Instructions for creating and managing self-contained interactive HTML documents through the Octo HTML service. These documents are published as immutable versions, unlike Octo Docs documents, which use collaborative editing.

It covers creating HTML documents, saving their returned identifiers, publishing new versions, and handling metadata and legacy document references.

It prevents mixing two different document systems and their commands. It also defines how to identify a document across later operations.

octo-html — Skill for Claude Code and Codex by Mininglamp-OSS/octo-cli

Install

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.

Any agent

npx skills add Mininglamp-OSS/octo-cli --skill octo-html

Clone the repo

git clone --depth 1 https://github.com/Mininglamp-OSS/octo-cli

Made for: Claude Code, Codex.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/mininglamp-oss/octo-cli/octo-html/github.svg)](https://agentmods.dev/skills/mininglamp-oss/octo-cli/octo-html)

Your own site

<a href="https://agentmods.dev/skills/mininglamp-oss/octo-cli/octo-html"><img src="https://agentmods.dev/badge/skills/mininglamp-oss/octo-cli/octo-html/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/mininglamp-oss/octo-cli/octo-html"><img src="https://agentmods.dev/badge/skills/mininglamp-oss/octo-cli/octo-html.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 72 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 4,381 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits

NVIDIA SkillSpector pass 7 Sept 2026

How audits are shown

Origin original No closer match found in the catalogue.

Token cost

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	$0.00072	$0.04381
Opus 5.5	$0.00029	$0.01752
Sonnet 5.5	$0.00014	$0.00876
Haiku 4.5	$0.00007	$0.00438

Measured 3d ago against content hash 6c0b17d0db6e, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

octo-html 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.

skills/octo-html/SKILL.md · 348 lines

How it starts

The opening of the file, as written. The whole thing — 348 lines — stays where its author put it; the contents beside it link to each section on GitHub.

octo-html — interactive HTML documents

This is NOT the octo-docs body-editing domain. octo-cli html … talks to octo-doc, where a document is a self-contained HTML page published as immutable versions. octo-cli docs … talks to the separate CRDT/Yjs backend.

All commands call $OCTO_API_BASE_URL/docs-html/v1/* and return the standard {ok, identity, data, ...} success envelope.

Document-reference contract

Canonical create has no document reference. Omit slug and provide html. The CLI generates idempotency_key; an explicit key is optional. A display name belongs in meta.title; it is metadata, not identity.
Save data.slug from the response. New documents always return data.doc_id and data.slug, with data.slug == data.doc_id, whether mounted or unmounted. Use data.slug for every later operation.
Legacy documents keep their old reference. For an old document, use its legacy slug wherever this skill says <doc-ref>.
No alias identity and no same-name republish. Creating again with the same meta.title creates a different document. To publish another version, supply the saved data.slug in the server's legacy-named slug field and set --version to the version read with html source plus one.
Do not infer a mode from mount_type, registered, status, or whether data.doc_id is non-empty. registered and status report operational state, not identity.

Query and JSON-body fields remain named slug for wire compatibility. Put the saved document reference in them. Path help displays <doc-ref>, and old legacy slugs are accepted. The CLI does not persist the reference.

Minimum rollout dependency: this contract requires the canonical-create server changes in octo-docs-backend#166 and octo-docs-html#33 to be merged and deployed before this CLI is released. Source reads and guarded bot updates also require octo-docs-html#34. The HTML backend will be deployed first. The CLI release and rollout of its updated skills follow only after the source endpoint and publish guard are deployed and verified on every HTML-serving instance. Do not release this workflow during a mixed old/new backend rollout.

Read the full file on GitHub · 348 lines

Changes

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 Changed · +20 lines 6c0b17d0db6e
4d ago Changed · +4 lines f71b2d755e4c
6d ago Changed 807de0bb9e11
1mo ago Changed · +98 lines ac0237f05a1d
1mo ago Changed · +15 lines · +5 tokens per session 35c57eb7d82e
1mo ago First seen · 211 lines · 67 tokens per session scan A 697e881a397a

Subscribe to this mod's changes

octo-html is a skill published in the GitHub repository Mininglamp-OSS/octo-cli (920 stars, last pushed yesterday), licensed Apache-2.0. It adds 72 tokens to every session and 4,381 once invoked, about $0.0003 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 2026-08-30.

Documents Go ai-agent bot cli metadata-driven octo

xberg

Extract text, tables, metadata, and images from 97+ document formats (PDF, Office, images, HTML, email, archives, academic) using Xberg CLI.

CherryHQ/stella · 38 tokens

haypile

Search the user's local documents (PDF, docx, pptx, markdown, text, HTML, mbox email) through Haypile, a local search daemon. Use when the user asks what their files say, wants passages from contracts, papers, or notes, or wants a folder indexed for search. Every result carries a file and page citation. Runs entirely…

BenyD/haypile · 78 tokens

octo-html

Getting it into your agent

Wrote this? Show the measurements

What it costs to keep this loaded

Grade A, and why

Nothing flagged

How it starts

octo-html — interactive HTML documents

Document-reference contract

What this file has done since we first saw it

Other skills, from other repositories

xberg

haypile

gh-skill

gws-sheets

recipe-create-presentation

feishu