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/continuegit 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 | $0.00000 | $0.00676 |
| Opus 5 | $0.00000 | $0.00338 |
| Sonnet 5 | $0.00000 | $0.00135 |
| Haiku 4.5 | $0.00000 | $0.00068 |
Grade A, and why
continue scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 104 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Continue from Latest Handoff
Automatically loads and continues from the most recent handoff document, with verification.
Purpose
This command automates the continuation workflow after /clear by:
- Finding the most recent handoff via dynamic lookup (no symlink needed)
- Reading and loading context
- Briefing you on what we're continuing from
Usage
# After /clear, simply run:
/continue
# That's it - no manual file paths needed
What It Does
Step 1: Locate Latest Handoff
Dynamically finds the most recent transition using:
# Find most recent date directory
LATEST_DATE=$(ls -1 .claude/transitions/ | grep -E '^[0-9]{4}-[0-9]{2}-[0-9]{2}$' | sort -r | head -1)
# Find most recent timestamp in that directory
LATEST_TIME=$(ls -1 ".claude/transitions/$LATEST_DATE/" | grep -E '^[0-9]{6}\.md$' | sort -r | head -1)
# Full path to most recent transition
LATEST_TRANSITION=".claude/transitions/$LATEST_DATE/$LATEST_TIME"
Step 2: Load Context
Reads the handoff document and extracts key information.
Step 3: Brief You
Tells you:
- Which handoff file is being loaded (date + UTC timestamp)
- Session focus from that handoff
- Active work status
- Main next steps
Example Output
📋 Continuing from: .claude/transitions/2025-10-20/124933.md
Handoff created: 2025-10-20 12:49:33 UTC
Session Focus: Handoff Command Refactoring - UTC Timestamp-based Organization
Active Work: Moved from numbered transitions to UTC timestamp structure
Next Steps: Complete handoff command updates, test new approach
Main Takeaways:
- Removed numbered format (2025-10-19_006) in favor of UTC timestamps
- No more counter management or symlink complexity
- Dynamic lookup using two simple ls commands
- PWD verification added to prevent wrong-directory creation
Ready to continue. What would you like to work on?
Error Handling
If issues detected:
- No date directories found: Alerts you to create first handoff with
/handoff - No transitions in latest date: Indicates corruption or incomplete handoff
- Wrong directory: Verifies
.claude/transitions/exists before proceeding
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 · 104 lines · 0 tokens per session scan A 5c0434f134da
continue is a command published in the GitHub repository stefan-jansen/claude-code-toolkit (85 stars, last pushed 1mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 676 tokens. 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.