oc-docs

oc-docs is a command for Claude Code from TheophilusChinomona/claude-openclaw-plugin. It costs 22 tokens per session (853 once invoked), scanned A, original, MIT.

A command for downloading, updating, checking, and searching a local copy of OpenClaw documentation from its website and GitHub.

In plain words
What is it for?
Use it to sync core or complete documentation, update a selected category, check sync status, or search the cached pages.
Why use it?
It keeps documentation available locally and shows which pages changed, failed, or were skipped during synchronization.

Command for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: built for openclaw.

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is cd "${PLUGIN_ROOT}" && python scripts/oc-docs-fetch.py sync [flags].

Part of the openclaw plugin — 31 skills, 22 commands, 4 agents, 3 hooks shipped together

Good fit Use it to sync core or complete documentation, update a selected category, check sync status, or search the cached pages.

Compare 6 commands from other repositories ↓
Install

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.

Clone the repo
git clone --depth 1 https://github.com/TheophilusChinomona/claude-openclaw-plugin
agentmods
npx agentmods add commands/theophiluschinomona/claude-openclaw-plugin/oc-docs

Made for: Claude Code.

Or install openclaw, the plugin that ships this one along with the rest of its 31 skills, 22 commands, 4 agents, 3 hooks.

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.

agentmods badge for oc-docs

README.md
[![agentmods](https://agentmods.dev/badge/commands/theophiluschinomona/claude-openclaw-plugin/oc-docs/github.svg)](https://agentmods.dev/commands/theophiluschinomona/claude-openclaw-plugin/oc-docs)
Your own site
<a href="https://agentmods.dev/commands/theophiluschinomona/claude-openclaw-plugin/oc-docs"><img src="https://agentmods.dev/badge/commands/theophiluschinomona/claude-openclaw-plugin/oc-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.

agentmods 80×15 button for oc-docs

Your own site · 80×15
<a href="https://agentmods.dev/commands/theophiluschinomona/claude-openclaw-plugin/oc-docs"><img src="https://agentmods.dev/badge/commands/theophiluschinomona/claude-openclaw-plugin/oc-docs.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 22 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 853 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.
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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00022 $0.00853
Opus 5 $0.00011 $0.00426
Sonnet 5 $0.00004 $0.00171
Haiku 4.5 $0.00002 $0.00085

Measured 8d ago against content hash def6d2ff6aff, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

oc-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 8d 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.

plugins/openclaw/commands/oc-docs.md · 122 lines

How it starts

The opening of the file, as written. The whole thing — 122 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/oc-docs Command

Manage locally-cached OpenClaw documentation from docs.openclaw.ai and GitHub.

Plugin Root

Determine the plugin root path:

PLUGIN_ROOT="$HOME/.claude/plugins/openclaw-plugin/plugins/openclaw"

Subcommands

Parse the user's arguments to determine the subcommand:

sync (default if no args)

Fetch and update documentation from upstream sources using parallel HTTP.

Flags:

  • --full — Fetch all tiers (Tier 1 + 2 + 3, ~431 pages)
  • --category <name> — Fetch only pages in the specified category
  • --force — Re-fetch everything, ignore staleness
  • --concurrency N — Max concurrent requests (default: 10)
  • No flags — Fetch Tier 1 only (~148 core pages)

Steps:

  1. Run the fetch script:
    cd "${PLUGIN_ROOT}" && python scripts/oc-docs-fetch.py sync [flags]
    
  2. The script handles: fetching llms.txt, parsing entries, filtering by tier/category, parallel HTTP fetch, manifest updates, and INDEX.md regeneration.
  3. Parse the JSON output from stdout for summary stats.
  4. Report results to the user: pages fetched, unchanged, skipped, failed.

status

Show documentation sync status.

Steps:

  1. Run:
    cd "${PLUGIN_ROOT}" && python scripts/oc-docs-fetch.py status
    
  2. Display the output directly to the user.

Example output:

OpenClaw Documentation Status
========================================
Total fetched: 148 pages
  docs-site:   148
  github:      0
Stale:         12 (> 7 days)
Storage:       2.3M

By Category:

  [Tier 1 - Core]
    automation       23 pages
    channels         31 pages
    cli              52 pages
    concepts          8 pages
    gateway          15 pages
    security         19 pages

  [Tier 2 - Extended]
    install           0 pages
    providers         0 pages
    ...

search <query>

Search crawled documentation for a query string.

Steps:

  1. Check if .crawled/ exists and has content. If not, suggest /oc-docs sync.
  2. Use Grep to search .crawled/ for the query pattern.
  3. Show matches with file path, line number, and surrounding context (3 lines).
  4. Group results by category for readability.
  5. Limit to 20 results by default, mention if more exist.

Read the full file on GitHub · 122 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.

  1. 8d ago First seen · 122 lines · 22 tokens per session scan A def6d2ff6aff

Subscribe to this mod's changes

oc-docs is a command published in the GitHub repository TheophilusChinomona/claude-openclaw-plugin (2 stars, last pushed 5mo ago), licensed MIT. It adds 22 tokens to every session and 853 once invoked, about $0.0001 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.