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 oinam/ovellum --skill ovellum-docsgit clone --depth 1 https://github.com/oinam/ovellumWrote 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/oinam/ovellum/ovellum-docs)<a href="https://agentmods.dev/skills/oinam/ovellum/ovellum-docs"><img src="https://agentmods.dev/badge/skills/oinam/ovellum/ovellum-docs/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/oinam/ovellum/ovellum-docs"><img src="https://agentmods.dev/badge/skills/oinam/ovellum/ovellum-docs.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 | $0.00079 | $0.00716 |
| Opus 5 | $0.00039 | $0.00358 |
| Sonnet 5 | $0.00016 | $0.00143 |
| Haiku 4.5 | $0.00008 | $0.00072 |
Grade A, and why
ovellum-docs 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 9d 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 — 66 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Ovellum docs
Ovellum is a documentation tool for TypeScript and JavaScript: a merge engine that lets auto-generated API docs and hand-written prose live in the same files, plus a static-site builder for purely manual docs. Site: https://ovellum.oss.oinam.com.
Setup
- Install (local to the project, so CI and
npxresolve the same version):npm install -D ovellum - Scaffold:
npx ovellum init. It writes a commentedovellum.config.ts, a starter page, anAGENTS.md, and.gitignoreentries. Three modes:- manual — hand-written Markdown → static site.
- auto — Markdown generated from source on every build.
- hybrid — generated, then merged with hand-written zones (the default and the differentiator).
The hybrid contract (the rule to respect)
Generated files are regenerated on every build. Hand-written prose survives only inside a protected zone:
<!-- @manual:start id="why" -->
Prose that survives regeneration.
<!-- @manual:end -->
Anything outside a zone in a generated file is overwritten. When the symbol a
zone was attached to disappears (a rename or refactor), its prose is moved to
.ovellum/orphans/ rather than lost — review it with ovellum orphans, and use
ovellum diff to spot likely renames.
Commands (all support --json; stable exit codes 0 / 1 / 3)
ovellum build— parse + generate + merge, or build the site.ovellum check— validate internal links + flag unsafe URLs (exit 1 on issues).ovellum diff— preview what a rebuild would change (added/removed/changed/ renamed symbols);--exit-codeto gate CI.ovellum orphans— list quarantined prose (--stalefor old ones).
Driving Ovellum as an agent
Prefer the MCP server — it exposes the operations as tools, including the one no other docs tool offers: writing prose into a protected zone that survives regeneration.
claude mcp add ovellum -- npx ovellum mcp --cwd /path/to/project
Tools: ovellum_query_symbol, ovellum_diff, ovellum_check,
ovellum_list_orphans, ovellum_get_page, ovellum_build, and
ovellum_write_zone (write/update a @manual block under an anchor id;
dryRun to preview).
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.
- 9d ago First seen · 66 lines · 79 tokens per session scan A a823e758268e
ovellum-docs is a skill published in the GitHub repository oinam/ovellum (1 stars, last pushed 1mo ago), licensed MIT. It adds 79 tokens to every session and 716 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 2026-08-31.
Other skills, from other repositories
init
Bootstrap docaudit for a repo, or add and refresh its optional local documentation harness. Use when the user asks to set up docaudit, initialize the doc-audit harness, or run docaudit on a repo that lacks /check-docs / /review-docs / doc-lint. Inventories the repo, proposes a doc-audit.json config for approval…
audit
Change-driven documentation audit. Use when the user asks to audit docs since the last audit, check documentation consistency after code/config changes, run a full doc consistency sweep, or verify nothing is stale before a release. Diffs since the anchor, maps changed files to impacted docs, runs the configured…
using-docshark
Use when installing, running, and troubleshooting DocShark as an MCP server, including client setup for STDIO mode and endpoint checks for HTTP mode.
typo3-docs
Use when creating, editing, or reviewing TYPO3 extension documentation (Documentation/.rst, guides.xml, README.md, XLF translations), rendering docs with Docker, using TYPO3 RST directives, adding screenshots, deploying to docs.typo3.org, improve docs, fix documentation, or XLIFF 2-space indentation (TYPO3 v14+).
docshark
Use when answering framework, library, SDK, or API documentation questions with DocShark MCP tools, especially for indexed-doc search, full-page retrieval, and library lifecycle tasks.
keep-the-why
Extract and preserve the reasoning code cannot explain - decisions, rejected alternatives, workarounds, incidents, constraints - plus project setup and maintainer interviews. Not for what changed (see Keep a Changelog) - only why.