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/robertsfeir/mybrain/mybrain-setupnpx skills add robertsfeir/mybrain --skill mybrain-setupgit 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/skills/robertsfeir/mybrain/mybrain-setup)<a href="https://agentmods.dev/skills/robertsfeir/mybrain/mybrain-setup"><img src="https://agentmods.dev/badge/skills/robertsfeir/mybrain/mybrain-setup.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 | $0.00075 | $0.09059 |
| Opus 5 | $0.00037 | $0.04529 |
| Sonnet 5 | $0.00015 | $0.01812 |
| Haiku 4.5 | $0.00007 | $0.00906 |
Grade A, and why
mybrain-setup scanned grade A with 2 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
test: ["CMD-SHELL", "curl -fsS http://127.0.0.1:8787/health || exit 1"] Runs shell commandslowCapability
Expected in a hook, worth knowing in a rule or an instructions file.
proj = subprocess.check_output(['git', 'rev-parse', '--show-toplevel'], text=True).strip() How it starts
The opening of the file, as written. The whole thing — 715 lines — stays where its author put it; the contents beside it link to each section on GitHub.
MyBrain -- Setup
This skill installs MyBrain.
Install scope is always per-project (local). The MCP server is registered with claude mcp add using the default local scope — it lives in this user's Claude config for this project only. It is never registered with --scope user (that registration leaks to every project on the machine and causes port races and mis-attributed thoughts), never with --scope project (that ships the registration to teammates via .mcp.json), and never auto-registered by the plugin loader (v2.2.0 and earlier shipped a .mcp.json at the plugin root that Claude Code's plugin system would auto-register as plugin:mybrain:mybrain with a hard-coded BRAIN_SCOPE: "personal" — that file was removed in v2.2.1, but stale plugin caches may still carry it). Step 0 below detects any pre-existing non-local registration and offers to remove it.
The only user-facing choice during setup is where the brain's database lives. Four backends are supported:
- Bundled -- PostgreSQL, Ollama, and the MCP server all run inside a single container. No API key needed. One port. One volume. Recommended for personal use.
- Docker -- Multi-container: PostgreSQL + optional Ollama (compose profile) + MCP server. Uses OpenRouter or Ollama for embeddings.
- Native -- No Docker. Ollama runs directly on the host, Postgres is whatever the user already has installed (or any reachable PG), and the MCP server runs as a local process registered via
claude mcp add. - RDS -- Connect to a shared PostgreSQL database on AWS RDS or any reachable remote Postgres. Multiple repos can share one database — ltree scoping (
BRAIN_SCOPE) isolates each repo's thoughts.
Embedding dim and the schema
The schema ships with a {{EMBED_DIM}} placeholder that is substituted at scaffold time (default: 1536). The default Ollama model (gte-qwen2-1.5b-instruct) and the default OpenRouter model (openai/text-embedding-3-small) both produce 1536-dim vectors, so the default schema works against every default backend out of the box. Users who want a 1024-dim local model (e.g. mxbai-embed-large) substitute {{EMBED_DIM}}=1024 at scaffold time and override OLLAMA_MODEL=mxbai-embed-large in their .env.
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.
- 4d ago First seen · 715 lines · 75 tokens per session scan A be5e03b4393d
mybrain-setup is a skill published in the GitHub repository robertsfeir/mybrain (0 stars, last pushed 3mo ago), licensed Apache-2.0. It adds 75 tokens to every session and 9,059 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 2 findings (makes network calls, runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
knowledge-ingest
Ingest or update a codebase in the agent-knowledge base. First run bootstraps the knowledge base from scratch; subsequent runs are incremental (only changed/new/deleted files reprocessed). Uses tree-sitter for zero-token structural extraction. Trigger on "/knowledge-ingest", "ingest this codebase", "load this into…
llm-wiki
The foundational knowledge distillation pattern for building and maintaining an AI-powered Obsidian wiki. Based on Andrej Karpathy's LLM Wiki architecture. Use this skill whenever the user wants to understand the wiki pattern, set up a new knowledge base, or needs guidance on the three-layer architecture (raw sources…
wegent-knowledge
Knowledge base management and search tools for Wegent. Provides capabilities to list, create, update, and search knowledge bases and documents using RAG retrieval. Use this skill when the user wants to manage knowledge bases, documents, or search for information programmatically.
karpathy-llm-wiki
Use when building or maintaining a personal LLM-powered knowledge base. Triggers: ingesting sources into a wiki, querying wiki knowledge, linting wiki quality, 'add to wiki', 'what do I know about', or any mention of 'LLM wiki' or 'Karpathy wiki'.
knowledge-base-interop
Two-layer knowledge architecture — curate in LLM Wiki, search in Astra KB. Covers input classification, source-to-wiki ingestion, wiki-to-KB export (batch + realtime), semantic chunking, SAG extraction, health checks, and multi-format export.
memory-systems
This skill should be used for persistent semantic memory in agent systems: cross-session knowledge retention, entity tracking, temporal validity, graph or vector retrieval, memory consolidation, and memory benchmark selection. Route file-backed scratchpads to filesystem-context, handoff summaries to…