Agent skill

Spellbook Setup

by kid-sid in kid-sid/claude-spellbook

A skill your agent uses when installing claude-spellbook for the first time, setting up skills/agents/commands globally or into a specific project, registering the memorymap MCP server, enabling…

MITAuto-check passedAgent Workflows

Install Spellbook Setup

skills CLI
$ npx skills add kid-sid/claude-spellbook --skill spellbook-setup -a claude-code

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

GitHub CLI
$ gh skill install kid-sid/claude-spellbook spellbook-setup --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/kid-sid/claude-spellbook.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/spellbook-setup .claude/skills/spellbook-setup && 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
spellbook-setup
GitHub stars
189
Token cost
~2.4k tokens
SKILL.md length
731 words
Files
1
Skills in repo
54
Repo updated
First seen
Licence
MIT

At a glance

A skill your agent uses when installing claude-spellbook for the first time, setting up skills/agents/commands globally or into a specific project, registering the memorymap MCP server, enabling…

  • Works in 6 steps: Skills → Agents → Slash Commands → …
  • Installing claude-spellbook for the first time
  • SKILL.md covers When to Activate, Prerequisites, Clone the Repo and Global Install (Recommended), plus 6 more sections
  • Calls claude, git and bash

What it does

Spellbook Setup is an agent skill from kid-sid/claude-spellbook. Use when installing claude-spellbook for the first time, setting up skills/agents/commands globally or into a specific project, registering the memorymap MCP server, enabling lifecycle hooks, or migrating an existing install to a new machine.

Its SKILL.md is about 2.4k 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 Agent Workflows, covering MCP servers. It works with Model Context Protocol and Python. The repository describes itself as: A curated collection of skills, prompts, and workflows that extend Claude's capabilities — your personal grimoire for AI-powered development. The licence is MIT.

When your agent uses it

  • Installing claude-spellbook for the first time
  • Setting up skills/agents/commands globally
  • Into a specific project
  • Registering the memorymap MCP server

Example prompts

  • “/spellbook-setup”

Requirements

  • Python 3

Workflow steps

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

  1. Skills
  2. Agents
  3. Slash Commands
  4. memory_map MCP Server
  5. Lifecycle Hooks
  6. Global CLAUDE.md (Optional)

What it can do on your machine

Read from SKILL.md and the folder at commit a7c2ac9. 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:

    • claude
    • git
    • bash
    • pip
    • make
    • python
    • python3

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

  • Network

    No URLs in SKILL.md. Its commands use git and pip, 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

Spellbook Setup loads about 2.4k tokens when it runs. Until then it costs about 65 tokens; SKILL.md has 731 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~65
When it runs · the whole SKILL.md, loaded when a task matches
~2.4k

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 kid-sid/claude-spellbook at commit a7c2ac9, republished under its MIT licence (© kid-sid). 731 words, ~2,401 tokens.

Download SKILL.mdSave it as .claude/skills/spellbook-setup/SKILL.md (or your agent's skills folder).
name
spellbook-setup
description
Use when installing claude-spellbook for the first time, setting up skills/agents/commands globally or into a specific project, registering the memory_map MCP server, enabling lifecycle hooks, or migrating an existing install to a new machine.

Claude Spellbook Setup

Install and configure claude-spellbook — globally (all projects) or scoped to one project.

When to Activate

  • Installing claude-spellbook on a new machine or for a new user
  • Deciding between global and project-level skill/agent install
  • Setting up the memory_map MCP server for persistent memory
  • Enabling auto-format, safety, and history hooks in settings.json
  • Adding spellbook skills/commands to a single project without touching global config
  • Verifying or repairing an existing spellbook install

Prerequisites

RequirementCheck
Claude Code CLIclaude --version
Gitgit --version
Python 3.9+ (for memory_map)python --version or python3 --version

Clone the Repo

bash
git clone https://github.com/kid-sid/claude-spellbook.git
cd claude-spellbook

Global install puts skills, agents, and commands into ~/.claude/ so they are available in every project without any per-project steps.

Step 1 — Skills
bash
# All skills (recommended — they activate on-demand, no overhead)
cp -r skills/* ~/.claude/skills/

# Single skill
cp -r skills/security ~/.claude/skills/
Step 2 — Agents
bash
cp -r .claude/agents/* ~/.claude/agents/
Step 3 — Slash Commands
bash
cp -r .claude/commands/* ~/.claude/commands/
Step 4 — memory_map MCP Server
bash
# Install from PyPI — bundles the OpenAI client for semantic history search
pip install "memory-map-mcp[embed-openai]"

# Base install — works fine if you stick with local embeddings or BM25 only
# pip install memory-map-mcp

Set the MongoDB URI (required for history; key-value memory falls back to a local file):

bash
# Mac/Linux — add to ~/.zshrc or ~/.bashrc
export MEMORY_MAP_MONGO_URI="mongodb+srv://<user>:<password>@<cluster>.mongodb.net"

# Windows PowerShell — add to $PROFILE
$env:MEMORY_MAP_MONGO_URI = "mongodb+srv://<user>:<password>@<cluster>.mongodb.net"

Register globally:

bash
claude mcp add -s user memory_map -- memory-map-mcp

Verify registration:

bash
claude mcp list

See skills/memory-map/skill.md for full setup (vector search, env vars, troubleshooting).

Step 5 — Lifecycle Hooks

Add to ~/.claude/settings.json (create if absent). The memory-map-hook entry point is installed by the pip package — no need for absolute paths.

json
{
  "hooks": {
    "UserPromptSubmit": [
      { "matcher": "", "hooks": [{ "type": "command", "command": "memory-map-hook", "timeout": 10 }] }
    ],
    "PreCompact": [
      { "matcher": "", "hooks": [{ "type": "command", "command": "memory-map-hook --force", "timeout": 15 }] }
    ],
    "Stop": [
      { "matcher": "", "hooks": [{ "type": "command", "command": "memory-map-hook --force", "timeout": 15, "async": true }] }
    ]
  }
}
Step 6 — Global CLAUDE.md (Optional)

Append to ~/.claude/CLAUDE.md to load memory in every project:

markdown
## Session Setup (Required)
At the start of every session, before doing anything else:
1. Call `load_memory` with the current working directory
2. Call `suggest_history` with the current working directory and the user's first message
3. Read both outputs before exploring files or asking questions

Project-Level Install

Project-level keeps spellbook assets inside one repo. Use this when: the team shares a specific subset of skills, you want version-controlled agents per repo, or you can't modify global config.

Skills (project-scoped)
bash
# All skills
cp -r /path/to/claude-spellbook/skills/* .claude/skills/

# Selected skills only
mkdir -p .claude/skills
cp -r /path/to/claude-spellbook/skills/security .claude/skills/
cp -r /path/to/claude-spellbook/skills/api-design .claude/skills/
Agents and Commands
bash
mkdir -p .claude/agents .claude/commands
cp /path/to/claude-spellbook/.claude/agents/* .claude/agents/
cp /path/to/claude-spellbook/.claude/commands/* .claude/commands/
Project Hooks
bash
# Copy spellbook's hooks config into the project (review before committing)
cp /path/to/claude-spellbook/.claude/settings.local.json .claude/settings.local.json

settings.local.json enables auto-format on write/edit, bash command logging, and safety guards. Add to .gitignore if the hooks reference local paths; commit if they are path-agnostic.

Tool Configs
bash
# Install formatter/linter configs for one language
bash /path/to/claude-spellbook/tools/install.sh python --target .
bash /path/to/claude-spellbook/tools/install.sh typescript --target .

# All languages
bash /path/to/claude-spellbook/tools/install.sh all --target .

Or via Makefile:

bash
make setup TARGET=. LANG=python
Per-Project Memory (CLAUDE.md)

Add this block to CLAUDE.md at the project root (create the file if absent):

markdown
## Session Setup (Required)
At the start of every session, before doing anything else:
1. Call `load_memory` with the current working directory
2. Call `suggest_history` with the current working directory and the user's first message
3. Read both outputs before exploring files or asking questions

Commit CLAUDE.md so all teammates get session-start memory loading.


Scope Decision Matrix

GoalGlobalProject
Use skills in all your projects✓—
Share agents with the whole team—✓ (commit .claude/agents/)
Keep skills out of the repo✓—
Audit/pin agent versions per project—✓
Memory + history in every project✓ (hooks + global MCP)—
One-off test of a new skill—✓
Personal MCP server (private API keys)✓ (-s user)—
Shared MCP server (team tooling)—✓ (-s project)

Verify the Install

bash
# Skills are visible
ls ~/.claude/skills/         # global
ls .claude/skills/           # project

# Agents are visible
ls ~/.claude/agents/         # global
ls .claude/agents/           # project

# Commands are visible
ls ~/.claude/commands/       # global
ls .claude/commands/         # project

# MCP server is registered
claude mcp list

# Hooks are present
cat ~/.claude/settings.json  # look for "hooks" key

Open a new Claude Code session and describe a task — the relevant skill should activate automatically (no manual invocation needed).


Updating

bash
cd claude-spellbook
git pull

# Re-copy to overwrite outdated files
cp -r skills/* ~/.claude/skills/
cp -r .claude/agents/* ~/.claude/agents/
cp -r .claude/commands/* ~/.claude/commands/

Skills and agents are plain markdown — no restart required after updating.


Show full SKILL.md (341 more words)Show less

Red Flags

  • Registering memory_map with -s project instead of -s user — project-scoped MCP servers are stored in .claude/mcp.json and apply to everyone who clones the repo; memory_map uses local paths that differ per machine; always register with -s user
  • Copying settings.local.json into a shared repo without reviewing paths — hooks may reference absolute paths to local formatters or scripts; paths that exist on your machine may not exist on a teammate's; audit every command value before committing
  • Installing all 50+ skills globally then wondering why context is slow — skills are loaded on-demand by description matching, not all at once; installing everything globally has no performance cost; if load times feel slow, the issue is elsewhere (large CLAUDE.md, slow MCP server)
  • Omitting CLAUDE.md in a project after setting up memory_map — without CLAUDE.md, Claude won't call load_memory at session start even if the MCP server is registered; the file is what triggers the session setup routine
  • Using hardcoded Windows paths in hooks for a cross-platform team — C:/Users/yourname/... hooks break on Mac/Linux; either use relative paths, an env var ($HOME), or keep lifecycle hooks in ~/.claude/settings.json (personal) rather than .claude/settings.json (shared)
  • Not gitignoring .claude/settings.local.json — this file is for personal overrides and local tool paths; committing it forces your local paths onto teammates; add it to .gitignore
  • Forgetting to add a timeout to hooks — a hook that hangs (e.g., slow Python startup, network call) blocks Claude Code indefinitely; every hook command must have "timeout": N

Checklist

  • claude --version confirms Claude Code is installed
  • Repo cloned: git clone https://github.com/kid-sid/claude-spellbook.git
  • Skills copied to ~/.claude/skills/ (global) or .claude/skills/ (project)
  • Agents copied to ~/.claude/agents/ or .claude/agents/
  • Slash commands copied to ~/.claude/commands/ or .claude/commands/
  • pip install memory-map-mcp succeeded; memory-map-mcp is on PATH
  • MEMORY_MAP_MONGO_URI exported in shell profile
  • memory_map registered: claude mcp list shows memory_map
  • Lifecycle hooks added to ~/.claude/settings.json with timeout values
  • CLAUDE.md present at project root with the session-setup block
  • .claude/settings.local.json added to .gitignore if hooks use local paths
  • Tool configs installed for the project's language stack
  • New Claude Code session opened — a relevant skill activates automatically on first task

© kid-sid, MIT. 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 skills/spellbook-setup of kid-sid/claude-spellbook.

Open the folder on GitHubat commit a7c2ac9

Compare with similar skills

Spellbook Setup 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.

Spellbook Setup compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Spellbook Setup this skillkid-sid/claude-spellbook189—~2.4kAutomated safety check: PassMIT
MCP Server Builderanthropics/skills180k62 repos~2.3kAutomated safety check: PassApache-2.0
MCP Server BuildershareAI-lab/learn-claude-code78k5 repos~1.2kAutomated safety check: PassMIT
Fastmcp Client CLIPrefectHQ/fastmcp28k1 repos~823Automated safety check: PassApache-2.0
MemPalace Setup and OperationMemPalace/mempalace59k—~2.2kAutomated safety check: PassMIT
FastmcpTommy-yw/RunbookHermes5463 repos~2.1kAutomated safety check: PassMIT

Similar skills

  • MCP Server Builder

    anthropics/skills

    Official

    Guides the design and implementation of Model Context Protocol servers in TypeScript or Python, from tool naming and error messages to evaluation.

    180k GitHub starsUsed in 62 repos~2.3k tokens
    Agent WorkflowsAuto-check passed
  • MCP Server Builder

    shareAI-lab/learn-claude-code

    Walks through building MCP servers in Python or TypeScript that expose tools, resources and prompts to Claude, with templates, registration and testing.

    78k GitHub starsUsed in 5 repos~1.2k tokens
    Agent WorkflowsAuto-check passed
  • Fastmcp Client CLI

    PrefectHQ/fastmcp

    Query and invoke tools on MCP servers using fastmcp list and fastmcp call.

    28k GitHub starsUsed in 1 repo~823 tokens
    Agent WorkflowsAuto-check passed
  • Installs and configures MemPalace as a private local palace, a shared-brain hub or a client of an existing hub, including MCP registration and version-correct initialization.

    59k GitHub stars~2.2k tokensUpdated today
    Agent WorkflowsAuto-check passed
  • Fastmcp

    Tommy-yw/RunbookHermes

    Build, test, inspect, install, and deploy MCP servers with FastMCP in Python.

    546 GitHub starsUsed in 3 repos~2.1k tokens
    Agent WorkflowsAuto-check passed
  • Migrate To Archestra

    archestra-ai/archestra

    Migrate an existing agentic PoC/pilot (Claude Code project files, MCP configs, hooks, local tools, openclaw config, or similar hand-rolled setup artifacts) into an Archestra instance.

    4.3k GitHub stars~2.6k tokensUpdated today
    Agent WorkflowsAuto-check passed

More from kid-sid/claude-spellbook

All 54 skills in this repo
  • Accessibility

    kid-sid/claude-spellbook

    A skill your agent uses when building or reviewing UI components for keyboard and screen reader compatibility, adding ARIA to custom widgets, auditing a page for WCAG AA conformance, or preparing…

    189 GitHub stars~3.2k tokensUpdated 2 mo ago
    Auto-check passed
  • Agentex

    kid-sid/claude-spellbook

    A skill your agent uses when building, wiring, or debugging an Agentex agent — choosing agent type, configuring acp.py and manifest.yaml, using adk.messages or adk.state, or resolving…

    189 GitHub stars~2.2k tokensUpdated 2 mo ago
    Auto-check: notes
  • AI Engineer

    kid-sid/claude-spellbook

    A skill your agent uses when building production LLM applications — designing RAG pipelines, choosing vector databases, implementing agent orchestration, optimizing cost, or adding AI safety…

    189 GitHub stars~3.7k tokensUpdated 2 mo ago
    Auto-check passed
  • Angular

    kid-sid/claude-spellbook

    A skill your agent uses when building or refactoring Angular applications — choosing between signals, RxJS, and NgRx for state, configuring routing with guards and lazy loading, optimizing change…

    189 GitHub stars~5k tokensUpdated 2 mo ago
    Auto-check passed
  • API Design

    kid-sid/claude-spellbook

    A skill your agent uses when designing new REST endpoints, reviewing an existing API contract, adding pagination or filtering, planning a versioning strategy, or building a public or partner-facing…

    189 GitHub stars~3.6k tokensUpdated 2 mo ago
    Auto-check passed
  • Auth

    kid-sid/claude-spellbook

    A skill your agent uses when implementing login flows, issuing or validating JWTs, setting up OAuth2/OIDC with a provider, designing role-based or attribute-based access control, securing API…

    189 GitHub stars~3.2k tokensUpdated 2 mo ago
    Auto-check passed

Categories

Questions about Spellbook Setup

What does Spellbook Setup do?

A skill your agent uses when installing claude-spellbook for the first time, setting up skills/agents/commands globally or into a specific project, registering the memorymap MCP server, enabling…. Spellbook Setup is an agent skill from kid-sid/claude-spellbook. Use when installing claude-spellbook for the first time, setting up skills/agents/commands globally or into a specific project, registering the memorymap MCP server, enabling lifecycle hooks, or migrating an existing install to a new machine.

When should I use Spellbook Setup?

Spellbook Setup fits situations like: installing claude-spellbook for the first time; setting up skills/agents/commands globally; into a specific project; registering the memorymap MCP server.

How do I install Spellbook Setup in Claude Code?

Run `npx skills add kid-sid/claude-spellbook --skill spellbook-setup -a claude-code`. Or copy the skill folder (skills/spellbook-setup in kid-sid/claude-spellbook) into .claude/skills/spellbook-setup in your project. Claude Code loads it when a task matches its description.

How do I install Spellbook Setup in Codex?

Run `npx skills add kid-sid/claude-spellbook --skill spellbook-setup -a codex`. Or copy the skill folder (skills/spellbook-setup in kid-sid/claude-spellbook) into .agents/skills/spellbook-setup in your project. Codex loads it when a task matches its description.

Can I use Spellbook Setup 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 kid-sid/claude-spellbook --skill spellbook-setup -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/spellbook-setup, .gemini/skills/spellbook-setup, .github/skills/spellbook-setup and .opencode/skills/spellbook-setup in your project.

What does Spellbook Setup need to run?

Going by SKILL.md and its folder, Spellbook Setup needs the command-line tools its instructions call (claude, git, bash, pip, make and python). Our summary lists: Python 3.

Does Spellbook Setup access the network?

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

Is Spellbook Setup 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 Spellbook Setup use?

Spellbook Setup is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Spellbook Setup use?

About 2.4k tokens (SKILL.md is roughly 9.6k 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 Spellbook Setup?

Skills that share tags, products or a category with Spellbook Setup: MCP Server Builder (anthropics/skills, 180k stars), MCP Server Builder (shareAI-lab/learn-claude-code, 78k stars), Fastmcp Client CLI (PrefectHQ/fastmcp, 28k stars) and MemPalace Setup and Operation (MemPalace/mempalace, 59k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Spellbook Setup?

kid-sid (a GitHub user) maintains it in kid-sid/claude-spellbook, which has 189 GitHub stars. The repository holds 54 skills in this directory. The repository was last updated on August 5, 2026.

Source: kid-sid/claude-spellbook on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.