create-tasks

A task-planning command that breaks a large software issue into small, actionable work items. It organizes the resulting tasks into project files and phases.

In plain words
What is it for?
Use it to create task plans from issue documents, divide work into phases, and generate progress files for each issue.
Why use it?
It turns a broad issue into steps that an AI coding agent or developer can handle and track individually.

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/agentsea/flashbacker/create-tasks
Clone the repo
git clone --depth 1 https://github.com/agentsea/flashbacker

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 1,614 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 $0.01614
Opus 5 $0.00000 $0.00807
Sonnet 5 $0.00000 $0.00323
Haiku 4.5 $0.00000 $0.00161

Measured 2d ago against content hash f7b83383c100, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

create-tasks 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.

templates/.claude/commands/fb/create-tasks.md · 174 lines

How it starts

The opening of the file, as written. The whole thing — 174 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Create Granular Tasks from Issue

Generate atomic, AI-friendly task breakdown from comprehensive issues following the ai-dev-tasks methodology.

Directory Structure

docs/issues/                     # Source issue files (read from here)
├── ISSUE-XXX-title.md          # Individual issue files to analyze
└── README.md                   # Issue tracking reference

docs/tasks/                     # Task files location (write to here)
├── ISSUE-XXX-name/             # Per-issue task directories (create these)
│   ├── README.md               # Task progress dashboard
│   ├── phase-1-name.md         # Granular tasks for Phase 1
│   ├── phase-2-name.md         # Granular tasks for Phase 2
│   └── phase-N-name.md         # Additional phases as needed
└── metadata.json               # Task metadata and tracking

Usage

/fb:create-tasks <issue-number> [force] [phases]

Examples:

  • /fb:create-tasks ISSUE-027 - Generate full task breakdown for XYZ project scaffolding
  • /fb:create-tasks ISSUE-015 force - Regenerate tasks, overwrite existing
  • /fb:create-tasks ISSUE-027 phases:1,2 - Generate only specific phases

Command Implementation

Parse the command arguments:

  • Argument 1 (required): Issue number (ISSUE-027, ISSUE-015, etc.)
  • Argument 2 (optional): "force" to overwrite existing task files
  • Argument 3 (optional): "phases:1,2,3" to generate only specific phases

Argument Parsing Logic

  1. Extract Issue Number: First argument must match ISSUE-XXX pattern
  2. Check Force Flag: Look for "force" in arguments to enable overwrite
  3. Parse Phases: Look for "phases:" prefix followed by comma-separated numbers
  4. Validate Issue: Ensure issue file exists in docs/issues/ directory

How It Works

Step 1: Issue Analysis

  1. Read Issue File: Load docs/issues/ISSUE-XXX-*.md
  2. Parse Structure: Extract phases, deliverables, acceptance criteria
  3. Identify Dependencies: Map dependencies between phases and tasks
  4. Validate Scope: Ensure issue is suitable for task breakdown

Read the full file on GitHub · 174 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 · 174 lines · 0 tokens per session scan A f7b83383c100

Subscribe to this mod's changes

create-tasks is a command published in the GitHub repository agentsea/flashbacker (57 stars, last pushed 7mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,614 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.