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 guhcostan/claude-mega-brain --skill ingestgit clone --depth 1 https://github.com/guhcostan/claude-mega-brainWrote 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/guhcostan/claude-mega-brain/ingest)<a href="https://agentmods.dev/skills/guhcostan/claude-mega-brain/ingest"><img src="https://agentmods.dev/badge/skills/guhcostan/claude-mega-brain/ingest/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/guhcostan/claude-mega-brain/ingest"><img src="https://agentmods.dev/badge/skills/guhcostan/claude-mega-brain/ingest.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00108 | $0.00700 |
| Opus 5 | $0.00054 | $0.00350 |
| Sonnet 5 | $0.00022 | $0.00140 |
| Haiku 4.5 | $0.00011 | $0.00070 |
Grade A, and why
ingest 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 — 68 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ingest — OKF Concept Writer
Turns raw input (schema dump, API doc, user description, table definition) into one OKF-formatted .md file committed to the knowledge base.
Before writing
Look for existing OKF files: any .md with type: frontmatter, or index.md / log.md in the project. If none exist, stop and tell the user to run /mega-brain:init first.
If .mega-brain.json defines dir, save new concepts under that directory. Otherwise, choose a sensible location (docs/, project root, etc.) consistent with existing OKF files.
Check if a concept with the same name already exists. If so, ask whether to update it or create a new one.
Output format
One .md file per concept. Only type is required:
---
type: <concept type>
title: <display name>
description: <one sentence, plain language, no jargon>
resource: <URL to the actual resource, if any>
tags: [<tag1>, <tag2>]
timestamp: <ISO 8601 date>
---
<body: exact schema, formula, join patterns, examples, caveats>
Common types
| Type | Use for |
|---|---|
BigQuery Table |
BQ tables with schema |
BigQuery Dataset |
BQ datasets |
Table |
Non-BQ database tables |
Metric |
KPI or business metric with formula |
API |
REST/GraphQL endpoints |
Runbook |
Operational procedures |
Concept |
Business or domain terminology |
Service |
Internal microservices |
Pipeline |
ETL or data pipelines |
Types are freeform — add your own.
Process
- Read the source material
- Identify the concept type and canonical name
- Write
description: one sentence, plain language - Add
resourceURL if there's a live resource (BQ console URL, API endpoint, dashboard) - Write the body with exact values — preserve field names, types, and formulas as-is; do not generalize
- Link to related concepts with
[Name](relative-path.md)— this builds the knowledge graph - Save next to related OKF files (e.g.
docs/tables/<slug>.mdor<config-dir>/tables/<slug>.md) - Add one line to
index.md:- [Title](path) — description - Append to
log.md:<date> — added <title>
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 · 68 lines · 108 tokens per session scan A 059c11c770d7
ingest is a skill published in the GitHub repository guhcostan/claude-mega-brain (125 stars, last pushed 1mo ago), licensed MIT. It adds 108 tokens to every session and 700 once invoked, about $0.0005 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 2026-08-30.
Other skills, from other repositories
rethink
Challenge system assumptions against accumulated evidence. Triages observations and tensions, detects patterns, generates proposals. The scientific method applied to knowledge systems. Triggers on "/rethink", "review observations", "challenge assumptions", "what have I learned".
graph
Interactive knowledge graph analysis. Routes natural language questions to graph scripts, interprets results in domain vocabulary, and suggests concrete actions. Triggers on "/graph", "/graph health", "/graph triangles", "find synthesis opportunities", "graph analysis".
remember
Capture friction as methodology notes. Three modes — explicit description, contextual (review recent corrections), session mining (scan transcripts for patterns). Triggers on "/remember", "/remember [description]".
seed
Add a source file to the processing queue. Checks for duplicates, creates archive folder, moves source from inbox, creates extract task, and updates queue. Triggers on "/seed", "/seed [file]", "queue this for processing".
reflect
Find connections between notes and update MOCs. Requires semantic judgment to identify genuine relationships. Use after /reduce creates notes, when exploring connections, or when a topic needs synthesis. Triggers on "/reflect", "/reflect [note]", "find connections", "update MOCs", "connect these notes".
llm-wiki
Build and maintain an LLM-curated personal knowledge base — the "LLM Wiki" pattern from Andrej Karpathy's April 2026 gist. Use this skill whenever the user wants to ingest a source (paper, article, transcript, PDF, notes) into a persistent compounding knowledge base, ask a question against accumulated notes, lint or…