next

A task-planning command that recommends unfinished tasks by weighing priority, dependency status, how many tasks they unblock, and their estimated complexity.

In plain words
What is it for?
Use it to rank available tasks in a project and receive a configurable number of next-task suggestions.
Why use it?
It helps choose work that is ready to start and likely to move the project forward, rather than selecting tasks that are still blocked.

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/sequenzia/claude-plugins/next
Clone the repo
git clone --depth 1 https://github.com/sequenzia/claude-plugins
Per session 11 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 699 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 $0.00011 $0.00699
Opus 5 $0.00005 $0.00349
Sonnet 5 $0.00002 $0.00140
Haiku 4.5 $0.00001 $0.00070

Measured yesterday against content hash 3afb31cf9640, 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.

plugins/mission-control/commands/next.md · 119 lines

How it starts

The opening of the file, as written. The whole thing — 119 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Suggest the best tasks to work on next based on priority, complexity, and dependency analysis.

Arguments:

  • count (optional): Number of recommendations (default: 5)
  • project-name (optional): Project name if multiple task files exist

Process

  1. Locate task file

    • Search for tasks/*.tasks.json files
    • Use specified project or prompt if multiple exist
  2. Filter eligible tasks

    • Status is "not_started" or "in_progress"
    • blocked_by array is empty (no incomplete dependencies)
  3. Score and rank tasks

    Scoring algorithm:

    score = (priority_weight * 100) + (blocking_weight * 50) + complexity_bonus
    
    Priority weights:
    - critical: 4
    - high: 3
    - medium: 2
    - low: 1
    
    Blocking weight:
    - Number of tasks this task blocks (unblocks others faster)
    
    Complexity bonus (quick wins):
    - XS: +15
    - S: +10
    - M: +5
    - L: +0
    - XL: -5
    
  4. Generate recommendations

Output Format

# Next Task Recommendations

**Project:** <project-name>
**Available tasks:** X (of Y total)

## Top Recommendations

### 1. TASK-XXX: <title>
**Score:** 450 | **Priority:** critical | **Complexity:** S

<brief description>

**Why recommended:**
- Critical priority (highest urgency)
- Blocks 3 other tasks
- Small complexity (quick win)

**Acceptance criteria:**
- [ ] Criterion 1
- [ ] Criterion 2

---

### 2. TASK-YYY: <title>
**Score:** 380 | **Priority:** high | **Complexity:** M

<brief description>

**Why recommended:**
- High priority
- Blocks 2 other tasks
- Unlocks Phase 2 work

---

### 3. TASK-ZZZ: <title>
**Score:** 320 | **Priority:** high | **Complexity:** XS

<brief description>

**Why recommended:**
- High priority
- Extra small complexity (very quick win)

---

(continue for requested count)

## Summary

| Rank | Task | Priority | Complexity | Blocks | Score |
|------|------|----------|------------|--------|-------|
| 1 | TASK-XXX | critical | S | 3 | 450 |
| 2 | TASK-YYY | high | M | 2 | 380 |
| 3 | TASK-ZZZ | high | XS | 0 | 320 |

## Quick Actions

- View task details: `/mission-control:show TASK-XXX`
- Mark complete when done: `/mission-control:complete TASK-XXX`

Read the full file on GitHub · 119 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 · 119 lines · 0 tokens per session scan A 3afb31cf9640

Subscribe to this mod's changes

next is a command published in the GitHub repository sequenzia/claude-plugins (2 stars, last pushed 7mo ago), licensed MIT. It adds 11 tokens to every session and 699 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.