What is brainctl CLAUDE.md?

Project instructions for brainctl, an agent-memory system that stores information in a database and provides command-line and MCP access. MCP is a standard way for an AI agent to use external tools.

It helps maintain and use the brainctl and agentmemory codebase, including its database, command-line program, MCP server, and project-specific setup.

It gives developers one reference for the system's files, database, build and test process, migrations, and available tools.

How TSchonleber/brainctl configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to TSchonleber/brainctl. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/TSchonleber/brainctl/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/TSchonleber/brainctl

Made for: Claude Code.

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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/tschonleber/brainctl/claude-md/github.svg)](https://agentmods.dev/instructions/tschonleber/brainctl/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/tschonleber/brainctl/claude-md"><img src="https://agentmods.dev/badge/instructions/tschonleber/brainctl/claude-md/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.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/tschonleber/brainctl/claude-md"><img src="https://agentmods.dev/badge/instructions/tschonleber/brainctl/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 6,298 This file is loaded in full into every session.

When invoked 6,298 The same file — it is already loaded in full.

Security scan B 1 finding. A grade says what 26 rules found in the file — not that it is safe.

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.

Model	Per session	Once invoked
Fable 5.1	$0.06298	$0.06298
Opus 5.5	$0.02519	$0.02519
Sonnet 5.5	$0.01260	$0.01260
Haiku 4.5	$0.00630	$0.00630

Measured 7d ago against content hash 43449d64f6eb, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade B, and why

brainctl CLAUDE.md scanned grade B with 1 finding 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 7d 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.

Asks for rootmediumPrivilege escalation

A mod that escalates privileges can change anything on the machine, not only the project.

non-custodial keypair at `~/.brainctl/wallet.json` (chmod 0600). The

CLAUDE.md · 440 lines

How it starts

The opening of the file, as written. The whole thing — 440 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Claude Code — brainctl / agentmemory

What This Is

Unified agent memory system. SQLite-backed (brain.db) with FTS5, vector embeddings (sqlite-vec + Ollama nomic-embed-text), knowledge graph, affect tracking, belief collapse mechanics, and AGM conflict resolution.

Published as brainctl on PyPI (v2.2.1+, current 2.9.1).

Key Paths

DB: db/brain.db (WAL mode, foreign keys ON, 59 user-facing tables, 84 numbered migrations, 002–085 with no gaps, plus the unnumbered V2-4 file db/migrations/quantum_schema_migration_sqlite.sql). The runner only picks up files matching ^\d+_.+\.sql$, so brainctl migrate never applies the quantum file; its quantum columns (confidence_phase, hilbert_projection, coherence_syndrome, decoherence_rate, is_superposed, belief_density_matrix, coherence_score, ...) and belief_collapse_events ship in init_schema.sql instead. Slot 050 is 050_thalamus.sql.
CLI: bin/brainctl — main CLI entry
MCP server: the brainctl-mcp console script points at agentmemory.mcp_entrypoint:run, which prints the pip install 'brainctl[mcp]' hint when the MCP extra is missing and otherwise delegates to agentmemory.mcp_server:run (also runnable as python -m agentmemory.mcp_server). As of v2 surface consolidation (2026-05-20): 100 visible tools (370 registered internally; 270 hidden behind action-discriminated dispatchers). Installed as the brainctl-mcp console script via pip. See MCP_SERVER.md for the tool reference and docs/TOOL_MIGRATION_V2.md for v1→v2 migration. The legacy standalone bin/brainctl-mcp script was removed after 2.8.1; use the console script.
Bench: bin/brainctl-bench — retrieval eval harness (P@k / MRR / nDCG@k regression gate, fixtures under tests/bench/)
Source: src/agentmemory/ — Python package
Config: config/ — quiet hours, consolidation schedules
Agents: agents/ — per-agent config (pipeline, engram, etc.)

Build & Test

pip install -e .                                      # dev install
brainctl stats                                        # verify DB
brainctl search "test"                                # test search
python3 -m agentmemory.mcp_server --list-tools        # 100-tool v2 MCP surface
python3 -m tests.bench.run                            # retrieval quality benchmark
python3 -m tests.bench.run --check                    # fail on >2% regression vs baseline

Read the full file on GitHub · 440 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.

7d ago Changed · +4 tokens per session 43449d64f6eb
14d ago Changed · +1 lines · +182 tokens per session 766d491055dd
2mo ago First seen · 439 lines · 6,112 tokens per session scan B ad0a78853454

Subscribe to this mod's changes

brainctl CLAUDE.md is an instructions file published in the GitHub repository TSchonleber/brainctl (78 stars, last pushed 8d ago), licensed MIT. It adds 6,298 tokens to every session, about $0.0252 per session on Opus 5.5. A static security scan graded it B with 1 finding (asks for root). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Memory and context

brainctl CLAUDE.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
brainctl CLAUDE.mdTSchonleber/brainctl	Instructions file	78	8d ago	MIT	B	6,298	Claude Code
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	today	MIT	A	7,461	Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	yesterday	MIT	A	4,680	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	5,516	GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	3,093	GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness	Instructions file	274k	2d ago	MIT	A	4,313	Codex, OpenCode

brainctl: Instructions file for Claude Code