Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/evergreen-it-dev/folionpx agentmods add skills/evergreen-it-dev/folio/folio-contentWrote 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/evergreen-it-dev/folio/folio-content)<a href="https://agentmods.dev/skills/evergreen-it-dev/folio/folio-content"><img src="https://agentmods.dev/badge/skills/evergreen-it-dev/folio/folio-content/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/evergreen-it-dev/folio/folio-content"><img src="https://agentmods.dev/badge/skills/evergreen-it-dev/folio/folio-content.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 | $0.00037 | $0.02305 |
| Opus 5.5 | $0.00015 | $0.00922 |
| Sonnet 5.5 | $0.00007 | $0.00461 |
| Haiku 4.5 | $0.00004 | $0.00231 |
Grade A, and why
Folio Content 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.
How it starts
The opening of the file, as written. The whole thing — 306 lines — stays where its author put it; the contents beside it link to each section on GitHub.
How to write content for Folio
The main skill for any write of the body of a page (create_page,
update_page). Follow it every time you create or edit markdown — both when
you write a new page from scratch and when you make a pinpoint edit of an
existing one.
Write the content in the language the user writes in, unless they ask for another one. The templates below show the structure; their headings are to be written in that language too.
1. Iron rules
- The title of a page is the first line of the body,
# Title(H1). It is not a separate field: renaming a page in Folio is an edit of the H1. When you writemarkdownforcreate_page/update_page, the first non-empty line has to be an H1 with the real title — never# TODOor an empty heading. - Do not write the frontmatter (
id,slug,order,icon,cover,labels,status) by hand. The server serializes these fields itself; the body you pass to the tools is what goes after the closing---(and most often without a frontmatter block at all). If an icon or an order has to be set, that is a separate action through the UI/API, not a line in the markdown. - Nothing beyond the allowed profile. Allowed: CommonMark + GFM
(headings, lists, code, quotes, tables, strikethrough, autolinks,
task lists, footnotes) + the Folio extensions listed below. Do not invent
other constructs (there are no KaTeX formulas, no
::toc/::include/::embed/:::plugin— none of them is implemented in the engine, even if it turned up in somebody's draft before; the only working directives are::pagetreeand the inline:status[...], see §2). - No
<script>,<style>,<iframe>,style="..."or other scripted HTML constructs — the sanitizer cuts them out completely; the text inside an unknown tag can be lost altogether. Of "raw" HTML only these are deliberately allowed:<details><summary>,<mark>,<u>, the usual table tags (<table>,<colgroup>,<col>and so on) and<br>. Do not write<ins>/<u>/<mark>yourself — Folio has markdown for all of them (see "Text formatting" below).
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 · 306 lines · 37 tokens per session scan A 133af1915fd9
Folio Content is a skill published in the GitHub repository evergreen-it-dev/folio (69 stars, last pushed today), licensed MIT. It adds 37 tokens to every session and 2,305 once invoked, about $0.0001 per session on Opus 5.5. 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 2026-10-09.
Other skills, from other repositories
solomd
Read, search, edit, and version-control any folder of Markdown notes via the SoloMD MCP server. 13 tools including AutoGit per-note history, semantic search, and write-with-sandbox via an accept/reject branch. Includes 11 starter agent recipes (weekly review, todo extract, link suggester, …).
github
A writing guide for GitHub issues, pull requests, code reviews, and release notes in Zhin projects. GitHub is a service where teams track bugs, discuss changes, review code, and publish project updates.
youtube-fetcher
Retrieve YouTube transcripts and subtitles, summarize or analyze what was said, or save an Obsidian-ready Markdown knowledge-base note with captions, creator metadata, chapters, language, and source provenance. Use for a YouTube URL or video ID when the request needs spoken content or an archival note. A bare YouTube…
install-by2kb
Install, configure, update, or diagnose the by2kb CLI for this Hermes plugin. Preserve existing configuration and keep Hermes-managed plugin code separate from CLI upgrades.
reduce
Extract structured knowledge from source material. Comprehensive extraction is the default — every insight that serves the domain gets extracted. For domain-relevant sources, skip rate must be below 10%. Zero extraction from a domain-relevant source is a BUG. Triggers on "/reduce", "/reduce [file]", "extract…
verify
Combined verification — recite (description quality via cold-read prediction) + validate (schema compliance) + review (health checks). Use as a quality gate after creating notes or as periodic maintenance. Triggers on "/verify", "/verify [note]", "verify note quality", "check note health".