Agent skill

Relaunch

by naveedharri in naveedharri/baalda

Kill the running Baalda desktop (Tauri) dev instance AND the backend server, then launch fresh instances of both.

Apache-2.0Auto-check passedKnowledge Management

Install Relaunch

skills CLI
$ npx skills add naveedharri/baalda --skill relaunch -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install naveedharri/baalda relaunch --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/naveedharri/baalda.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.agents/skills/relaunch .claude/skills/relaunch && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
relaunch
GitHub stars
155
Token cost
~870 tokens
SKILL.md length
415 words
Files
1
Skills in repo
3
Repo updated
First seen
Licence
Apache-2.0

At a glance

Kill the running Baalda desktop (Tauri) dev instance AND the backend server, then launch fresh instances of both.

  • Works in 5 steps: Kill the running instances → Make sure Postgres is up → Launch the backend server → …
  • The user says relaunch
  • SKILL.md covers Steps and Notes
  • Calls pnpm, docker and tsx

What it does

Relaunch is an agent skill from naveedharri/baalda. Kill the running Baalda desktop (Tauri) dev instance AND the backend server, then launch fresh instances of both. Use when the user says "relaunch", "restart the app", "kill and relaunch", or wants a clean restart after code/config changes.

Its SKILL.md is about 870 tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in Knowledge Management, covering Second brain. It works with Tauri, PostgreSQL, pnpm and Vite. The repository describes itself as: The team second brain. Plain Markdown files on your disk, edited together in real time, and read and written by your AI like a teammate. The licence is Apache-2.0.

When your agent uses it

  • The user says relaunch
  • Restart the app
  • Kill and relaunch
  • Wants a clean restart after code/config changes

Example prompts

  • “relaunch”
  • “restart the app”
  • “kill and relaunch”
  • “/relaunch”

Requirements

  • Docker

Workflow steps

5 steps, taken from the step headings in SKILL.md.

  1. Kill the running instances
  2. Make sure Postgres is up
  3. Launch the backend server
  4. Launch the desktop
  5. Confirm both came up

What it can do on your machine

Read from SKILL.md and the folder at commit 2e988ad. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Shell commands in SKILL.md call:

    • pnpm
    • docker
    • tsx
    • curl

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md. Its commands use pnpm, docker and curl, which can reach the network depending on how they are called.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Relaunch loads about 870 tokens when it runs. Until then it costs about 62 tokens; SKILL.md has 415 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~62
When it runs · the whole SKILL.md, loaded when a task matches
~870

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from naveedharri/baalda at commit 2e988ad, republished under its Apache-2.0 licence (© naveedharri). 415 words, ~870 tokens.

Download SKILL.mdSave it as .claude/skills/relaunch/SKILL.md (or your agent's skills folder).
name
relaunch
description
Kill the running Baalda desktop (Tauri) dev instance AND the backend server, then launch fresh instances of both. Use when the user says "relaunch", "restart the app", "kill and relaunch", or wants a clean restart after code/config changes.

Relaunch Skill Guide

Kills the current desktop (Tauri) dev process tree and the backend server, then starts fresh instances of both. Postgres (Docker) is left running — restarting the server process does not touch the DB, so no re-seed is needed.

Project: the app/ directory in this Baalda checkout. Resolve paths from the repository root; do not assume a particular clone location.

  • Desktop launch: pnpm run dev:desktop (= pnpm --filter desktop tauri dev; Vite on :1420) from the app root.
  • Server launch: pnpm run dev from app/apps/server/ (tsx watch; HTTP :3010, Hocuspocus WS :3011, GET /health).

Steps

1. Kill the running instances

Inspect the desktop dev chain (dev:desktop → tauri dev → vite → target/debug/desktop) and backend (tsx watch src/index.ts). Use process arguments, parent relationships, and working directories to identify only this Baalda checkout's processes. Stop identified PIDs with SIGTERM, wait for shutdown, and use SIGKILL only for confirmed survivors. Avoid broad pkill patterns that could stop another project's Vite or tsx processes. Skip shutdown if none run.

2. Make sure Postgres is up

The server needs Postgres (Docker, host port 5439). It usually stays up across restarts — only start it if it's missing.

bash
docker ps --filter "publish=5439" --format "{{.Names}} {{.Status}}" || true
# If nothing is listed, from app/apps/server/ run: pnpm run db:up

Do not run pnpm run migrate unless migrations changed, and never run pnpm test in apps/server (it wipes the dev DB / users/orgs/vaults).

3. Launch the backend server

Launch from the server directory with Codex exec_command, using a short yield_time_ms and retaining the returned session ID for startup logs. For a detached process, use subprocess.Popen(..., start_new_session=True) with stdin from DEVNULL and stdout/stderr redirected to a fresh log file in a temporary directory; retain its PID and log path.

bash
# From the repository root:
cd app/apps/server && pnpm run dev
Show full SKILL.md (149 more words)Show less
4. Launch the desktop

Launch from the app root using the same background process approach as the server.

bash
# From the repository root:
cd app && pnpm run dev:desktop
5. Confirm both came up
  • Server (wait ~3–5s): curl -s http://localhost:3010/health returns OK, and the task output shows the HTTP :3010 / Hocuspocus WS listeners started.
  • Desktop (wait ~15–20s; cargo may recompile): tail the background task output. Success looks like:
VITE v7.x ready ...
Running `target/debug/desktop`

If tauri.conf.json or Rust changed, expect a Compiling desktop / Rebuilding application... step before Running target/debug/desktop.

Notes

  • If a process is owned by a Codex exec session, stop that session cleanly as well so its output stream closes. Poll session output with write_stdin.
  • Restarting the server process is safe — it does not re-seed or wipe anything. Only pnpm test in apps/server wipes the DB.
  • A tauri.conf.json edit auto-triggers a rebuild in a running tauri dev, so a full relaunch is only needed when the watcher isn't running or you want a clean slate.

© naveedharri, Apache-2.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in .agents/skills/relaunch of naveedharri/baalda.

Open the folder on GitHubat commit 2e988ad

Compare with similar skills

Relaunch next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Relaunch compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Relaunch this skillnaveedharri/baalda155—~870Automated safety check: PassApache-2.0
Veloxdb Scalable Performanceveloxbase/veloxdb646—~1.7kAutomated safety check: PassMIT
Devinggo Project Inithuagelong/devinggo122—~1.1kAutomated safety check: NotesApache-2.0
Tauri Packagingbkywksj/knowledge-base330—~3.3kAutomated safety check: PassCustom licence
LangBot Core Developmentlangbot-app/LangBot18k—~1.4kAutomated safety check: NotesApache-2.0
Happy Monorepo Dev Guideslopus/happy24k—~1.8kAutomated safety check: PassMIT

Similar skills

  • Guides scalability and performance work for VeloxDB's Tauri + Rust PostgreSQL backend and React + TanStack frontend.

    646 GitHub stars~1.7k tokensUpdated 9 days ago
    DatabasesAuto-check passed
  • Devinggo Project Init

    huagelong/devinggo

    DevingGo 项目初始化与本地开发环境配置流程。用于用户询问项目初始化、开发环境搭建、依赖检查、配置文件生成、数据库迁移、本地启动后端/前端/Worker 服务、或希望 AI 大模型一步步把 DevingGo 跑起来时。适用于基于本项目 CLI、Makefile、manifest/config、hack/config、admin-ui 前端工作区的初始化排障与启动验证。

    122 GitHub stars~1.1k tokensUpdated 3 mo ago
    DatabasesAuto-check: notes
  • Tauri Packaging

    bkywksj/knowledge-base

    Tauri 打包与分发技能,指导桌面端(Windows/macOS/Linux)与移动端(Android/iOS)的构建、签名和分发。

    330 GitHub stars~3.3k tokensUpdated 6 days ago
    MobileAuto-check passed
  • LangBot Core Development

    langbot-app/LangBot

    Covers developing the LangBot core backend and web UI: dev setup, repo layout, API auth types, adding endpoints, migrations and keeping the MCP server in step.

    18k GitHub stars~1.4k tokensUpdated today
    DevelopmentAuto-check: notes
  • Local development guide for the Happy pnpm monorepo: install, build, test and run the CLI, server, Expo app and Tauri desktop packages.

    24k GitHub stars~1.8k tokensUpdated today
    DevelopmentAuto-check passed
  • Desktop Dual Repo Test

    Eynzof/Hermes-CN-Desktop

    A skill your agent uses when starting or verifying Hermes Agent CN Desktop with the latest Hermes-CN-Desktop and Hermes-CN-Core branches — dev smoke test (pnpm tauri:dev), packaged beta/release…

    1.8k GitHub stars~1.8k tokensUpdated 18 days ago
    Testing & QAAuto-check passed

More from naveedharri/baalda

  • Baalda Guide

    naveedharri/baalda

    Answer any question about Baalda (the team second-brain app at baalda.com) in plain, non-technical language — what it is, what it can and cannot do, which file formats it supports (Markdown, images…

    155 GitHub stars~1.8k tokensUpdated today
    Auto-check passed
  • Window Simulator

    naveedharri/baalda

    Run Baalda's real desktop UI in a local browser with synthetic vault data to preview Windows or macOS layouts, investigate visual bugs, and capture screenshots from a Mac.

    155 GitHub stars~1.2k tokensUpdated today
    Auto-check passed

Questions about Relaunch

What does Relaunch do?

Kill the running Baalda desktop (Tauri) dev instance AND the backend server, then launch fresh instances of both. Relaunch is an agent skill from naveedharri/baalda. Kill the running Baalda desktop (Tauri) dev instance AND the backend server, then launch fresh instances of both.

When should I use Relaunch?

Relaunch fits situations like: the user says relaunch; restart the app; kill and relaunch; wants a clean restart after code/config changes.

How do I install Relaunch in Claude Code?

Run `npx skills add naveedharri/baalda --skill relaunch -a claude-code`. Or copy the skill folder (.agents/skills/relaunch in naveedharri/baalda) into .claude/skills/relaunch in your project. Claude Code loads it when a task matches its description.

How do I install Relaunch in Codex?

Run `npx skills add naveedharri/baalda --skill relaunch -a codex`. Or copy the skill folder (.agents/skills/relaunch in naveedharri/baalda) into .agents/skills/relaunch in your project. Codex loads it when a task matches its description.

Can I use Relaunch in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add naveedharri/baalda --skill relaunch -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/relaunch, .gemini/skills/relaunch, .github/skills/relaunch and .opencode/skills/relaunch in your project.

What does Relaunch need to run?

Going by SKILL.md and its folder, Relaunch needs the command-line tools its instructions call (pnpm, docker, tsx and curl). Our summary lists: Docker.

Does Relaunch access the network?

SKILL.md contains no URLs. Its commands use docker and curl, which can reach the network depending on how they are called. This is read from the text; nothing was executed.

Is Relaunch safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Relaunch use?

Relaunch is published under the Apache-2.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Relaunch use?

About 870 tokens (SKILL.md is roughly 3.5k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Relaunch?

Skills that share tags, products or a category with Relaunch: Veloxdb Scalable Performance (veloxbase/veloxdb, 646 stars), Devinggo Project Init (huagelong/devinggo, 122 stars), Tauri Packaging (bkywksj/knowledge-base, 330 stars) and LangBot Core Development (langbot-app/LangBot, 18k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Relaunch?

naveedharri (a GitHub user) maintains it in naveedharri/baalda, which has 155 GitHub stars. The repository holds 3 skills in this directory. The repository was last updated on October 9, 2026.

Source: naveedharri/baalda on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.