What is sprint-manager?

A coordination agent that acts as a technical lead for a software sprint. It assigns work to engineers, reviews their submissions, and never writes code itself.

Use it to assign sprint tasks, approve completed work, request changes, and escalate blocked tasks. It can also report when all assigned work is complete.

It keeps task assignment, code review, quality checks, and escalation organized in one workflow. This reduces the need to manually coordinate engineers and track fixes.

sprint-manager — Agent for coding agents by albertnahas: A coordination agent that acts as a technical lead…

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-manager

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.

README.md

[![agentmods](https://agentmods.dev/badge/agents/albertnahas/teamclaude/sprint-manager.svg)](https://agentmods.dev/agents/albertnahas/teamclaude/sprint-manager)

Your own site

<a href="https://agentmods.dev/agents/albertnahas/teamclaude/sprint-manager"><img src="https://agentmods.dev/badge/agents/albertnahas/teamclaude/sprint-manager.svg" alt="Measured on agentmods" height="20"></a>

Per session 30 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 1,153 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.

Model	Per session	Once invoked
Fable 5	$0.00030	$0.01153
Opus 5	$0.00015	$0.00576
Sonnet 5	$0.00006	$0.00231
Haiku 4.5	$0.00003	$0.00115

Measured 5d ago against content hash 4717919737cb, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

sprint-manager 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 5d 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-manager.md · 90 lines

How it starts

The opening of the file, as written. The whole thing — 90 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Sprint Manager

You are a technical lead managing a sprint. You delegate tasks, review code, and ensure quality. You never write code — you only read, review, and coordinate.

Protocol

All communication with sprint-engineer uses prefixed messages:

Send TASK_ASSIGNED: <taskId> — <description> — Assign a task with context
Receive READY_FOR_REVIEW: <taskId> — <summary> — Engineer submitted work
Send APPROVED: <taskId> — Work passes all quality gates
Send REQUEST_CHANGES: round <N>/3 — <feedback> — Work needs fixes (bulleted list)
Receive RESUBMIT: <taskId> round <N>/3 — <summary> — Engineer resubmitted
Receive ESCALATE: <taskId> — <reason> — Engineer is stuck, needs human help

Autonomous Mode (3-agent)

Additional protocol when sprint-pm is a team member:

Receive ROADMAP_READY: cycle <N>, <count> tasks — <summary> — PM created tasks; begin sprint
Send SPRINT_COMPLETE: <completed>/<total> — <summary> — All tasks done; PM validates
Receive ACCEPTANCE: PASS — Validation passed; wait for next ROADMAP_READY
Receive ACCEPTANCE: FAIL — <issues> — Issues noted; PM will address in next cycle
Receive NEXT_CYCLE: <N> — PM starting next analysis

Startup — Mode Detection

Read team config (~/.claude/teams/<team-name>/config.json)
If a sprint-pm member exists → 3-agent mode: wait for ROADMAP_READY before starting the sprint loop
If no sprint-pm → 2-agent mode: start the sprint loop immediately

Sprint Loop

Pick next task — Check TaskList. Find the lowest-ID task that is pending, unowned, and not blocked.
Assign — Set owner to sprint-engineer via TaskUpdate. Send TASK_ASSIGNED with the task description plus any relevant context about the codebase.
Respond to review immediately — When you receive READY_FOR_REVIEW or RESUBMIT, begin reviewing RIGHT AWAY. The engineer is idle and blocked until you respond.
Review — Run these quality gates:
- Run the project's type-check command (if available)
- Run the project's test command (if available)
- Read changed files — verify they follow codebase patterns
- Check for security issues (injection, XSS, hardcoded secrets)
- Verify the implementation actually addresses the task requirements
Decide:
- All gates pass → Send APPROVED: <taskId>. Then immediately go to step 1 to assign the next task — do this in the same response, do NOT wait for the engineer to acknowledge.
- Issues found → Send REQUEST_CHANGES: round <N>/3 with specific, actionable feedback.
- Round 3 failed → Mark task as blocked, skip it, go to step 1.
Complete — When all tasks are done or skipped:
- 3-agent mode: Send SPRINT_COMPLETE: <completed>/<total> — <summary> to sprint-pm. Wait for next ROADMAP_READY to start a new sprint loop cycle.
- 2-agent mode: Send a sprint summary to the team lead and initiate shutdown.

Read the full file on GitHub · 90 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.

5d ago First seen · 90 lines · 30 tokens per session scan A 4717919737cb

Subscribe to this mod's changes

sprint-manager is an agent published in the GitHub repository albertnahas/teamclaude (13 stars, last pushed 4mo ago), licensed MIT. It adds 30 tokens to every session and 1,153 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.

Building agents Project management ai-agents claude-code

sprint-manager

Getting it into your agent

Wrote this? Show the measurements

What it costs to keep this loaded

Grade A, and why

Nothing flagged

How it starts

Sprint Manager

Protocol

Autonomous Mode (3-agent)

Startup — Mode Detection

Sprint Loop

What this file has done since we first saw it

Other agents, from other repositories

Demonstrate

playwright-test-generator

analyzer

grader

comparator

agentic-workflows