Agent skill

Claude Mega Brain

by guhcostan in guhcostan/claude-mega-brain

OKF knowledge navigation. An agent skill from guhcostan/claude-mega-brain.

MITAuto-check passedKnowledge Management

Install Claude Mega Brain

skills CLI
$ npx skills add guhcostan/claude-mega-brain --skill claude-mega-brain -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install guhcostan/claude-mega-brain claude-mega-brain --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/guhcostan/claude-mega-brain.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/claude-mega-brain .claude/skills/claude-mega-brain && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
claude-mega-brain
GitHub stars
126
Token cost
~588 tokens
SKILL.md length
230 words
Files
1
Skills in repo
4
Repo updated
First seen
Licence
MIT

At a glance

OKF knowledge navigation. An agent skill from guhcostan/claude-mega-brain.

  • Works in 4 steps: Read the file — paths in are relative to… → Follow links — text links in the body… → log.md — chronological changelog; last 3… → …
  • The user asks about a table
  • SKILL.md covers What OKF files look like, Navigation, When to proactively read files and If context is missing
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Claude Mega Brain is an agent skill from guhcostan/claude-mega-brain. OKF knowledge navigation. ALWAYS use this skill the moment a <mega-brain block appears in session context — it means the project has documented concepts and you must consult them before answering questions about data, schemas, metrics, APIs, or systems. Also trigger when the user asks about a table, column, metric definition, service, or API endpoint and there's any chance it's documented in the project. When in doubt, read the file directly.

Its SKILL.md is about 590 tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in Knowledge Management, covering REST APIs and Product metrics. The repository describes itself as: OKF-powered knowledge context for Claude Code — injects your project's knowledge base at every session. The licence is MIT.

When your agent uses it

  • The user asks about a table
  • Metric definition
  • API endpoint and theres any chance its documented in the project

Example prompts

  • “s any chance it”
  • “/claude-mega-brain”

Workflow steps

4 steps, taken from the first numbered list in SKILL.md.

  1. Read the file — paths in are relative to the project root; use the Read tool directly
  2. Follow links — text links in the body point to related concepts; read them
  3. log.md — chronological changelog; last 3 entries are injected automatically
  4. Linked concepts auto-surface — after you read an OKF file, linked concept summaries appear via PostToolUse hook

What it can do on your machine

Read from SKILL.md and the folder at commit de1ab9c. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md (its code samples are yaml).

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Claude Mega Brain loads about 588 tokens when it runs. Until then it costs about 117 tokens; SKILL.md has 230 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~117
When it runs · the whole SKILL.md, loaded when a task matches
~588

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from guhcostan/claude-mega-brain at commit de1ab9c, republished under its MIT licence (© guhcostan). 230 words, ~588 tokens.

Download SKILL.mdSave it as .claude/skills/claude-mega-brain/SKILL.md (or your agent's skills folder).
name
claude-mega-brain
description
OKF knowledge navigation. ALWAYS use this skill the moment a `<mega-brain>` block appears in session context — it means the project has documented concepts and you must consult them before answering questions about data, schemas, metrics, APIs, or systems. Also trigger when the user asks about a table, column, metric definition, service, or API endpoint and there's any chance it's documented in the project. When in doubt, read the file directly.

claude-mega-brain — OKF Knowledge Navigator

When <mega-brain> context is present, the project has OKF-documented concepts — any Markdown file with type: in its YAML frontmatter. These are the authoritative source for domain knowledge: exact schemas, metric formulas, API contracts, runbooks, business definitions. Answers from the knowledge base beat answers from training data.

What OKF files look like

Any .md file anywhere in the project with YAML frontmatter containing type::

yaml
---
type: BigQuery Table
title: Orders
description: One row per completed customer order.
resource: https://...
tags: [sales, revenue]
timestamp: 2026-06-29T00:00:00Z
---

# Schema
| Column | Type | Description |
...

No dedicated folder required. The file can live in docs/, wiki/, project root, anywhere.

Navigation

  1. Read the file — paths in <mega-brain> are relative to the project root; use the Read tool directly
  2. Follow links — [text](rel-path.md) links in the body point to related concepts; read them
  3. log.md — chronological changelog; last 3 entries are injected automatically
  4. Linked concepts auto-surface — after you read an OKF file, linked concept summaries appear via PostToolUse hook

When to proactively read files

  • User asks about a data source, table, column, or metric — check <mega-brain> index first
  • Before writing SQL, queries, or code that touches project data
  • When a business term is ambiguous — OKF has the canonical definition
  • When the user says "check the knowledge base", "what do we know about X", or "olha no okf"

If <mega-brain> context is missing

No OKF concepts found in the project yet. Suggest:

  • /mega-brain:init — creates index.md and log.md to get started
  • /mega-brain:migrate — scans existing docs and generates OKF files automatically

© guhcostan, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in skills/claude-mega-brain of guhcostan/claude-mega-brain.

Open the folder on GitHubat commit de1ab9c

Compare with similar skills

Claude Mega Brain next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Claude Mega Brain compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Claude Mega Brain this skillguhcostan/claude-mega-brain126—~588Automated safety check: PassMIT
Confluence To Markdowniurykrieger/claude-bedrock1051 repos~2.8kAutomated safety check: NotesMIT
Anytype Importpricklywiggles/niamos192—~3.3kAutomated safety check: PassNone
CLI Anything ObsidianHKUDS/CLI-Anything52k—~1.3kAutomated safety check: PassApache-2.0
Sage Wikixoai/sage-wiki623—~2.4kAutomated safety check: PassMIT
Scrapecreators APIScrapeCreators/social-media-research-skills3.4k—~4kAutomated safety check: NotesMIT

Similar skills

  • Confluence To Markdown

    iurykrieger/claude-bedrock

    Internal fetcher module for Confluence pages. An agent skill from iurykrieger/claude-bedrock.

    105 GitHub starsUsed in 1 repo~2.8k tokens
    Knowledge ManagementAuto-check: notes
  • Anytype Import

    pricklywiggles/niamos

    Import a page from the user's self-hosted Anytype into this Niamos Obsidian vault, page-by-page, recursing into children only when the user explicitly says so.

    192 GitHub stars~3.3k tokensUpdated 3 mo ago
    Knowledge ManagementAuto-check passed
  • CLI Anything Obsidian

    HKUDS/CLI-Anything

    Command-line interface for Obsidian — Knowledge management and note-taking via Obsidian Local REST API.

    52k GitHub stars~1.3k tokensUpdated 18 days ago
    Knowledge ManagementAuto-check passed
  • Sage Wiki

    xoai/sage-wiki

    Reference skill for sage-wiki — local-first knowledge graph with MCP server, REST API, compiled wiki, and Obsidian-compatible output.

    623 GitHub stars~2.4k tokensUpdated 4 days ago
    Knowledge ManagementAuto-check passed
  • Scrapecreators API

    ScrapeCreators/social-media-research-skills

    Scrape and extract public data from 27+ social media platforms using the ScrapeCreators REST API.

    3.4k GitHub stars~4k tokensUpdated 1 mo ago
    Backend & APIsAuto-check: notes
  • X Twitter Scraper

    davila7/claude-code-templates

    X API & Twitter scraper skill for AI coding agents. An agent skill from davila7/claude-code-templates.

    33k GitHub stars~1.8k tokensUpdated today
    Backend & APIsAuto-check passed

More from guhcostan/claude-mega-brain

  • Ingest

    guhcostan/claude-mega-brain

    Create or update a single OKF concept file from raw input. An agent skill from guhcostan/claude-mega-brain.

    126 GitHub stars~694 tokensUpdated 2 mo ago
    Auto-check passed
  • Init

    guhcostan/claude-mega-brain

    Initialize OKF knowledge base files in the current project. An agent skill from guhcostan/claude-mega-brain.

    126 GitHub stars~530 tokensUpdated 2 mo ago
    Auto-check passed
  • Migrate

    guhcostan/claude-mega-brain

    Scan the project and migrate existing documentation into OKF format.

    126 GitHub stars~975 tokensUpdated 2 mo ago
    Auto-check passed

Questions about Claude Mega Brain

What does Claude Mega Brain do?

OKF knowledge navigation. An agent skill from guhcostan/claude-mega-brain. Claude Mega Brain is an agent skill from guhcostan/claude-mega-brain. OKF knowledge navigation.

When should I use Claude Mega Brain?

Claude Mega Brain fits situations like: the user asks about a table; metric definition; API endpoint and theres any chance its documented in the project.

How do I install Claude Mega Brain in Claude Code?

Run `npx skills add guhcostan/claude-mega-brain --skill claude-mega-brain -a claude-code`. Or copy the skill folder (skills/claude-mega-brain in guhcostan/claude-mega-brain) into .claude/skills/claude-mega-brain in your project. Claude Code loads it when a task matches its description.

How do I install Claude Mega Brain in Codex?

Run `npx skills add guhcostan/claude-mega-brain --skill claude-mega-brain -a codex`. Or copy the skill folder (skills/claude-mega-brain in guhcostan/claude-mega-brain) into .agents/skills/claude-mega-brain in your project. Codex loads it when a task matches its description.

Can I use Claude Mega Brain in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add guhcostan/claude-mega-brain --skill claude-mega-brain -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/claude-mega-brain, .gemini/skills/claude-mega-brain, .github/skills/claude-mega-brain and .opencode/skills/claude-mega-brain in your project.

What does Claude Mega Brain need to run?

SKILL.md names no scripts, command-line tools or credentials: Claude Mega Brain is instructions for the agent only.

Does Claude Mega Brain access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Claude Mega Brain safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Claude Mega Brain use?

Claude Mega Brain is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Claude Mega Brain use?

About 588 tokens (SKILL.md is roughly 2.4k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Claude Mega Brain?

Skills that share tags, products or a category with Claude Mega Brain: Confluence To Markdown (iurykrieger/claude-bedrock, 105 stars), Anytype Import (pricklywiggles/niamos, 192 stars), CLI Anything Obsidian (HKUDS/CLI-Anything, 52k stars) and Sage Wiki (xoai/sage-wiki, 623 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Claude Mega Brain?

guhcostan (a GitHub user) maintains it in guhcostan/claude-mega-brain, which has 126 GitHub stars. The repository holds 4 skills in this directory. The repository was last updated on July 22, 2026.

Source: guhcostan/claude-mega-brain on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.