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/dwmkerr/claude-toolkit/nextgit clone --depth 1 https://github.com/dwmkerr/claude-toolkitWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/commands/dwmkerr/claude-toolkit/next)<a href="https://agentmods.dev/commands/dwmkerr/claude-toolkit/next"><img src="https://agentmods.dev/badge/commands/dwmkerr/claude-toolkit/next.svg" alt="Measured on agentmods" height="20"></a>What 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 | $0.00013 | $0.00575 |
| Opus 5 | $0.00006 | $0.00287 |
| Sonnet 5 | $0.00003 | $0.00115 |
| Haiku 4.5 | $0.00001 | $0.00057 |
Grade A, and why
next 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 4d 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.
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 — 52 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/next
Arguments
$ARGUMENTS
Context
- Branch: !
git branch --show-current - Recent commits: !
git log --oneline -10 - Working tree: !
git status --short - tasks.md: !
cat tasks.md 2>/dev/null || echo "No tasks.md found" - ideas.md: !
cat ideas.md 2>/dev/null || echo "No ideas.md found" - Framework detection: !
ls -d .obra/ .openspec/ docs/plans/ 2>/dev/null || echo "No framework directories found" - Open GitHub issues: !
gh issue list --limit 5 --state open 2>/dev/null || echo "No GitHub issues or gh not configured"
Instructions
Determine the mode from the arguments above:
Suggest Mode (default — no arguments, or arguments that aren't about wrapping up)
Analyze all the context above and produce:
- Current State — 1-2 sentences: what branch we're on, what the recent work looks like, whether the working tree is clean
- Suggested Next Actions — up to 5 bullet points, prioritized. Each bullet should:
- Start with a source tag like
[tasks.md],[GitHub #N],[ideas.md],[branch], or[plan] - Be a concrete, actionable next step
- Be brief (one line)
- Start with a source tag like
If a development framework is detected (Obra Superpowers plans in docs/plans/, OpenSpec, etc.), check for active plans and include their next steps in the suggestions.
Present the bullets and stop. Do not start working on anything.
Wrap-up Mode (arguments contain "done", "finished", "complete", "wrap up", or similar)
The user is finished with current work. Do:
- Summary — briefly describe what was accomplished this session based on conversation history and recent commits
- Ask what to do next using
AskUserQuestionwith these options:- Create/update PR — if on a feature branch with commits ahead of main
- Update tasks.md — mark current task done, add any new tasks discovered
- Update ideas.md — capture any ideas that came up during work
- Nothing, just summarize — only show the summary
- Execute whichever actions the user selects
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.
- 4d ago First seen · 52 lines · 13 tokens per session scan A d292f262f56c
next is a command published in the GitHub repository dwmkerr/claude-toolkit (23 stars, last pushed 9d ago), licensed MIT. It adds 13 tokens to every session and 575 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
git
Git operations with intelligent commit messages and workflow optimization.
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.