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 evergreen-it-dev/folio --skill folio-formsgit clone --depth 1 https://github.com/evergreen-it-dev/folioWrote 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-forms)<a href="https://agentmods.dev/skills/evergreen-it-dev/folio/folio-forms"><img src="https://agentmods.dev/badge/skills/evergreen-it-dev/folio/folio-forms/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-forms"><img src="https://agentmods.dev/badge/skills/evergreen-it-dev/folio/folio-forms.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 | $0.01382 |
| Opus 5.5 | $0.00015 | $0.00553 |
| Sonnet 5.5 | $0.00007 | $0.00276 |
| Haiku 4.5 | $0.00004 | $0.00138 |
Grade A, and why
Folio Forms 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 today.
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 — 114 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Folio forms (kind: form)
A form is a page of questions. Every answer becomes a new row of a data
table paired with the form: each field of the form fills one column of that
table. The form file (<name>.form.md) holds only the definition; the answers
live in the table (<name>.table.md, a child page of the form when the form
created it).
Tools
| Tool | What it does |
|---|---|
read_page (form id) |
The definition: form.title, description, public, submitButton, fields (columnId, label, help, required, kind), form.table.id (the paired table) and the etag |
create_form |
A new form. Without table it creates a new paired table too (one column per field). With table (a table page id) the form goes under that existing table |
update_form |
Change the title, description, submit button label, public, and/or the whole list of fields |
folio_table_query (form.table.id) |
Read the answers |
folio_table_update_column |
Change the choices of a select/status field, or a column's type (the field follows the column) |
Field types
text (one line, the default), longtext, number, date, checkbox,
select (choices in options; multiple: true for several), status
(without options it gets the status preset PLANNING … CANCELLED), user,
link. Give options as plain labels (["Small", "Medium", "Large"]) or as
{ "value": "Large", "color": "green" }.
How the answerer sees them: select/status show the column's options as a
radio group (up to 6 options) or a dropdown (more), several values
(multiple: true) as checkboxes or a searchable list, status with its colours;
user is a searchable member picker; link is a URL plus an optional label —
they are not plain text boxes. The choices come live from the paired table's
column, so changing the options with folio_table_update_column changes the
form at once, and a value outside the options is rejected on submit. Give a
select/status field its options when you create it — without any, the form
has nothing to offer. A user field is shown only to signed-in members; an
anonymous answerer of a public form does not see it (the answer is ignored),
so do not make a user field the only way to identify someone in a public form
and do not rely on it being required there.
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.
- today First seen · 114 lines · 37 tokens per session scan A a08db499ad63
Folio Forms is a skill published in the GitHub repository evergreen-it-dev/folio (71 stars, last pushed yesterday), licensed MIT. It adds 37 tokens to every session and 1,382 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 2026-10-17.
Other skills, from other repositories
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.
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…
docx-press
Teaches agents how to author Markdown that renders cleanly into DOCX via writedocx, with heading hierarchy (up to 6 levels), tables, lists, blockquotes, code blocks, citations, embedded images, SVG diagrams (rendered to PNG first), and document structure patterns for reports, proposals, and technical documents.
obsidian-vault-workflow
Use this skill when a user asks an agent to inspect, organize, summarize, or update an Obsidian vault through this MCP server.
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".