sprint-done

sprint-done is a command for Claude Code from skybao1024/sprint-flow. It costs 14 tokens per session (407 once invoked), scanned B, original, MIT.

A command that checks manually completed sprint work and marks it finished only after independent verification passes.

In plain words
What is it for?
Use it to verify a specified sprint or the current sprint, repair failures when needed, and finalize the work.
Why use it?
It prevents a sprint from being closed based only on the implementer's own assessment.

Command for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: reads .claude/ paths; mentions CLAUDE.md; names the AskUserQuestion tool.

Part of the sprint-flow plugin — 1 skill, 4 commands, 3 agents shipped together

Good fit Use it to verify a specified sprint or the current sprint, repair failures when needed, and finalize the work.

Compare 6 commands from other repositories ↓
Install with agentmods
npx agentmods add commands/skybao1024/sprint-flow/sprint-done
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.

Clone the repo
git clone --depth 1 https://github.com/skybao1024/sprint-flow

Made for: Claude Code.

Or install sprint-flow, the plugin that ships this one along with the rest of its 1 skill, 4 commands, 3 agents.

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-done

README.md
[![agentmods](https://agentmods.dev/badge/commands/skybao1024/sprint-flow/sprint-done.svg)](https://agentmods.dev/commands/skybao1024/sprint-flow/sprint-done)
Your own site
<a href="https://agentmods.dev/commands/skybao1024/sprint-flow/sprint-done"><img src="https://agentmods.dev/badge/commands/skybao1024/sprint-flow/sprint-done.svg" alt="Measured on agentmods" height="20"></a>
Per session 14 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 407 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 1 finding. 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 $0.00014 $0.00407
Opus 5 $0.00007 $0.00204
Sonnet 5 $0.00003 $0.00081
Haiku 4.5 $0.00001 $0.00041

Measured 8d ago against content hash a10ad1c77822, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade B, and why

sprint-done scanned grade B with 1 finding 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 8d 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.

Reads agent configuration directoriesmediumAgent snooping

.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.

cat ~/.claude/plugins/installed_plugins.json | grep -A 3 '"sprint-flow@sprint-flow-marketplace"' | grep installPath | cut -d'"' -f4
plugins/sprint-flow/commands/sprint-done.md · 38 lines

What it actually says

Sprint Done - Claude Code Wrapper

Independently verify and, when needed, repair a manually implemented Sprint Flow sprint using the shared done and loop specs.

Arguments: $ARGUMENTS (optional sprint number)

Resolve Plugin Root

Find PLUGIN_PATH:

cat ~/.claude/plugins/installed_plugins.json | grep -A 3 '"sprint-flow@sprint-flow-marketplace"' | grep installPath | cut -d'"' -f4

If empty, fall back to:

find ~/.claude/plugins -type d -name "sprint-flow" | grep -E "cache.*sprint-flow-marketplace" | head -1

Read {PLUGIN_PATH}/workflow/done-spec.md, {PLUGIN_PATH}/workflow/run-spec.md, and {PLUGIN_PATH}/workflow/loop-spec.md. Load verifier/repairer contracts, loop templates, the primary persona, relevant specialists, and the selected completion template before dispatch or finalization.

Claude Code Adaptation

  • Use $ARGUMENTS as the sprint number when supplied; otherwise use .sprint/config.json current_sprint.
  • Use CLAUDE.md from config when generating next-session instructions.
  • Use /sprint-run {N+1} as the next sprint command.
  • Use a fresh Agent(...) verifier and sequential repair workers according to the shared loop spec.
  • Do not mark a sprint completed unless the latest complete independent verification cycle says PASS.
  • If more sprints remain after PASS, generate the next handoff and verification plan using the shared run and loop requirements.
  • Persist a blocked loop and surface its exact recovery action instead of treating manual completion intent as proof.
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. 8d ago First seen · 38 lines · 14 tokens per session scan B a10ad1c77822

Subscribe to this mod's changes

sprint-done is a command published in the GitHub repository skybao1024/sprint-flow (5 stars, last pushed 21d ago), licensed MIT. It adds 14 tokens to every session and 407 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.