next-task

A command that selects the highest-priority queued task and starts its implementation.

In plain words
What is it for?
Use it to find a task in Next or Backlog, request confirmation, move it to In Progress, implement it, update the changelog, and mark it Done.
Why use it?
It removes the need to manually search the task list and defines the steps for moving work from the queue to completion.

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/smekai/taskplanner/next-task
Clone the repo
git clone --depth 1 https://github.com/smekai/taskplanner
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 339 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 $0.00339
Opus 5 $0.00006 $0.00169
Sonnet 5 $0.00003 $0.00068
Haiku 4.5 $0.00001 $0.00034

Measured 2d ago against content hash edb67805abde, 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 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.

plugins/taskplanner/commands/next-task.md · 31 lines

What it actually says

Next Task

Pick the highest-priority unstarted task and begin implementation.

Steps

Determine the absolute current repository root first and pass it as workspace_root on every MCP call.

  1. Call taskplanner_list with state: "Next" to find tasks queued for implementation.
  2. If no tasks are in Next, fall back to taskplanner_list with state: "Backlog".
  3. Select the first task (highest priority, since tasks are sorted by priority).
  4. Show the user which task you are picking and ask for confirmation before proceeding.
  5. Once confirmed: a. Call taskplanner_move to move the task to "In Progress". b. Read .tasks/config.json to check if aiPlanRequired is true. c. If plan is required, write a ### Plan subsection under the task heading in IN_PROGRESS.md before writing any code. The plan should have 3-7 bullets covering: intended changes, key files, and notable risks. d. Implement the task. e. When done, call taskplanner_move to move the task to "Done". f. Add a CHANGELOG.md entry under ## [Unreleased] in the appropriate subsection (Added, Changed, Fixed, Removed).

Conventions

  • Do NOT change task IDs.
  • Keep the --- separator between tasks in markdown files.
  • When moving to Done, condense the ### Plan to a short summary of what was actually done.
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 · 31 lines · 13 tokens per session scan A edb67805abde

Subscribe to this mod's changes

next-task is a command published in the GitHub repository smekai/taskplanner (19 stars, last pushed 4d ago), licensed MIT. It adds 13 tokens to every session and 339 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.