next

A command that recommends which available project task should be done next. It considers task dependencies, priority, effort, and recent activity.

In plain words
What is it for?
Use it to find the next ready task, compare the best candidates, and decide what to start working on.
Why use it?
It helps when a project has many tasks and it is unclear which one is ready or most important. It also points to a command for starting the chosen task and handling its status.

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/dtannen/pm/next
Clone the repo
git clone --depth 1 https://github.com/dtannen/pm

Made for: Claude Code.

Per session 19 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,630 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 $0.00019 $0.01630
Opus 5 $0.00010 $0.00815
Sonnet 5 $0.00004 $0.00326
Haiku 4.5 $0.00002 $0.00163

Measured yesterday against content hash d6d0c6e85c37, 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 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.

.claude-plugin/commands/next.md · 232 lines

How it starts

The opening of the file, as written. The whole thing — 232 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Get Next Priority Task

Intelligently recommend the next highest-priority task to work on based on dependencies, parallel opportunities, and project status.

Usage

/pm:next

Instructions

Analyze the current project state to recommend the optimal next task for execution.

MCP Integration (preferred)

Use MCP to identify available tasks and compute a recommendation.

  • Full name: mcp__project-manager-mcp__get_available_tasks — Primary list of ready tasks
  • Full name: mcp__project-manager-mcp__list_tasks — For additional filtering or scoring
  • Full name: mcp__project-manager-mcp__get_task_details — Deep context for top candidates

Recommended flow:

  1. Call mcp__project-manager-mcp__get_available_tasks (e.g., status=TODO, include_locked=false) to fetch candidates.
  2. Score by: dependency readiness, RA score (complexity), epic priority, estimated hours, and recent activity.
  3. For the top 3 tasks, fetch ...__get_task_details and present concise rationales.
  4. Provide a “start now” suggestion that points to /pm:task-start <task> which will handle locking and status via MCP.

1. Scan Task Status

Read all tasks in .pm/tasks/ and categorize by status:

  • Open: Available for execution
  • In Progress: Currently being worked on
  • Blocked: Waiting for dependencies
  • Completed: Finished tasks

2. Dependency Analysis

For each open task:

  • Check depends_on field for prerequisite tasks
  • Verify all dependencies are completed
  • Identify tasks with no remaining dependencies (ready to start)
  • Calculate dependency chain length for prioritization

3. Parallel Execution Opportunities

Identify tasks that can run simultaneously:

  • Check parallel: true flag
  • Review conflicts_with field to avoid conflicts
  • Group compatible tasks for parallel execution
  • Consider current in-progress tasks for conflict avoidance

4. Priority Scoring Algorithm

Score each available task based on:

Critical Path Impact (Weight: 40%)
  • Tasks on critical path get highest priority
  • Tasks blocking other tasks get bonus points
  • Tasks with many dependents score higher

Read the full file on GitHub · 232 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. yesterday First seen · 232 lines · 19 tokens per session scan A d6d0c6e85c37

Subscribe to this mod's changes

next is a command published in the GitHub repository dtannen/pm (0 stars, last pushed 10mo ago), licensed MIT. It adds 19 tokens to every session and 1,630 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 2026-08-31.