skilld
All skills
garrytan avatar

/setup-gbrain

@730a101 official
by Garry Tangarrytan/gstack135k stars
20,051

Set up gbrain for this coding agent: install the CLI, initialize a local PGLite or Supabase brain, register MCP, capture per-remote trust policy. (gstack)

Requires /gstack-upgrade /plan-tune /retro /ship /qa-only /document-generate /context-save /learn /qa /review /investigate

Ask your Agent

Use this Skill: https://skilld.dev/gh/garrytan/gstack/setup-gbrain

This session only. Nothing lands on disk.

sectionstranscript-gate.md

≈762 tokens on demand. Your agent reads this file only when SKILL.md points to it.

<!-- AUTO-GENERATED from transcript-gate.md.tmpl — do not edit directly --> <!-- Regenerate: bun run gen:skill-docs -->

After memory sync is wired (Step 7) but before persisting the CLAUDE.md config (Step 8), offer to bring this Mac's coding-agent transcripts + curated ~/.gstack/ artifacts into gbrain so the retrieval surface (per-skill manifests, salience block) has data to surface.

Run the probe to size the operation:

bun run ~/.claude/skills/gstack/bin/gstack-memory-ingest.ts --probe

Read the output. If Total files in window: 0, skip — there's nothing to ingest. Set gstack-config set transcript_ingest_mode incremental silently and continue to Step 8.

If New (never ingested) is < 200 AND total bytes are < 100MB: silent bulk via bun run ~/.claude/skills/gstack/bin/gstack-memory-ingest.ts --bulk --quiet. Set transcript_ingest_mode=incremental and continue.

Otherwise (the "many transcripts on disk" path): AskUserQuestion with the exact counts AND the value promise. Default scope is current repo only, last 90 days:

"Found <N_repo> transcripts in THIS repo (<repo-slug>) over the last 90 days, plus <N_other> across other repos on this machine (<bytes> total if all ingested). Ingest THIS repo's transcripts into gbrain?

What you get after this: every gstack skill auto-loads recent salience from your past sessions in this repo, so the agent finds your prior work without you describing it. You can query 'what was I doing on day X' and get a real answer. Per-session pages are searchable, taggable, and deletable. Secret scanning runs before any push.

What stays the same: nothing leaves your machine unless gbrain sync is enabled (Step 7). Per-repo trust policies still apply.

Multi-Mac note: if you HAVE enabled brain sync (Step 7), these transcript pages will sync across your Macs. Caveat: deleting a transcript page later removes it from gbrain but git history retains it in prior commits. Use gstack-transcript-prune to delete in bulk; use git filter-repo on the brain remote for hard-delete from history."

Options:

  • A) Yes — this repo, last 90 days (recommended; ~est min)
  • B) Yes — this repo, ALL history
  • C) Yes — this repo + other repos on this machine
  • D) Skip historical, track new from now (transcript_ingest_mode=incremental)
  • E) Never ingest transcripts (transcript_ingest_mode=off)

After answer:

~/.claude/skills/gstack/bin/gstack-config set transcript_ingest_mode <choice>
bun run ~/.claude/skills/gstack/bin/gstack-gbrain-sync.ts --full --no-brain-sync

(--no-brain-sync because Step 7 already wired that path; this just runs the code import + memory ingest stages. Brain-sync will run on the next preamble hook.)

If A/D/E, ingest is incremental from this point on; preamble-boundary hook runs bun run ~/.claude/skills/gstack/bin/gstack-gbrain-sync.ts --incremental --quiet on every skill start (cheap mtime fast-path).

Reference doc for users: setup-gbrain/memory.md (linked from CLAUDE.md Step 8).

Source: SKILL.md on GitHub

Third-party checks

1 warning1d3 checks · Risk SAFE
  • Gen Agent Trust Hub1d

    This skill automates the setup of gbrain, a persistent knowledge base for coding agents. It handles CLI installation, database initialization, and MCP tool registration while maintaining high standards for credential security and data integrity.

  • Socket1d

    2 alerts: gptAnomaly

  • Snyk1d

    Risk: LOW · No issues

Provenance

Signed by skilld at 730a101. This ties the file your Agent reads to that commit on GitHub. It does not review the instructions.

Last checked against GitHub 15 hours ago.

Activeupdated last week

Capability

What it can do
Runs commands Reads files Edits files
preamble-tier
2
version
1.0.0
All 7 allowed tools
BashReadWriteEditGlobGrepAskUserQuestion
Other metadata
triggers
[
  "setup gbrain",
  "install gbrain",
  "connect gbrain",
  "start gbrain",
  "configure gbrain"
]

Topics

README badge

README badge for garrytan/gstack/setup-gbrain

What it does

Installs the gbrain CLI, initializes a local PGLite or Supabase database backend, registers it as an MCP server, and configures per-remote trust policies. Targets developers who want to set up gbrain as a persistent knowledge store for Claude or other AI agents in a single command.

Generated from the current SKILL.md.

Frequently asked

What does this skill actually install?
It installs the gbrain CLI, initializes a local PGLite or Supabase database as the brain backend, registers it as an MCP server, and configures trust policies for remote connections.
Do I need Supabase, or can I use a local database?
You can choose either PGLite (local, no external service) or Supabase. The skill prompts you to pick during setup.
What happens if gbrain is already installed?
The skill checks for existing installations and updates or reconfigures as needed. It does not overwrite your settings without confirmation.
After setup, can this agent call gbrain directly?
Yes. Once the skill finishes, gbrain runs as an MCP server and this agent can invoke it for memory and knowledge operations.
Does this work in headless/CI environments?
The skill adapts based on session kind (interactive, headless, spawned). In headless mode, it avoids interactive prompts and blocks on user input.

Generated from the current SKILL.md. These answers refresh after source changes.