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-transitionsgit 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 | $0.00018 | $0.01093 |
| Opus 5 | $0.00009 | $0.00547 |
| Sonnet 5 | $0.00004 | $0.00219 |
| Haiku 4.5 | $0.00002 | $0.00109 |
Grade B, and why
setup:transitions scanned grade B with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
cat > .claude/hooks/init-transition.sh << 'HOOK_EOF' How it starts
The opening of the file, as written. The whole thing — 163 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Add Session Progress Tracking
This command adds automatic hourly transition file tracking to your project.
What it does:
- Creates
.claude/hooks/init-transition.sh- Hook that creates hourly progress files - Updates
.claude/settings.json- Adds UserPromptSubmit hook - Updates
CLAUDE.md- Adds progress tracking instructions
Implementation
# Check we're in a project with .claude directory
if [ ! -d ".claude" ]; then
echo "❌ No .claude directory found. Run /setup:existing first."
exit 1
fi
echo "🔄 Adding session progress tracking..."
echo ""
# Create hooks directory
mkdir -p .claude/hooks
# Create the transition hook
cat > .claude/hooks/init-transition.sh << 'HOOK_EOF'
#!/bin/bash
# Initialize hourly transition file for session progress tracking
# This hook runs on UserPromptSubmit to ensure the hourly file exists
# Format: .claude/transitions/YYYY-MM-DD/HH.md (e.g., 19.md for 7pm hour)
set -e
# Get project root (where .claude/ directory is)
PROJECT_ROOT="$(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/${HOUR}.md"
# Create today's transition directory if it doesn't exist
mkdir -p "$TODAY_DIR"
# Initialize hourly file if it doesn't exist
if [ ! -f "$HOURLY_FILE" ]; then
cat > "$HOURLY_FILE" << EOF
# Session Progress: $TODAY ${HOUR}:00
---
EOF
fi
# Exit silently (hook output not visible to Claude anyway)
exit 0
HOOK_EOF
chmod +x .claude/hooks/init-transition.sh
echo "✅ Created .claude/hooks/init-transition.sh"
Now update settings.json to add the hook:
# Get absolute path to hook
HOOK_PATH="$(pwd)/.claude/hooks/init-transition.sh"
# Check if settings.json exists
if [ ! -f ".claude/settings.json" ]; then
echo "❌ No .claude/settings.json found. Run /setup:existing first."
exit 1
fi
echo "📝 Updating .claude/settings.json..."
I'll update the settings.json to add the UserPromptSubmit hook configuration. Let me read the current settings and merge the hook configuration.
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.
- 2d ago First seen · 163 lines · 18 tokens per session scan B 65767c8e8fb6
setup:transitions is a command published in the GitHub repository stefan-jansen/claude-code-toolkit (85 stars, last pushed 1mo ago), licensed MIT. It adds 18 tokens to every session and 1,093 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other commands, from other repositories
generate-agents.template
This prompt was authored for Claude-style slash workflows. In Codex runtime, adapt tool calls as follows.
ng-context-pack
Portable command prompt generated from skills/briefing-an-agent/SKILL.md. Edit the skill, then run python tools/ng.py gen-commands; do not edit this file by hand.
enrich
Enrich project memory by mining 100 recently merged PRs: extracts decisions, conventions, gotchas, and architectural facts from PR discussions, review comments, and PR bodies.
implement.body
Every subagent invocation uses the delegation tool with the appropriate subagenttype (the implementation subagent, the tester subagent, or any specialized subagent the project ships). That tool is named Agent in an interactive Claude Code session and Task in the headless runtime (claude -p, Agent SDK). Read your…
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.
docs
Audit docs, fix doc rot, enforce README and changelog standards.