Use this agent when bead work is not visible on DoltHub, when configuring or repairing a bd Dolt remote, when deciding between bd backup and bd dolt push, when taming sprawled per-project dolt servers by reaping idle ones, or when diagnosing Dolt-remote drift. It knows the #1 root cause (no remote configured) and that…
Universal Dolt version-control workflow. Step 0 auto-detects what kind of Dolt stack is present — every make and model (classic Dolt repo, live dolt sql-server on its ACTUAL bound port, bd embedded store, Doltgres, DoltLite single-file DB, DumboDB) — and emits a ready-to-use connection descriptor, then routes to work…
Bob's Big Brain — the governed team brain: cited recall, hash-chained receipts. ONE plugin, two modes. Local (default): turn your own files into cited (qmd://) memory with deterministic governance and a tamper-evident SHA-256 hash-chained audit trail, in-process with no runtime network after one-time native dependency.
MCP server "governed-brain" as configured in jeremylongshore/bobs-big-brain-plugin. Runs plugin-runtime/bootstrap.cjs with node. Needs 3 environment variables to run.
Instructions for jeremylongshore/bobs-big-brain-plugin, covering agents.md, what this is, ⚠️ critical constraint — team mode is dependency-free, key files and team-mode server contract (the registrar's apps/api).
Instructions for jeremylongshore/bobs-big-brain-plugin: Agent + developer guidance for this repo lives in AGENTS.md — the single source of truth (what it is, the local|team dual-mode dispatch, govern.ts / seed-policy.ts, the team-mode server contract, build + smokes, the tenant-default gotcha, retrieval roadmap…
Saves a single fact, decision, pattern, or convention into your governed knowledge brain so it can be recalled later — and retires memories that are outdated. Side-effecting: it writes to your durable corpus, so it never auto-fires — invoke it explicitly. Use when you want the brain to remember something specific…
Answers questions about your own systems, notes, decisions, runbooks, and conventions from your governed knowledge brain, returning a qmd:// citation for every claim — receipts, not recall. Use when you want to know what your brain has captured about your own architecture, infrastructure, decisions, or conventions…
AGENTS.md instructions for jeremylongshore/intent-eval-lab, covering agent instructions, quick reference, non-interactive shell commands, force overwrite without prompting and for recursive operations.
Claude Code instructions for jeremylongshore/intent-eval-lab, covering claude.md — intent eval lab, what this is, phase a landed (this repo), phase b/c gate and brand-name policy (partner-consent discipline).