plan-sprint

plan-sprint is a command for Claude Code from Hundia/autospec. It costs 0 tokens per session (2,746 once invoked), scanned A, original, MIT.

A collaborative sprint-planning workflow for turning a development goal into a ready-to-use sprint plan. It gathers analysis from specialist AI agents and has project managers review and finalize the plan before adding it to the backlog.

In plain words
What is it for?
Use it to plan features, fixes, or improvements such as authentication, payment changes, or dashboards, with clear deliverables and backlog tickets.
Why use it?
It helps turn a vague feature request into defined work before coding starts. Multiple reviews are used to identify missing requirements and produce an actionable plan.

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/hundia/autospec/plan-sprint
Clone the repo
git clone --depth 1 https://github.com/Hundia/autospec

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for plan-sprint

README.md
[![agentmods](https://agentmods.dev/badge/commands/hundia/autospec/plan-sprint.svg)](https://agentmods.dev/commands/hundia/autospec/plan-sprint)
Your own site
<a href="https://agentmods.dev/commands/hundia/autospec/plan-sprint"><img src="https://agentmods.dev/badge/commands/hundia/autospec/plan-sprint.svg" alt="Measured on agentmods" height="20"></a>
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 2,746 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 $0.02746
Opus 5 $0.00000 $0.01373
Sonnet 5 $0.00000 $0.00549
Haiku 4.5 $0.00000 $0.00275

Measured 4d ago against content hash 849d536d39de, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

plan-sprint 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 4d 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.

.claude/commands/plan-sprint.md · 302 lines

How it starts

The opening of the file, as written. The whole thing — 302 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Plan Sprint

Assemble a team of expert AI agents to collaboratively plan a sprint before building it. Experts analyze the goal in parallel, then three PMs (drafter → reviewer → finalizer) produce a production-ready sprint plan for the backlog.

Usage

/plan-sprint [goal description]

Examples:

  • /plan-sprint Add user authentication with JWT and social login
  • /plan-sprint Refactor payment processing to support subscriptions
  • /plan-sprint Build admin dashboard with analytics and user management

Instructions

When this command is invoked, execute the 6-phase planning workflow below. The argument $ARGUMENTS is the sprint goal description.


Phase 1: Goal Analysis & Expert Selection

  1. Validate the goal. If $ARGUMENTS is empty or too vague (fewer than 5 words, no clear deliverable), ask the user to clarify:

    I need a clearer sprint goal. Please describe:
    - What feature/fix/improvement you want
    - Who it's for (which user personas)
    - Any specific subsystems involved
    
    Example: "Add user authentication with JWT, social login, and role-based access control"
    
  2. Read specs/backlog.md — scan all ## Sprint X headers to determine the next sprint number.

  3. Read docs/ index — identify which subsystems the goal touches. Cross-reference with existing documentation sections.

  4. Determine which experts to activate based on the goal:

    Expert Role Activate When Reads
    Architect System design, API contracts, integration ALWAYS specs/02_backend_lead.md, specs/03_frontend_lead.md, project entry points, relevant docs/
    UX/UI Expert User flows, components, accessibility Sprint has ANY frontend/GUI work specs/10_ui_designer.md, docs/ui-design-system/, docs/flows/
    Database Expert Schema changes, migrations, query patterns Sprint has schema changes or new models specs/04_db_architect.md, docs/architecture/database.md, schema file
    Human Experience Expert User journeys, personas, cognitive load Sprint has user-facing features specs/01_product_manager.md, relevant docs/flows/ for affected user journeys

Read the full file on GitHub · 302 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. 4d ago First seen · 302 lines · 0 tokens per session scan A 849d536d39de

Subscribe to this mod's changes

plan-sprint is a command published in the GitHub repository Hundia/autospec (4 stars, last pushed 2mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 2,746 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 2026-08-31.