m-next-task

A workflow for finding and ranking unfinished development work in a project.

In plain words
What is it for?
It scans development notes and Git history, assesses task status and blockers, ranks priorities, and collects relevant references.
Why use it?
It brings together pending items from documentation, trackers, and recent commits so the next actions are easier to choose.

Command

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/penwyp/claudepreference/m-next-task
Clone the repo
git clone --depth 1 https://github.com/penwyp/ClaudePreference
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 733 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 $0.00000 $0.00733
Opus 5 $0.00000 $0.00367
Sonnet 5 $0.00000 $0.00147
Haiku 4.5 $0.00000 $0.00073

Measured 2d ago against content hash a739be14acae, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

m-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 2d 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.

commands/m-next-task.md · 109 lines

How it starts

The opening of the file, as written. The whole thing — 109 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Next Tasks Workflow: Analyze Status & Plan Actions

Target: $ARGUMENTS (Default: medium priority if none specified)

Scope: Analyze current development status and generate prioritized action plan

Execution Steps

  1. Documentation & Tracker Scan

    • Inspect development tracking files (docs/dev*.md, TODO.md, etc.)
    • Extract pending tasks and action items
    • Review project roadmap and milestone documents
  2. Git History Analysis

    • Parse recent commits for TODO markers and incomplete work
    • Identify new changes requiring follow-up actions
    • Detect unfinished features or partial implementations
  3. Task Status Assessment

    • Evaluate current task completion status
    • Identify blocking dependencies and prerequisites
    • Assess resource availability and constraints
  4. Priority Ranking

    • Rank tasks based on specified priority level or default medium
    • Consider business impact, technical debt, and dependencies
    • Balance feature development with maintenance tasks
  5. Reference Collection

    • Gather relevant files, commits, and documentation
    • Identify helpful discussions and decision records
    • Compile supporting materials for task execution
  6. Generate Next Tasks Report

    • Compile findings into structured markdown format
    • Save to docs/workspaces/next-tasks-MM-dd-HH-mm-ss.md

Output Format

English Report

summary
  • Concise overview of current development status
  • Key context and recent progress highlights
  • Overall project health and momentum assessment
tasks

Prioritized task list with structure:

{
  "id": "string",
  "description": "string",
  "priority": "high|medium|low",
  "status": "pending|blocked|in-progress",
  "dependencies": ["task_id_1", "task_id_2"]
}
references
  • Relevant files and documentation links
  • Related commits and pull requests
  • Helpful discussions and decision records
  • External resources and documentation
clarifications

Questions for requirement or implementation ambiguities:

  • Unclear priorities or scope boundaries
  • Missing technical specifications
  • Resource allocation and timeline concerns

Read the full file on GitHub · 109 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. 2d ago First seen · 109 lines · 0 tokens per session scan A a739be14acae

Subscribe to this mod's changes

m-next-task is a command published in the GitHub repository penwyp/ClaudePreference (137 stars, last pushed 3mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 733 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.