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 instructions/sandermoon/local-brain/claude-mdgit clone --depth 1 https://github.com/SanderMoon/local-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/instructions/sandermoon/local-brain/claude-md)<a href="https://agentmods.dev/instructions/sandermoon/local-brain/claude-md"><img src="https://agentmods.dev/badge/instructions/sandermoon/local-brain/claude-md.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 | $0.01901 | $0.01901 |
| Opus 5 | $0.00950 | $0.00950 |
| Sonnet 5 | $0.00380 | $0.00380 |
| Haiku 4.5 | $0.00190 | $0.00190 |
Grade A, and why
local-brain 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 3d 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 — 201 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
Project Overview
Local Brain is a minimalist, local-first project management CLI tool for developers. It manages Brains (high-level workspaces) and Projects (specific focus areas within a Brain), providing context management for notes, tasks, and code repositories.
Key Concepts:
- Brains: Top-level workspaces (e.g., "Work", "Personal"). Only one brain is active at a time, symlinked to
~/brain - Projects: Focus areas within a brain. Each has
notes.md,todo.md, and optional git repo links - Dump: Quick capture inbox (
00_dump.md) for tasks/notes that get refiled to projects - Local-first: Plain text Markdown files, grep-able, version-controllable
Build & Test Commands
Building
make build # Build binary to ./brain
make dev-install # Install to ~/.local/bin
make install # Install to /usr/local/bin (system-wide)
Testing
make test # Fast unit tests only (default)
make test-all # All tests including integration
make test-unit # Unit tests only
make test-integration # Integration tests only
make test-cover # Generate coverage report (coverage.html)
make test-race # Run with race detection
# Run single test
go test -v ./pkg/api -run TestGenerateItemID
go test -v ./pkg/config -run TestLoadConfig
Code Quality
make fmt # Format code
make vet # Run go vet
make lint # Run golangci-lint (if installed)
make check # Run all checks (fmt, vet, test)
Release
make snapshot # Test release build without tags (artifacts in dist/)
make release # Create production release (requires git tag)
Architecture
Package Structure
cmd/ - Cobra CLI commands (19 commands)
- Each command in separate file (e.g.,
add.go,project.go,todo.go) - All register with
rootCmdin theirinit()functions root.godefines base command and version handling
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.
- 3d ago First seen · 201 lines · 1,901 tokens per session scan A b0676e998780
local-brain CLAUDE.md is an instructions file published in the GitHub repository SanderMoon/local-brain (9 stars, last pushed 5mo ago), licensed MIT. It adds 1,901 tokens to every session, about $0.0095 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.
Other instructions, from other repositories
chainlink CLAUDE.md
Instructions for dollspace-gay/chainlink, covering chainlink issue tracker, commands, issues, organization and sessions.
JIRA-Assistant-Skills CLAUDE.md
Instructions for grandcamel/JIRA-Assistant-Skills, covering jira assistant skills, project overview, architecture, directory structure and shared library pattern.
pm-copilot CLAUDE.md
Instructions for dkships/pm-copilot, covering pm copilot — mcp server, commands, pii guardrails (load-bearing for any pr), environment variables and conventions.
pm-copilot AGENTS.md
Instructions for dkships/pm-copilot, covering pm copilot — agent instructions, what this is, tech stack, scope and boundaries and working rules.
task-orchestrator CLAUDE.md
Instructions for jpicklyk/task-orchestrator, covering project: mcp task orchestrator, build commands, docker (most common), architecture and modes of operation.
festival GEMINI.md
Gemini CLI instructions for Obedience-Corp/festival: Festival is a goal-oriented project management methodology for human and AI development workflows, driven by the fest and camp CLIs, installed and kept in sync by a third tool, festival. The skills imported below describe how to plan and execute festivals. Load them…