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/robertsfeir/mybrain/claude-mdgit clone --depth 1 https://github.com/robertsfeir/mybrainWrote 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/robertsfeir/mybrain/claude-md)<a href="https://agentmods.dev/instructions/robertsfeir/mybrain/claude-md"><img src="https://agentmods.dev/badge/instructions/robertsfeir/mybrain/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 5.1 | $0.01487 | $0.01487 |
| Opus 5 | $0.00744 | $0.00744 |
| Sonnet 5 | $0.00297 | $0.00297 |
| Haiku 4.5 | $0.00149 | $0.00149 |
Grade A, and why
mybrain 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 5d 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 — 116 lines — stays where its author put it; the contents beside it link to each section on GitHub.
mybrain-mcp
Project Overview
Personal semantic thought storage and retrieval MCP server with vector embeddings and ltree scoping. Implements the 8-tool atelier-brain protocol for cross-project compatibility (mybrain ADR-0001).
Tech Stack
- Runtime: Node.js 18+ (ESM modules)
- MCP Framework:
@modelcontextprotocol/sdk1.27.1 - Database: PostgreSQL 12+ with pgvector (1536-dim embeddings) and ltree extensions
- HTTP Server: Node
http(Streamable HTTP transport mode) - Embeddings: Provider-abstracted (OpenRouter, OpenAI, GitHub Models, local Ollama)
- Containerization: Docker (Alpine), Docker Compose
Source Layout
server.mjs — startup orchestrator (transport + wiring only, ~250 lines)
lib/ — all server logic
config.mjs — resolveConfig, buildProviderConfig, identity, enums
db.mjs — createPool, runMigrations
crash-guards.mjs — installCrashGuards (process-level signal/error handlers)
embed.mjs — getEmbedding, probeEmbeddingDim, startEmbedWorker
llm-provider.mjs — embed/chat provider adapters (openai-compat, anthropic, local)
llm-response.mjs — assertLlmContent (LLM response validation)
conflict.mjs — detectConflicts, classifyConflict, getBrainConfig
consolidation.mjs — startConsolidationTimer, runConsolidation
ttl.mjs — startTTLTimer, runTTLEnforcement
tools.mjs — registerTools (8 protocol tools)
rest-api.mjs — createRestHandler (Settings UI REST endpoints)
static.mjs — handleStaticFile (Settings UI asset serving)
hydrate.mjs — discoverSubagentFiles/discoverEvaFiles/Tier 1-3 hydration
migrations/ — auto-applied SQL migrations (idempotent, runs at startup)
scripts/ — out-of-band utilities (hydrate-telemetry.mjs)
templates/ — Docker deployment scaffolding (Dockerfile, compose.yml, schema.sql)
ui/ — reserved for Settings UI static assets (placeholder; lib/static.mjs serves from here when populated)
tests/brain/ — node:test integration tests (require DATABASE_URL)
skills/ — Claude Code skills (mybrain-setup, mybrain-overview)
.claude-plugin/ — plugin manifest for marketplace
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.
- 5d ago First seen · 116 lines · 1,487 tokens per session scan A 28830f63ff91
mybrain CLAUDE.md is an instructions file published in the GitHub repository robertsfeir/mybrain (0 stars, last pushed 3mo ago), licensed Apache-2.0. It adds 1,487 tokens to every session, about $0.0074 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
pulse8-ai-cortex-knowledge-vault AGENTS.md
Instructions for synpulse8-opensource/pulse8-ai-cortex-knowledge-vault, covering agents.md — pulse8.ai cortex, repository map, environment variables, essential commands and dependencies.
OpenKB CLAUDE.md
Claude Code instructions for VectifyAI/OpenKB, a project described as: OpenKB: Open LLM Knowledge Base.
rag-code-mcp copilot-instructions.md
Instructions for doITmagic/rag-code-mcp, covering copilot instructions - ragcode mcp, ⚖️ the golden rule, project overview, architecture & patterns and developer workflows.
Axon copilot-instructions.md
Copilot instructions for jyunming/Axon, covering axon knowledge center — copilot instructions, what axon is, project namespaces, hierarchical projects (up to 5 levels) and merged read-only scopes.
llm-brain CLAUDE.md
Instructions for kimsanguine/llm-brain, covering llm-brain — claude code 운영 지침, 가드레일 (절대 위반 금지), 프라이버시 경계 (agent memory os), 명령어 and ingest.
openclaw-memory-vectorize AGENTS.md
Instructions for Atlas-Os1/openclaw-memory-vectorize, covering agents.md, quick setup (execute these commands), 1. install dependencies, 2. create vectorize index (skip if exists) and 3. deploy worker.