next-task

A command that selects and prepares the next development action using current tasks, recent activity, dependencies, and time limits.

In plain words
What is it for?
Use it to resume recent work, find an unblocked task, or choose a quick, easy, or important task.
Why use it?
It helps decide what to work on when several tasks are active, idle, blocked, or unfinished.

Command for Claude Code

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/asachs01/float-mcp/next-task
Clone the repo
git clone --depth 1 https://github.com/asachs01/float-mcp

Made for: Claude Code.

Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 414 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin 100% copy Near-identical to another mod 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 $0.00000 $0.00414
Opus 5 $0.00000 $0.00207
Sonnet 5 $0.00000 $0.00083
Haiku 4.5 $0.00000 $0.00041

Measured yesterday against content hash aa6087d7c9d5, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

next-task 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.

Origin

This is a copy

100% identical to next-task — 12 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

.claude/commands/tm/next/next-task.md · 76 lines

What it actually says

Intelligently determine and prepare the next action based on comprehensive context.

This enhanced version of 'next' considers:

  • Current task states
  • Recent activity
  • Time constraints
  • Dependencies
  • Your working patterns

Arguments: $ARGUMENTS

Intelligent Next Action

1. Context Gathering

Let me analyze the current situation:

  • Active tasks (in-progress)
  • Recently completed tasks
  • Blocked tasks
  • Time since last activity
  • Arguments provided: $ARGUMENTS

2. Smart Decision Tree

If you have an in-progress task:

  • Has it been idle > 2 hours? → Suggest resuming or switching
  • Near completion? → Show remaining steps
  • Blocked? → Find alternative task

If no in-progress tasks:

  • Unblocked high-priority tasks? → Start highest
  • Complex tasks need breakdown? → Suggest expansion
  • All tasks blocked? → Show dependency resolution

Special arguments handling:

  • "quick" → Find task < 2 hours
  • "easy" → Find low complexity task
  • "important" → Find high priority regardless of complexity
  • "continue" → Resume last worked task

3. Preparation Workflow

Based on selected task:

  1. Show full context and history
  2. Set up development environment
  3. Run relevant tests
  4. Open related files
  5. Show similar completed tasks
  6. Estimate completion time

4. Alternative Suggestions

Always provide options:

  • Primary recommendation
  • Quick alternative (< 1 hour)
  • Strategic option (unblocks most tasks)
  • Learning option (new technology/skill)

5. Workflow Integration

Seamlessly connect to:

  • /project:task-master:start [selected]
  • /project:workflows:auto-implement
  • /project:task-master:expand (if complex)
  • /project:utils:complexity-report (if unsure)

The goal: Zero friction from decision to implementation.

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. yesterday First seen · 76 lines · 0 tokens per session scan A aa6087d7c9d5

Subscribe to this mod's changes

next-task is a command published in the GitHub repository asachs01/float-mcp (2 stars, last pushed 6mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 414 tokens. A static security scan graded it A with 0 findings. It is 100% identical to next-task, differing in 12 lines, and is treated as a copy.