generate

A command that turns a specification document into a structured list of small, testable development tasks.

In plain words
What is it for?
Use it to create an implementation plan from requirements, features, acceptance criteria, constraints, and error-handling needs.
Why use it?
It breaks a broad plan into clear pieces of work and shows which tasks depend on others.

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/generate
Clone the repo
git clone --depth 1 https://github.com/sequenzia/claude-plugins
Per session 9 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,269 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 $0.00009 $0.01269
Opus 5 $0.00005 $0.00634
Sonnet 5 $0.00002 $0.00254
Haiku 4.5 $0.00001 $0.00127

Measured yesterday against content hash fc681389368f, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

generate 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/generate.md · 189 lines

How it starts

The opening of the file, as written. The whole thing — 189 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Generate a comprehensive task list from a specification document, organized under a named mission.

Arguments: $ARGUMENTS

Parse the arguments to extract:

  • Mission name: First argument (required) - The name for this mission (e.g., "Build User Authentication System")
  • Spec document: Second argument (required) - Path to the specification document

If mission name contains spaces, it should be quoted. Example: /mission-control:generate "Build Auth System" specs/auth-spec.md

Analysis Process

  1. Read and parse the specification document thoroughly

    • Identify all explicit requirements, features, and acceptance criteria
    • Extract implicit requirements (error handling, infrastructure, etc.)
    • Note constraints and scope boundaries
  2. Decompose into atomic tasks

    • Each task should have single responsibility
    • Tasks should be independent where possible
    • Tasks must have clear start/end conditions
    • Tasks must be testable with verifiable criteria
  3. Map dependencies between tasks

    • Identify blocking dependencies: Task B cannot start until Task A completes
    • Calculate blocked_by and blocks relationships
    • Flag tasks that are ready to start (no blockers)
  4. Assign priorities and complexity

    • Priority: critical, high, medium, low (based on dependency depth and risk)
    • Complexity: XS, S, M, L, XL (T-shirt sizing)
    • When parsing PRDs, map P0=critical, P1=high, P2=medium, P3=low
  5. Generate acceptance criteria for each task

    • Derive from the specification's acceptance criteria and user stories
    • Ensure each criterion is specific and testable
  6. Organize into execution phases

    • Phase 1: Tasks with no blocking dependencies
    • Phase 2+: Tasks whose dependencies are satisfied by previous phases

PRD Integration

When analyzing PRDs from prd-tools:

  • Extract features from Section 5 (Functional Requirements)
  • Map user stories (US-XXX) to source_requirements
  • Convert acceptance criteria items to task acceptance_criteria
  • Map P0-P3 priorities to critical/high/medium/low
  • Use Section 9 (Implementation Plan) for execution_phases
  • Use Section 10 (Dependencies) for task dependencies

Read the full file on GitHub · 189 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 · 189 lines · 9 tokens per session scan A fc681389368f

Subscribe to this mod's changes

generate is a command published in the GitHub repository sequenzia/claude-plugins (2 stars, last pushed 7mo ago), licensed MIT. It adds 9 tokens to every session and 1,269 once invoked, about $0.0000 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.