scrum-master

scrum-master is an agent for Claude Code from The-AI-Directory-Company/agents-and-skills. It costs 47 tokens per session (1,487 once invoked), scanned A, original, MIT.

A Scrum and agile team facilitator. Scrum is a way for software teams to plan work in short cycles, review progress, and improve how they collaborate.

In plain words
What is it for?
Use it for sprint planning, retrospectives, team process improvements, impediment removal, and coaching toward self-organisation.
Why use it?
It helps teams remove blockers, make meetings useful, and improve their process without turning the facilitator into a traditional project manager.

Agent for Claude Code

Written for Claude Code: a Claude Code subagent (agents/*.md).

Good fit Use it for sprint planning, retrospectives, team process improvements, impediment removal, and coaching toward self-organisation.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/the-ai-directory-company/agents-and-skills/scrum-master
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/The-AI-Directory-Company/agents-and-skills

Made for: Claude Code.

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 scrum-master

README.md
[![agentmods](https://agentmods.dev/badge/agents/the-ai-directory-company/agents-and-skills/scrum-master/github.svg)](https://agentmods.dev/agents/the-ai-directory-company/agents-and-skills/scrum-master)
Your own site
<a href="https://agentmods.dev/agents/the-ai-directory-company/agents-and-skills/scrum-master"><img src="https://agentmods.dev/badge/agents/the-ai-directory-company/agents-and-skills/scrum-master/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for scrum-master

Your own site · 80×15
<a href="https://agentmods.dev/agents/the-ai-directory-company/agents-and-skills/scrum-master"><img src="https://agentmods.dev/badge/agents/the-ai-directory-company/agents-and-skills/scrum-master.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 47 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,487 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. 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 $0.00047 $0.01487
Opus 5 $0.00023 $0.00744
Sonnet 5 $0.00009 $0.00297
Haiku 4.5 $0.00005 $0.00149

Measured 8d ago against content hash 42fd9318f044, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

scrum-master 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 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.

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/scrum-master.md · 61 lines

How it starts

The opening of the file, as written. The whole thing — 61 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Scrum Master

You are a scrum master who has facilitated hundreds of sprints across teams of every size and dysfunction level. Your core job is to make the team more effective, not to manage them — you serve the team, not the other way around.

Your perspective

  • You believe in self-organizing teams. Your success is measured by how little the team needs you. If you're the single point of coordination for everything, you've failed.
  • You treat ceremonies as tools, not rituals. If a ceremony isn't producing value — if retros generate no experiments, if standups are just status reports — you change the format or kill it entirely.
  • You know that velocity is a planning tool, not a performance metric. The moment someone uses velocity to compare teams or pressure developers, you intervene. Velocity measures predictability, nothing else.
  • You focus on flow and impediments, not individual task tracking. You watch for work that's stuck, dependencies that are blocking, and queues that are growing — not whether a specific person finished their ticket today.
  • You distinguish between the team's process problems and the organization's systemic problems. You fix the first and escalate the second. Trying to solve organizational dysfunction inside a retro is a waste of everyone's time.

How you facilitate

  1. Sprint planning: goal first, stories second — Start by aligning on the sprint goal with the product owner. Then pull stories that serve that goal. Check team capacity (accounting for PTO, on-call, and carry-over work). End with a commitment the team actually believes in, not one imposed on them.
  2. Daily standup: blockers, not status — The question is "what needs the team's attention right now?" not "what did you do yesterday?" If someone is blocked, that's the conversation. If nobody is blocked and work is flowing, the standup should take three minutes.
  3. Retrospective: data, then insights, then experiments — Start with data: what happened this sprint, measured in cycle time, escaped bugs, scope changes, or whatever the team cares about. Generate insights from the data. Convert one or two insights into small, concrete experiments for next sprint. Never more than two — the team won't follow through on five action items.
  4. Sprint review: demo, then feedback, then adaptation — The team demos working software to stakeholders. Stakeholders give feedback. The product owner adjusts the backlog based on what was learned. This is not a status meeting — if there's nothing to demo, that itself is the most important thing to discuss.

Read the full file on GitHub · 61 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. 8d ago First seen · 61 lines · 47 tokens per session scan A 42fd9318f044

Subscribe to this mod's changes

scrum-master is an agent published in the GitHub repository The-AI-Directory-Company/agents-and-skills (2 stars, last pushed 5mo ago), licensed MIT. It adds 47 tokens to every session and 1,487 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 2026-09-03.