agentmods.dev

superbrain CLAUDE.md

superbrain CLAUDE.md is an instructions file for coding agents from m3talux/superbrain. It costs 566 tokens per session, scanned A, original, MIT.

Repository rules for SuperBrain, including required checks, release files, dependency loading, tests, and hooks. A repository is the code and files managed together for a project.

In plain words
What is it for?
Making and reviewing SuperBrain changes while keeping type checks, builds, tests, release checks, import-safe entry points, and test-first development aligned.
Why use it?
It prevents changes from breaking CI, missing committed build output, loading dependencies too early, or weakening tests and session behavior.

Instructions file

not rated 41 24d ago A scan 566 tokens original MIT
View the source file m3talux/superbrain
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.

agentmods
npx agentmods add instructions/m3talux/superbrain/claude-md
Clone the repo
git clone --depth 1 https://github.com/m3talux/superbrain

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 superbrain CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/m3talux/superbrain/claude-md.svg)](https://agentmods.dev/instructions/m3talux/superbrain/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/m3talux/superbrain/claude-md"><img src="https://agentmods.dev/badge/instructions/m3talux/superbrain/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 566 This file is loaded in full into every session.
When invoked 566 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
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 $0.00566 $0.00566
Opus 5 $0.00283 $0.00283
Sonnet 5 $0.00113 $0.00113
Haiku 4.5 $0.00057 $0.00057

Measured 4d ago against content hash 7c640bb33b65, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

superbrain CLAUDE.md 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 4d 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.

CLAUDE.md · 45 lines

How it starts

The opening of the file, as written. The whole thing — 45 lines — stays where its author put it; the contents beside it link to each section on GitHub.

SuperBrain — repository rules

Instructions for anyone (human or agent) making changes in this repo. These are enforced by CI and by main branch protection.

Non-negotiables

  • The gate must stay green. Every change keeps all of these passing: npm run typecheck (0 errors), npm run build, npm test (full suite), git diff --exit-code dist (a.k.a. npm run release:check).
  • dist/ is committed deliberately. A marketplace /plugin install is a bare git clone with no node_modules, so the compiled output ships in-repo. If you touch src/ or bin/, run npm run build and commit the resulting dist/ in the same change, or CI fails.
  • Entrypoints stay import-safe. Files under bin/ must load with only Node built-ins before dependencies exist. Heavy deps (better-sqlite3, @huggingface/transformers, the MCP SDK, gray-matter) are reached only via a dynamic import() gated behind a depsPresent() check. tests/freshClone E2E.test.ts enforces this — never weaken it.
  • Test-first. Write or update a failing test before the change; never delete or skip a test to make the suite pass.
  • Never disrupt the session. Hooks always exit 0; data is append-or-create with soft-delete; failures surface via the sentinel, not by crashing.

Public-facing content

  • No phased-delivery / internal-process narrative in public docs. README and other shipped docs describe the product as it is, not the order it was built. Don't reference docs/superpowers/ (internal, gitignored).
  • Keep README claims truthful and current (defaults, paths, behavior).

Versioning

  • Pre-1.0, in active development. package.json, .claude-plugin/plugin.json, and the MCP server version stay in lockstep. Don't bump the version casually.

Workflow

  • Branch off main (fix/…, feat/…, chore/…); open a PR; CI must be green before merge. main rejects force-pushes and branch deletion.
  • Commit messages: imperative mood, conventional prefix (feat:, fix:, chore:, docs:, refactor:, test:).

Read the full file on GitHub · 45 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. 4d ago First seen · 45 lines · 566 tokens per session scan A 7c640bb33b65

Subscribe to this mod's changes

superbrain CLAUDE.md is an instructions file published in the GitHub repository m3talux/superbrain (41 stars, last pushed 24d ago), licensed MIT. It adds 566 tokens to every session, about $0.0028 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.

LLMclaude-codeclaude-code-pluginknowledge-managementobsidianpersonal-knowledge-management
Related

Other instructions, from other repositories

corpus CLAUDE.md

Claude Code instructions for evb87-tech/corpus, covering corpus — engine for an llm-curated second brain, two repos, one system, hard rules — never break these, repo layout — monorepo of two plugins and configuration — load on demand from corpus-core/rules/.

evb87-tech/corpus · 1,081 tokens

corpus AGENTS.md

AGENTS.md instructions for evb87-tech/corpus, covering agents.md, two repos, one system, hard rules, repo layout — monorepo of two plugins and where the spec lives.

evb87-tech/corpus · 901 tokens

Kompl AGENTS.md

Instructions for tuirk/Kompl, covering agents.md — kompl operator guide, what is kompl?, agent rules — wiki safety (read before any docker command), never without explicit user confirmation and if a destructive action is going to happen anyway.

tuirk/Kompl · 1,091 tokens

memex-plugin CLAUDE.md

Instructions for linxule/memex-plugin, covering memex - personal knowledge base, quick start, check vault status, search for something (rrf scoring is default) and search recent docs only (7d, 2w, 3m).

linxule/memex-plugin · 2,575 tokens

second-brain-starter-kit AGENTS.md

AGENTS.md instructions for tonydzi/second-brain-starter-kit, covering agents.md — working in this repo, what this repo is, layout, how to verify a change and conventions.

tonydzi/second-brain-starter-kit · 1,104 tokens

llm-knowledge-bases CLAUDE.md

Instructions for rvk7895/llm-knowledge-bases, covering claude.md -- project instructions, project identity, configuration, skills and formatting rules (obsidian-compatible).

rvk7895/llm-knowledge-bases · 327 tokens