next

next is a command for coding agents from dwmkerr/claude-toolkit. It costs 13 tokens per session (575 once invoked), scanned A, original, MIT.

A command that reviews a project's current state and recommends what to do next, or helps close out completed work.

In plain words
What is it for?
Use it to check the current Git branch and working tree, review recent commits and task files, find open GitHub issues, and get prioritized next actions.
Why use it?
It gathers project information in one place so you do not have to inspect branches, files, plans, and issues manually.

Command

Part of the dwmkerr plugin — 5 skills, 1 command shipped together

Install

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.

agentmods
npx agentmods add commands/dwmkerr/claude-toolkit/next
Clone the repo
git clone --depth 1 https://github.com/dwmkerr/claude-toolkit

Or install dwmkerr, the plugin that ships this one along with the rest of its 5 skills, 1 command.

Wrote 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.

agentmods badge for next

README.md
[![agentmods](https://agentmods.dev/badge/commands/dwmkerr/claude-toolkit/next.svg)](https://agentmods.dev/commands/dwmkerr/claude-toolkit/next)
Your own site
<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>
Per session 13 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 575 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce 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

Measured 4d ago against content hash d292f262f56c, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

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.

plugins/dwmkerr/commands/next.md · 52 lines

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:

  1. Current State — 1-2 sentences: what branch we're on, what the recent work looks like, whether the working tree is clean
  2. 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)

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:

  1. Summary — briefly describe what was accomplished this session based on conversation history and recent commits
  2. Ask what to do next using AskUserQuestion with 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
  3. Execute whichever actions the user selects

Read the full file on GitHub · 52 lines

Changes

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.

  1. 4d ago First seen · 52 lines · 13 tokens per session scan A d292f262f56c

Subscribe to this mod's changes

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.