sprint-planning

sprint-planning is a skill for Claude Code from camilooscargbaptista/cto-toolkit. It costs 124 tokens per session (5,205 once invoked), scanned A, original, MIT.

A planning guide for software sprints, releases, backlogs, and roadmaps. It defines user stories with acceptance criteria, completion checks, and normal, failure, and edge-case scenarios.

In plain words
What is it for?
Use it to groom a backlog, write user stories, estimate tasks, plan a sprint or release, prioritize features, or create a roadmap.
Why use it?
It helps turn vague feature ideas into work that a team can estimate, prioritize, and verify. Required scenarios and completion checks expose missing details before work enters a sprint.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the cto-toolkit plugin — 54 skills, 6 agents, 3 hooks shipped together

Good fit Use it to groom a backlog, write user stories, estimate tasks, plan a sprint or release, prioritize features, or create a roadmap.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/camilooscargbaptista/cto-toolkit/sprint-planning
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.

Any agent
npx skills add camilooscargbaptista/cto-toolkit --skill sprint-planning
Clone the repo
git clone --depth 1 https://github.com/camilooscargbaptista/cto-toolkit

Made for: Claude Code.

Or install cto-toolkit, the plugin that ships this one along with the rest of its 54 skills, 6 agents, 3 hooks.

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 sprint-planning

README.md
[![agentmods](https://agentmods.dev/badge/skills/camilooscargbaptista/cto-toolkit/sprint-planning/github.svg)](https://agentmods.dev/skills/camilooscargbaptista/cto-toolkit/sprint-planning)
Your own site
<a href="https://agentmods.dev/skills/camilooscargbaptista/cto-toolkit/sprint-planning"><img src="https://agentmods.dev/badge/skills/camilooscargbaptista/cto-toolkit/sprint-planning/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for sprint-planning

Your own site · 80×15
<a href="https://agentmods.dev/skills/camilooscargbaptista/cto-toolkit/sprint-planning"><img src="https://agentmods.dev/badge/skills/camilooscargbaptista/cto-toolkit/sprint-planning.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 124 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 5,205 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00124 $0.05205
Opus 5 $0.00062 $0.02603
Sonnet 5 $0.00025 $0.01041
Haiku 4.5 $0.00012 $0.00521

Measured 10d ago against content hash 7e3ca47a13ba, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

sprint-planning 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 10d 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.

sprint-planning/SKILL.md · 513 lines

How it starts

The opening of the file, as written. The whole thing — 513 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Sprint & Release Planning

This skill helps you run effective planning processes — from writing good user stories to building quarterly roadmaps. Adapt the level of formality to your team's size and culture.

Before producing any planning output, read ../quality-standard/SKILL.md and apply its self-verification protocol, decomposition rules, and edge case prompting.

User Story Writing

A well-written story communicates intent without over-prescribing implementation. Every story MUST be production-ready with no ambiguity or missing acceptance criteria.

Format

As a [type of user],
I want to [action/capability],
so that [benefit/value].

Mandatory Story Requirements

Every story MUST include ALL of the following before it enters a sprint:

  1. Acceptance Criteria (minimum 3 scenarios) in Given-When-Then format

    • Happy path scenario (the normal case)
    • At least one error/failure scenario
    • At least one edge case or boundary scenario
  2. Definition of Done checklist (concrete, testable items)

    • Code reviewed
    • Tests written and passing
    • Acceptance criteria verified
    • Documentation updated
    • No console errors/warnings
    • (Add team-specific items)
  3. Dependencies (explicit list)

    • Other stories that must complete first
    • External APIs or services required
    • Data or configuration changes needed
    • Third-party integrations
  4. Estimated Complexity (S/M/L or story points)

    • Use Fibonacci: 1, 2, 3, 5, 8, 13
    • If >8, story is too large — split it
  5. Story Quality Checklist (INVEST)

    • Independent — Minimal coupling to other stories
    • Negotiable — Implementation approach is flexible
    • Valuable — Delivers measurable user or business value
    • Estimable — Team can estimate within a confidence range
    • Small — Completable in ≤1 sprint
    • Testable — Acceptance criteria are verifiable

Complete Example: Add PIX Payment Method

Title: Add PIX payment method to checkout flow

As a Brazilian customer,
I want to pay with PIX at checkout,
so that I can use my preferred, instant payment method without credit card fees.

## Acceptance Criteria

### Happy Path
Given a customer with a valid PIX key in their payment methods,
When they select PIX at checkout and complete the payment flow,
Then the payment processes instantly, they receive an order confirmation email
within 2 minutes, and the order status shows "Paid" in their account.

### Error Case: Invalid PIX Key
Given a customer enters an invalid PIX key during payment,
When they submit the payment form,
Then the system displays "Invalid PIX key format" error message,
highlights the input field in red, and suggests the correct format (email, phone, CPF, or random key).

### Edge Case: Duplicate Payment Attempt (Race Condition)
Given a customer has submitted a PIX payment but clicks "Submit" again immediately,
When the system processes both requests concurrently,
Then only one charge is applied, a duplicate prevention lock is acquired,
and the customer is informed "Payment already processing—do not refresh."

### Boundary Case: Large Transaction Amount
Given a customer attempts to pay R$50,000 via PIX,
When the transaction exceeds the PIX single-transfer limit (R$4,992),
Then the system displays "Amount exceeds PIX limit" and offers to split into multiple transfers
or suggests alternative payment methods.

### Boundary Case: Very Quick Payment
Given a customer completes PIX payment verification in <100ms,
When the webhook callback arrives from the payment processor,
Then the order status updates to "Paid" without race conditions
and the confirmation email is queued correctly.

## Definition of Done
- [ ] PIX payment method integrated with payment processor (Stripe/PagSeguro/equivalent)
- [ ] Checkout UI updated to show PIX as option with logo
- [ ] All 5 acceptance criteria scenarios tested (manual + automated)
- [ ] Idempotency keys implemented to prevent duplicate charges
- [ ] Webhook handler for payment status updates tested with 50+ mock scenarios
- [ ] Error messages user-friendly and match brand tone
- [ ] No console errors/warnings in Chrome DevTools
- [ ] Documentation updated: README, API docs, payment flow diagram
- [ ] Database migrations tested on staging
- [ ] Metrics added: PIX transaction success rate, average completion time
- [ ] Backwards-compatible with existing payment methods
- [ ] Security review: no sensitive PIX keys stored in logs
- [ ] Load tested with 100+ concurrent PIX transactions

## Dependencies
- Payment processor account with PIX support enabled
- Webhook signing key from payment provider
- Legal/compliance review (PIX is regulated in Brazil)
- Frontend form validation library already in place
- Database schema supports new `payment_method` type

## Estimated Complexity
M (5 story points)
- Medium because: new payment provider integration + webhook handling + race condition handling
- Not small due to concurrency complexity
- Not large because PIX API is simpler than some alternatives

Read the full file on GitHub · 513 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. 10d ago First seen · 513 lines · 124 tokens per session scan A 7e3ca47a13ba

Subscribe to this mod's changes

sprint-planning is a skill published in the GitHub repository camilooscargbaptista/cto-toolkit (7 stars, last pushed 5mo ago), licensed MIT. It adds 124 tokens to every session and 5,205 once invoked, about $0.0006 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.