
Steps
- Locate the data object. Grep for
window.<X> =/const PORTFOLIO_DATA. Confirm what consumes it (e.g.main.jsreadswindow.Xand builds DOM). - Snapshot the original data file to
*.orig— this is your verification baseline. - (Optional, one-time)
seed.js: load the original JS (shimwindow/module.exports), dump the parsed object to a YAML-frontmatter MD. Freezes today's content as the source. build.py: read the MD, emit valid JS reconstructing the SAME object:- Serialize with a real JS-literal emitter (objects/arrays as
{}/[], strings double-quoted with\"and\nescapes). Do NOT emit YAML — the browser must evaluate it. - Preserve structure exactly: same keys, same nesting, same field order where the consumer relies on it.
- Resolve constants: if the original referenced variables inside the data (e.g.
"https://orcid.org/" + ORCID), inline the values so the generated object equals the original at runtime. - For i18n, mirror the EXACT nesting of the original (e.g. bolsas may nest
i18n.en = {title,kind,desc}per language). Match it; don't transpose unless you also change the consumer.
- Serialize with a real JS-literal emitter (objects/arrays as
verify.js(Node): load BOTH the generated file and*.origvianew Function('window', src + 'return window.X'), then deep-equal the objects. Exit 1 on diff. This is the real test — a bytediffwill always show false positives.- Pre-commit hook: run
build.pysogit commitalways recompiles;git addthe generated file. - User workflow: edit
src/<site>.mdin Obsidian →python3 tools/build.py→git add -A && git commit && git push.
What ships with it
3 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.
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.
- 4d ago First seen · 45 lines · 75 tokens per session scan A 006d9f7ecb45
markdown-static-site-source is a skill published in the GitHub repository pedroiff0/awesome-skills (1 stars, last pushed yesterday), licensed MIT. It adds 75 tokens to every session and 1,017 once invoked, about $0.0004 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 2026-09-03.
Other skills, from other repositories
hermes-desktop-plugins
Write plugins for the Hermes desktop app: statusbar items, layout panes, command-palette commands, keybinds, routes, and themes. A plugin is a single plain-JavaScript ESM file the app loads at runtime — no build step, no repo changes. A plugin can also talk to its own Python backend namespace (ctx.rest/ctx.socket →…
mnemosyne-maintenance
Use when: upgrading Mnemosyne, diagnosing slow/hung consolidation (mnemosynesleep), fixing missing embeddings, or troubleshooting import/version mismatches.
plugin-first-web-dashboard
Build remote dashboards as plugins in MCP-first services.
pebble-protocol-ui
Component catalogue for Pebble pebblesend type "ui" blocks — OpenUI Lang syntax, components, the action model (buttons, forms, $state), and what Pebble does NOT support. View when building an interactive UI block.
receiving-webhooks
General guidelines for building a robust webhook receiver/handler: verifying signatures, raw-body access, replay protection, async processing, retries and endpoint auto-disabling. Use whenever you write, review, or debug a handler that consumes incoming webhooks from any provider.
agile-web-builder-agent
A Web front-end planning helper that turns product handover materials into a project structure, suggested page files, components, screen states and a first coding task list.