GBrain is a memory and retrieval layer for AI agents that searches, connects, and synthesizes information from stored sources. It is used to give coding agents and autonomous agents access to knowledge beyond their current code, including shared company information with access controls. The catalogue add-ons help agents operate GBrain and connect it to agent workflows.
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 skills add garrytan/gbrain --skill smoke-testgit clone --depth 1 https://github.com/garrytan/gbrainWrote 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/garrytan/gbrain/smoke-test)<a href="https://agentmods.dev/skills/garrytan/gbrain/smoke-test"><img src="https://agentmods.dev/badge/skills/garrytan/gbrain/smoke-test/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.
<a href="https://agentmods.dev/skills/garrytan/gbrain/smoke-test"><img src="https://agentmods.dev/badge/skills/garrytan/gbrain/smoke-test.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- Snyk pass
- NVIDIA SkillSpector warn
SkillSpector: 2 findings, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Rogue Agent · line 82 Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
- medium Rogue Agent · line 99 Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
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 | $0.00079 | $0.01929 |
| Opus 5.5 | $0.00032 | $0.00772 |
| Sonnet 5.5 | $0.00016 | $0.00386 |
| Haiku 4.5 | $0.00008 | $0.00193 |
Grade A, and why
smoke-test 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 13d 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 — 189 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Smoke Test Skillpack
Run
gbrain smoke-testafter any machine or container restart, or whenever something seems broken.
Contract
This skill guarantees:
- 8 core tests verify gbrain health after restart (plus OpenClaw services when present; skipped otherwise)
- Bounded local failures are auto-fixed before reporting; worker repair is explicit because process topology and shell-job policy are operator choices
- User-extensible via
~/.gbrain/smoke-tests.d/*.shdrop-in scripts - Results logged to
/tmp/gbrain-smoke-test.log - Exit code = number of unfixed failures (0 = all pass)
Built-in Tests
| # | Test | Auto-Fix |
|---|---|---|
| 1 | Bun runtime | Install from bun.sh |
| 2 | GBrain CLI loads | Reinstall deps |
| 3 | GBrain database (engine identity via gbrain engine status --json, then doctor --json's connection check) |
gbrain db-repair --yes, re-test |
| 4 | GBrain worker process | — (native supervisor status + duplicate detection) |
| 5 | OpenClaw Codex plugin (Zod CJS); skips if OpenClaw absent | npm install zod@4 --force |
| 6 | OpenClaw gateway; skips if OpenClaw absent | — (may not be started yet) |
| 7 | Embedding API key | — (check .env) |
| 8 | Brain repo exists | — |
Usage
CLI
gbrain smoke-test
This is the invocation for all installs; it resolves the test script from the installed package.
From any startup script or login hook
gbrain smoke-test >> /tmp/bootstrap.log 2>&1
From OpenClaw bootstrap (OpenClaw deployments only)
Add to your ensure-services.sh or equivalent:
bash /path/to/gbrain/scripts/smoke-test.sh >> /tmp/bootstrap.log 2>&1
From an agent
exec: gbrain smoke-test
Contributor note: inside a gbrain repo checkout you can also run the script
directly with bash scripts/smoke-test.sh.
Adding Custom Tests
Create executable scripts in ~/.gbrain/smoke-tests.d/:
# ~/.gbrain/smoke-tests.d/check-redis.sh
#!/bin/bash
redis-cli ping | grep -q PONG
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.
- 13d ago Changed bb1b3a4ea18c
- 14d ago Changed · +1 lines d536d1c89b44
- 16d ago Changed · +8 lines be2ff40493d5
- 1mo ago First seen · 180 lines · 79 tokens per session scan A 3e1b0c180d40
smoke-test is a skill published in the GitHub repository garrytan/gbrain (31,034 stars, last pushed today), licensed MIT. It adds 79 tokens to every session and 1,929 once invoked, about $0.0003 per session on Opus 5.5. 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 2026-09-03.
Other skills, from other repositories
docker-docs
Comprehensive Docker 28.x reference covering all features: installation, Dockerfile instructions, multi-stage builds, Docker Compose, networking, volumes, CLI commands, image management, registries, security best practices, CI/CD integration, debugging, and Kubernetes migration. Use whenever the user mentions Docker…
kubestellar-console
Multi-cluster Kubernetes dashboard with AI-powered operations via MCP server and 10+ built-in agent skills.
ci-debug-workflow
Debug failing CI pipelines, containers, and reproduce bugs locally. Use when CI is red, containers won't start, or need to reproduce bugs.
deployment-patterns
Deployment workflows, CI/CD pipeline patterns, Docker containerization, health checks, rollback strategies, and production readiness checklists for web applications. Use when setting up deployment infrastructure or planning releases.
operating-github-ci-fixer
Use when the user asks OpenSRE to fix failing GitHub CI, GitHub Actions checks, failing pull request checks, a broken PR branch, or CI on a named branch such as main.
analyze-ci
Analyze failed GitHub Action jobs for a pull request.