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 agentmods add commands/stefan-jansen/claude-code-toolkit/setup-javascriptgit clone --depth 1 https://github.com/stefan-jansen/claude-code-toolkitWhat 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 | $0.00017 | $0.00998 |
| Opus 5 | $0.00009 | $0.00499 |
| Sonnet 5 | $0.00003 | $0.00200 |
| Haiku 4.5 | $0.00002 | $0.00100 |
Grade A, and why
setup:javascript scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
JavaScript Project Setup
I'll set up a new JavaScript/Node.js project with Jest, ESLint, Prettier, and the Claude Code Framework.
# Constants
readonly CLAUDE_DIR=".claude"
PROJECT_NAME="${1}"
# If no project name provided, use current directory name
if [ -z "$PROJECT_NAME" ]; then
PROJECT_NAME=$(basename "$PWD")
fi
echo "🌐 Setting up JavaScript/Node.js project: $PROJECT_NAME"
echo ""
# Create directory structure
mkdir -p src
mkdir -p tests
# Create package.json
cat > package.json << EOF
{
"name": "$PROJECT_NAME",
"version": "0.1.0",
"description": "A JavaScript project",
"main": "src/index.js",
"scripts": {
"start": "node src/index.js",
"test": "jest",
"lint": "eslint src/",
"format": "prettier --write src/"
},
"devDependencies": {
"jest": "^29.0.0",
"eslint": "^8.0.0",
"prettier": "^3.0.0",
"@types/node": "^20.0.0"
},
"keywords": [],
"author": "",
"license": "ISC"
}
EOF
# Create main source file
cat > src/index.js << EOF
/**
* Main entry point for $PROJECT_NAME
*/
function main() {
console.log("Hello from $PROJECT_NAME!");
}
if (require.main === module) {
main();
}
module.exports = { main };
EOF
# Create test file
cat > tests/index.test.js << EOF
const { main } = require('../src/index');
describe('main function', () => {
test('should run without errors', () => {
expect(() => main()).not.toThrow();
});
});
EOF
# Create .gitignore
cat > .gitignore << 'EOF'
# Node
node_modules/
npm-debug.log*
yarn-debug.log*
yarn-error.log*
package-lock.json
yarn.lock
# Testing
coverage/
.nyc_output/
# Build
dist/
build/
*.tgz
# IDE
.vscode/
.idea/
*.swp
*.swo
*~
# OS
.DS_Store
Thumbs.db
# Environment
.env
.env.local
.env.*.local
# Logs
logs/
*.log
EOF
echo "✅ JavaScript project structure created"
echo ""
echo "🔧 Adding Claude Code Framework..."
# Create .claude directory structure (using shared-setup-patterns skill)
mkdir -p $CLAUDE_DIR/work
mkdir -p $CLAUDE_DIR/memory
mkdir -p $CLAUDE_DIR/reference
mkdir -p $CLAUDE_DIR/hooks
# Generate security hooks from shared skill
echo "I'll create .claude/settings.json with security hooks from the shared-setup-patterns skill."
# Create project CLAUDE.md
cat > CLAUDE.md << EOF
# $PROJECT_NAME
JavaScript/Node.js project with modern tooling.
## Project Knowledge
@.claude/memory/project_state.md
@.claude/memory/dependencies.md
@.claude/memory/conventions.md
@.claude/memory/decisions.md
## Current Work
@.claude/work/current/README.md
EOF
# Generate memory files from shared skill templates
echo "I'll create memory files (.claude/memory/*) using templates from the shared-setup-patterns skill."
# Create work README
cat > $CLAUDE_DIR/work/current/README.md << 'EOF'
# Current Work
Track active development tasks here. Use work units for larger features:
.claude/work/current/ ├── 001_feature_name/ │ ├── requirements.md │ ├── implementation.md │ └── notes.md
EOF
echo ""
echo "✅ JavaScript project setup complete!"
echo ""
echo "Next steps:"
echo " 1. cd into project directory (if not already there)"
echo " 2. npm install (or: yarn install, pnpm install)"
echo " 3. npm test"
echo " 4. npm start"
echo ""
echo "Project structure:"
echo " src/ - Source code"
echo " tests/ - Test files"
echo " .claude/ - Claude framework"
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.
- yesterday First seen · 183 lines · 17 tokens per session scan A e5928d2b592a
setup:javascript is a command published in the GitHub repository stefan-jansen/claude-code-toolkit (85 stars, last pushed 1mo ago), licensed MIT. It adds 17 tokens to every session and 998 once invoked, about $0.0001 per session on Opus 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 2026-08-30.
Other commands, from other repositories
remember
Save something to agent memory - picks project or user scope automatically from context.
disambiguate-plan
Thorough collaborative planning with iterative disambiguation - resolves all ambiguity before planning.
pr-review
Review a GitHub pull request: analyzes changed files to select relevant reviewers, loads project and user memory, runs reviewers in parallel, lets the user pick which findings to post, then submits the review on behalf of the user via gh CLI.
dataviz
Define chart types, color encoding, and data display conventions.
ship
Pre-launch gate — six-domain checklist before any production deployment.
build
Implement the next ready task from .forge/tasks.yaml using TDD discipline.