sprint-run

sprint-run is a command for Claude Code from Hundia/autospec. It costs 0 tokens per session (1,898 once invoked), scanned A, original, MIT.

A command that closes a numbered sprint and creates summary documentation with links to the project’s documentation. A sprint is a planned group of development tasks completed together.

In plain words
What is it for?
Use it to check backlog status, collect changed files, test results, and documentation updates, then create `sprints/sprint_X/summary.md`. It warns when tickets are still in progress or under testing.
Why use it?
It confirms whether all sprint tickets are finished or deliberately blocked before recording the result. This provides a consistent handoff and historical record.

Command for Claude Code

Written for Claude Code: installed under .claude/.

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/sprint-run
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 sprint-run

README.md
[![agentmods](https://agentmods.dev/badge/commands/hundia/autospec/sprint-run.svg)](https://agentmods.dev/commands/hundia/autospec/sprint-run)
Your own site
<a href="https://agentmods.dev/commands/hundia/autospec/sprint-run"><img src="https://agentmods.dev/badge/commands/hundia/autospec/sprint-run.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 1,898 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 5.1 $0.00000 $0.01898
Opus 5 $0.00000 $0.00949
Sonnet 5 $0.00000 $0.00380
Haiku 4.5 $0.00000 $0.00190

Measured 6d ago against content hash 861af51e559a, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

sprint-run 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 6d 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/sprint-run.md · 201 lines

How it starts

The opening of the file, as written. The whole thing — 201 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Sprint Run

Execute an entire sprint end-to-end: plan → implement → QA → docs → close.

Usage

/sprint-run [sprint_number]

Example: /sprint-run 4

Instructions

Execute the sprint through 8 phases. Get user confirmation after Phase 1 before proceeding.


Phase 1: Sprint Briefing

  1. Read specs/backlog.md — find the target sprint
  2. Read ALL relevant spec files referenced by the sprint's tickets
  3. Read ALL relevant docs/ sections — docs are the authoritative source. Include these paths in agent briefs so agents read them before implementing.
  4. Build execution plan:
    • Order tickets by dependencies (DAG sort)
    • Identify parallelizable batches (tickets with no mutual dependencies)
    • Map each ticket to recommended model (FinOps)
  5. Present plan to user and WAIT for confirmation before proceeding

Output:

## Sprint X: [Name] — Execution Plan

### Tickets (ordered by dependencies)
| # | Ticket | Owner | Model | Dependencies | Batch |
|---|--------|-------|-------|-------------|-------|

### Estimated Batches
- Batch 1 (parallel): X.1, X.2, X.3
- Batch 2 (sequential): X.4 (depends on X.1)
- Batch 3 (parallel): X.5, X.6

Shall I proceed with execution?

DEFAULT Execution Pattern: Orchestrator + Sonnet Agents

ALWAYS use this pattern. Opus orchestrates, Sonnet agents implement. This keeps the orchestrator's context clean and is FinOps efficient.

  1. Orchestrator (Opus 4.6) — never implements directly. Instead:

    • Writes agents/sprint-X-brief.md with full context package
    • Includes relevant docs/ file paths in the brief so agents read them FIRST
    • Spawns Agent(subagent_type=general-purpose, model="sonnet") for implementation
    • Reviews results, merges, then spawns next batch
  2. Sprint Agent (Sonnet 4.6) — reads brief, implements all tickets:

    • Reads agents/sprint-X-brief.md for full context
    • Reads ALL docs/ files listed in the brief BEFORE writing any code
    • Executes tickets per execute-ticket.md conventions
    • Updates specs/backlog.md (🔲→✅), docs/, sprint summary
    • If any code written is NOT documented in docs/, creates/updates the relevant doc file

Read the full file on GitHub · 201 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. 6d ago First seen · 201 lines · 0 tokens per session scan A 861af51e559a

Subscribe to this mod's changes

sprint-run 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 1,898 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.