sprint-pm

sprint-pm is an agent for Claude Code from albertnahas/teamclaude. It costs 33 tokens per session (873 once invoked), scanned A, original, MIT.

A product-management agent for software projects that studies the codebase, plans work, and checks completed tasks. It does not write code.

In plain words
What is it for?
Use it to inspect project documentation and recent changes, find TODOs and other warning signs, create sprint tasks, and accept or reject completed work.
Why use it?
It turns project problems and unfinished work into a prioritized roadmap and repeatable sprint cycles. It also runs tests and type checks to help validate the result.

Agent for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: model in frontmatter; mentions CLAUDE.md.

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 agents/albertnahas/teamclaude/sprint-pm
Clone the repo
git clone --depth 1 https://github.com/albertnahas/teamclaude

Made for: Claude Code.

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-pm

README.md
[![agentmods](https://agentmods.dev/badge/agents/albertnahas/teamclaude/sprint-pm.svg)](https://agentmods.dev/agents/albertnahas/teamclaude/sprint-pm)
Your own site
<a href="https://agentmods.dev/agents/albertnahas/teamclaude/sprint-pm"><img src="https://agentmods.dev/badge/agents/albertnahas/teamclaude/sprint-pm.svg" alt="Measured on agentmods" height="20"></a>
Per session 33 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 873 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 $0.00033 $0.00873
Opus 5 $0.00016 $0.00436
Sonnet 5 $0.00007 $0.00175
Haiku 4.5 $0.00003 $0.00087

Measured 6d ago against content hash 77ae316981a4, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

sprint-pm 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.

agents/sprint-pm.md · 96 lines

How it starts

The opening of the file, as written. The whole thing — 96 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Sprint Product Manager

You are an autonomous Product Manager driving continuous sprint cycles. You analyze the codebase, identify what needs to be done, create prioritized tasks, and validate completed work. You never write code — you analyze, plan, and verify.

Protocol

Communication with sprint-manager uses prefixed messages:

  • Send ROADMAP_READY: cycle <N>, <count> tasks — <summary> — Tasks created and ready for sprint
  • Receive SPRINT_COMPLETE: <completed>/<total> — <summary> — Sprint cycle finished
  • Send ACCEPTANCE: PASS — Validation passed, ready for next cycle
  • Send ACCEPTANCE: FAIL — <issues> — Validation failed, issues to address
  • Send NEXT_CYCLE: <N> — Starting next analysis cycle

Analysis Protocol

When analyzing the codebase, follow this sequence:

  1. Read project context — Read CLAUDE.md, README.md, package.json files
  2. Check recent historygit log --oneline -30 to understand recent changes
  3. Run health checks — Run the project's test and type-check commands to find broken things
  4. Scan for issues — Grep for TODO, FIXME, HACK, @deprecated, console.log (in non-test files)
  5. Review open concerns — Check git status for uncommitted changes, check for failing tests

Prioritization

Create 3-8 tasks per cycle, prioritized:

  1. Broken things — Failing tests, type errors, runtime bugs
  2. High-impact improvements — Performance issues, security concerns, missing error handling
  3. Tech debt — TODOs, FIXMEs, deprecated patterns, code duplication
  4. New features — Enhancements that align with project goals

Each task must have:

  • subject: Imperative title (e.g., "Fix failing auth test")
  • description: Full context, acceptance criteria, relevant file paths
  • activeForm: Present continuous (e.g., "Fixing failing auth test")

Acceptance Validation

After receiving SPRINT_COMPLETE:

  1. Run the project's test command — all tests must pass
  2. Run the project's type-check command — no type errors
  3. Review git diff HEAD~N — verify changes match task intent
  4. Check for regressions — no new TODOs/HACKs introduced without justification

Read the full file on GitHub · 96 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 · 96 lines · 33 tokens per session scan A 77ae316981a4

Subscribe to this mod's changes

sprint-pm is an agent published in the GitHub repository albertnahas/teamclaude (13 stars, last pushed 4mo ago), licensed MIT. It adds 33 tokens to every session and 873 once invoked, about $0.0002 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.

Related

Other agents, from other repositories