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-toolkitgit 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 | $0.00008 | $0.01762 |
| Opus 5 | $0.00004 | $0.00881 |
| Sonnet 5 | $0.00002 | $0.00352 |
| Haiku 4.5 | $0.00001 | $0.00176 |
Grade D, and why
setup-toolkit scanned grade D with 2 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.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
cat > .claude/hooks/init-transition.sh << 'HOOK_EOF' Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
"Bash(rm -rf:*)", How it starts
The opening of the file, as written. The whole thing — 272 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are helping set up Claude Code configuration for a project.
Project Setup Workflow
Step 1: Detect Project Context
First, examine the current directory to understand the project type:
pwd
ls -la
Look for indicators:
- Web project: package.json, Django files (manage.py, settings.py), templates/
- Python project: pyproject.toml, setup.py, requirements.txt
- Quant/Trading: mentions of trading, strategies, backtesting
- General: anything else
Step 2: Ask User for Configuration
Use AskUserQuestion to determine:
-
Project type (affects which plugins to enable):
- General development (system, workflow, memory, development)
- Web development (+ web-development)
- Quantitative/Trading (+ quant)
- Multiple types (let them select multiple)
-
MCP servers (which ones to enable):
- Chrome DevTools (browser automation, web testing)
- Serena (semantic code understanding)
- Context7 (documentation access)
- All standard servers
-
Permissions (optional):
- Standard (allow common operations)
- Strict (ask for most operations)
- Custom (ask user to specify later)
Step 3: Create Directory Structure
mkdir -p .claude/hooks
mkdir -p .claude/transitions
Step 4: Create Transition Hook
Create .claude/hooks/init-transition.sh:
cat > .claude/hooks/init-transition.sh << 'HOOK_EOF'
#!/bin/bash
# Initialize hourly transition file for session progress tracking
set -e
PROJECT_ROOT="$(git rev-parse --show-toplevel 2>/dev/null || pwd)"
TRANSITIONS_DIR="$PROJECT_ROOT/.claude/transitions"
TODAY=$(date +%Y-%m-%d)
HOUR=$(date +%H)
TODAY_DIR="$TRANSITIONS_DIR/$TODAY"
HOURLY_FILE="$TODAY_DIR/${HOUR}.md"
mkdir -p "$TODAY_DIR"
if [ ! -f "$HOURLY_FILE" ]; then
echo "# Session Progress: $TODAY ${HOUR}:00" > "$HOURLY_FILE"
echo "" >> "$HOURLY_FILE"
echo "---" >> "$HOURLY_FILE"
echo "" >> "$HOURLY_FILE"
fi
exit 0
HOOK_EOF
chmod +x .claude/hooks/init-transition.sh
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 · 272 lines · 8 tokens per session scan D a1fdb68b0a86
setup-toolkit is a command published in the GitHub repository stefan-jansen/claude-code-toolkit (85 stars, last pushed 1mo ago), licensed MIT. It adds 8 tokens to every session and 1,762 once invoked, about $0.0000 per session on Opus 5. A static security scan graded it D with 2 findings (reads agent configuration directories, recursive force delete). 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.