sprint

sprint is a command for Claude Code from aadivar/shiplog. It costs 0 tokens per session (460 once invoked), scanned A, original, MIT.

A command that starts a new Shiplog sprint, where a sprint is a numbered period of development work. It archives the previous sprint's session notes and prepares the progress file for the next one.

In plain words
What is it for?
Use it with /shiplog sprint to archive the current sprint, update docs/PROGRESS.md, and generate a summary of the completed sprint.
Why use it?
It keeps completed session records while resetting the active progress log, so ongoing work has a clear history and starting point.

Command for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: names the AskUserQuestion tool.

Part of the shiplog plugin — 1 skill, 8 commands, 4 agents, 1 hook shipped together

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/aadivar/shiplog/sprint
Clone the repo
git clone --depth 1 https://github.com/aadivar/shiplog

Made for: Claude Code.

Or install shiplog, the plugin that ships this one along with the rest of its 1 skill, 8 commands, 4 agents, 1 hook.

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

README.md
[![agentmods](https://agentmods.dev/badge/commands/aadivar/shiplog/sprint.svg)](https://agentmods.dev/commands/aadivar/shiplog/sprint)
Your own site
<a href="https://agentmods.dev/commands/aadivar/shiplog/sprint"><img src="https://agentmods.dev/badge/commands/aadivar/shiplog/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 460 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 $0.00460
Opus 5 $0.00000 $0.00230
Sonnet 5 $0.00000 $0.00092
Haiku 4.5 $0.00000 $0.00046

Measured 6d ago against content hash 651c15fe5d2a, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

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 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.

commands/sprint.md · 59 lines

What it actually says

/shiplog sprint

Start a new sprint with session log archival.

Trigger

User runs /shiplog sprint <n> or /shiplog sprint

Behavior

Step 1: Validate setup

Check that .shiplog/config.json exists. If not:

"Shiplog is not initialized. Run /shiplog init first."

Step 2: Determine sprint number

  • If user provided a number (e.g., /shiplog sprint 3), use that
  • If no number, read docs/PROGRESS.md to get current sprint and increment by 1

Step 3: Archive previous sprint

Read docs/PROGRESS.md and extract the session log entries for the current sprint.

Create an archive file:

  • Path: docs/archive/sprint-{N}.md (create docs/archive/ if it doesn't exist)
  • Content: The session log entries from the completed sprint, with a header

Step 4: Update PROGRESS.md

Edit docs/PROGRESS.md:

  • Update "Sprint" in Current State to the new sprint number
  • Clear the Session Log section and add a fresh table header for the new sprint
  • Update "Last Session" date
  • Keep the "What's Next" section (user will update it)

Step 5: Generate sprint summary

Count from the archived sprint:

  • Number of session entries
  • Features completed (cross-reference with PRD.md)
  • Features still in-progress

Step 6: Confirm and ask for focus

Sprint {N} started!

Sprint {N-1} summary:
  Sessions: {count}
  Features completed: {count}
  Features in-progress: {count}
  Archived to: docs/archive/sprint-{N-1}.md

What's the focus for Sprint {N}?

Use AskUserQuestion to ask for the sprint focus, then update the "Focus" field in PROGRESS.md's Current State.

Rules

  • Always archive before clearing — never lose session history
  • Sprint numbers must be positive integers
  • Don't allow going backwards (sprint 2 after sprint 3)
  • Create docs/archive/ directory if it doesn't exist
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 · 59 lines · 0 tokens per session scan A 651c15fe5d2a

Subscribe to this mod's changes

sprint is a command published in the GitHub repository aadivar/shiplog (3 stars, last pushed 6mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 460 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.

Related

Other commands, from other repositories