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 agentmods add skills/guhcostan/claude-mega-brain/initnpx skills add guhcostan/claude-mega-brain --skill initgit 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/init)<a href="https://agentmods.dev/skills/guhcostan/claude-mega-brain/init"><img src="https://agentmods.dev/badge/skills/guhcostan/claude-mega-brain/init.svg" alt="Measured on agentmods" 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 | $0.00089 | $0.00543 |
| Opus 5 | $0.00044 | $0.00271 |
| Sonnet 5 | $0.00018 | $0.00109 |
| Haiku 4.5 | $0.00009 | $0.00054 |
Grade A, and why
init 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 6d 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.
What it actually says
init — Initialize OKF Knowledge Base
Creates a minimal set of OKF files so claude-mega-brain can start injecting context at the next session. No dedicated folder required — files can live anywhere in the project.
What to create
Two files are enough to get started:
index.md — the knowledge map (put it at the project root or in docs/):
---
type: Index
title: <Project Name> Knowledge Base
description: Central reference for all project knowledge.
timestamp: <today ISO 8601>
---
# <Project Name>
## Tables / Data
<!-- [orders](docs/orders.md) — one-liner -->
## Metrics
<!-- [wau](docs/wau.md) — one-liner -->
## APIs
<!-- [auth](docs/auth.md) — one-liner -->
## Services
<!-- [payments](docs/payments.md) — one-liner -->
log.md — append-only changelog (same location as index.md):
---
type: Log
---
<today ISO date> — initialized OKF knowledge base
Steps
- Check if OKF files already exist — look for any
.mdwithtype:frontmatter, or an existingindex.md/log.md. If found, tell the user and stop. - Detect project type (
package.json,pyproject.toml,go.mod, etc.) to personalize the index template. - Ask the user where they want the files — suggest project root or
docs/as default. If.mega-brain.jsonhas adirfield, use that subdirectory instead. - Write
index.mdandlog.mdin the chosen location. - Tell the user:
- What was created and where
- Start a new Claude Code session for context injection to activate
- Add concepts with
/mega-brain:ingestor create.mdfiles withtype:frontmatter anywhere in the project - Run
/mega-brain:migrateto auto-populate from existing schemas and docs
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.
- 6d ago First seen · 59 lines · 89 tokens per session scan A f1ffb80f1db9
init is a skill published in the GitHub repository guhcostan/claude-mega-brain (125 stars, last pushed 1mo ago), licensed MIT. It adds 89 tokens to every session and 543 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 2026-08-30.
Other skills, from other repositories
reduce
Extract structured knowledge from source material. Comprehensive extraction is the default — every insight that serves the domain gets extracted. For domain-relevant sources, skip rate must be below 10%. Zero extraction from a domain-relevant source is a BUG. Triggers on "/reduce", "/reduce [file]", "extract…
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]".
verify
Combined verification — recite (description quality via cold-read prediction) + validate (schema compliance) + review (health checks). Use as a quality gate after creating notes or as periodic maintenance. Triggers on "/verify", "/verify [note]", "verify note quality", "check note health".
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".