sprint

sprint is a command for coding agents from albertnahas/teamclaude. It costs 16 tokens per session (2,505 once invoked), scanned A, original, MIT.

An autonomous software-development workflow that coordinates manager and engineer agents and shows progress visually. It can create work from a roadmap or analyze the project and create tasks when no roadmap input is supplied.

In plain words
What is it for?
Use it to run planned or automatically discovered development tasks, coordinate agents, detect project tooling, and run type checks and tests during the sprint.
Why use it?
It organizes multi-step coding work into tasks and development cycles, while using the project’s own configuration or detected package manager and test commands for verification.

Command

Part of the teamclaude plugin — 1 command, 7 agents 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/albertnahas/teamclaude/sprint
Clone the repo
git clone --depth 1 https://github.com/albertnahas/teamclaude

Or install teamclaude, the plugin that ships this one along with the rest of its 1 command, 7 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

README.md
[![agentmods](https://agentmods.dev/badge/commands/albertnahas/teamclaude/sprint.svg)](https://agentmods.dev/commands/albertnahas/teamclaude/sprint)
Your own site
<a href="https://agentmods.dev/commands/albertnahas/teamclaude/sprint"><img src="https://agentmods.dev/badge/commands/albertnahas/teamclaude/sprint.svg" alt="Measured on agentmods" height="20"></a>
Per session 16 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,505 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 $0.00016 $0.02505
Opus 5 $0.00008 $0.01252
Sonnet 5 $0.00003 $0.00501
Haiku 4.5 $0.00002 $0.00250

Measured 4d ago against content hash 29ce08357d83, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, 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 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.

commands/sprint.md · 310 lines

How it starts

The opening of the file, as written. The whole thing — 310 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Sprint: Autonomous Development with Visualization

You are orchestrating an autonomous sprint. The mode depends on whether input was provided.

If $ARGUMENTS.input is provided → follow Manual Mode below (you parse the roadmap, create tasks, 2-agent sprint) If no arguments → follow Autonomous Mode below (PM agent analyzes codebase, creates tasks, continuous 3-agent cycles)


Step 0: Detect Project Context

Before starting the sprint, detect the project's tooling so agents use the correct commands.

0a. Check for .sprint.yml

Read .sprint.yml in the project root (if it exists). This provides explicit configuration:

verification:
  type_check: "pnpm type-check"
  test: "pnpm test --run"

If .sprint.yml exists, use its values and skip auto-detection.

0b. Auto-detect Package Manager

Check which lockfile exists in the project root:

  • pnpm-lock.yamlpnpm
  • yarn.lockyarn
  • package-lock.jsonnpm
  • bun.lockb or bun.lockbun
  • None found → no package manager detected

0c. Auto-detect Commands

Read package.json scripts (if it exists):

  • If scripts.type-check exists → type-check command is {pm} type-check
  • If scripts.typecheck exists → type-check command is {pm} typecheck
  • If neither → no type-check command (agents skip it)
  • If scripts.test exists → test command is {pm} test --run
  • If neither → no test command (agents skip it)

For non-JS projects (no package.json):

  • Check for Makefilemake test, make check
  • Check for Cargo.tomlcargo check, cargo test
  • Check for go.modgo vet ./..., go test ./...
  • Check for pyproject.toml or setup.pypytest

0d. Build Context String

Compose a context string to inject into agent spawn prompts:

The project uses {pm}. Type-check: `{type_check_cmd}`. Test: `{test_cmd}`.

If a command is unavailable, note it: "No type-check command available — skip type-check verification."


Manual Mode

Read the full file on GitHub · 310 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 · 310 lines · 16 tokens per session scan A 29ce08357d83

Subscribe to this mod's changes

sprint is a command published in the GitHub repository albertnahas/teamclaude (13 stars, last pushed 4mo ago), licensed MIT. It adds 16 tokens to every session and 2,505 once invoked, about $0.0001 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 2026-08-30.