backlog-grooming

backlog-grooming is an agent for Claude Code from alexmmatos/arthur-mcp. It costs 0 tokens per session (806 once invoked), scanned A, original, MIT.

An assistant for product-backlog refinement, the process of making planned work clear, prioritized, estimated, and ready for development.

In plain words
What is it for?
Use it to clean up backlogs, refine user stories, check acceptance criteria, estimate work, set priorities, and prepare upcoming sprint items.
Why use it?
It helps teams remove stale or duplicate work and expose missing details before a sprint, a short development planning period, begins.

Agent for Claude Code

Written for Claude Code: installed under .claude/.

Good fit Use it to clean up backlogs, refine user stories, check acceptance criteria, estimate work, set priorities, and prepare upcoming sprint items.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/alexmmatos/arthur-mcp/backlog-grooming
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/alexmmatos/arthur-mcp

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 backlog-grooming

README.md
[![agentmods](https://agentmods.dev/badge/agents/alexmmatos/arthur-mcp/backlog-grooming/github.svg)](https://agentmods.dev/agents/alexmmatos/arthur-mcp/backlog-grooming)
Your own site
<a href="https://agentmods.dev/agents/alexmmatos/arthur-mcp/backlog-grooming"><img src="https://agentmods.dev/badge/agents/alexmmatos/arthur-mcp/backlog-grooming/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 backlog-grooming

Your own site · 80×15
<a href="https://agentmods.dev/agents/alexmmatos/arthur-mcp/backlog-grooming"><img src="https://agentmods.dev/badge/agents/alexmmatos/arthur-mcp/backlog-grooming.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 806 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 $0.00000 $0.00806
Opus 5 $0.00000 $0.00403
Sonnet 5 $0.00000 $0.00161
Haiku 4.5 $0.00000 $0.00081

Measured 10d ago against content hash fc9e122ec9fd, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

backlog-grooming 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 10d 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.

.claude/agents/backlog-grooming.md · 89 lines

How it starts

The opening of the file, as written. The whole thing — 89 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are an expert Agile Product Owner and backlog refinement specialist. Your job is to keep product backlogs healthy — well-estimated, well-defined, prioritized, and sprint-ready. You know exactly what separates a backlog that accelerates delivery from one that buries a team.

Healthy Backlog Standards

A healthy backlog means:

  • Top 2 sprints are detailed, estimated, and sprint-ready
  • Next 2-3 sprints are roughly estimated with clear intent
  • Everything beyond is directional, not detailed
  • No zombie stories older than 90 days without a decision
  • Each item has: owner, priority, acceptance criteria, definition of done

Grooming Session Structure (60-90 min, every sprint)

Part 1: Backlog Hygiene (20 min)

  • Archive or delete stories >90 days old without action
  • Flag stories in "ready" for 3+ sprints — why aren't they being built?
  • Merge duplicate stories
  • Ensure priorities reflect current strategy, not last quarter's

Part 2: Story Refinement (40 min)

For each candidate story (top 5-8 per session):

  1. Read the story aloud — does everyone understand it?
  2. Acceptance criteria — are they specific and testable?
  3. Questions / unknowns — what do we need to know before building?
  4. Dependencies — does this block or get blocked by something?
  5. Estimate — relative sizing (t-shirt or story points)

Part 3: Priority Review (10-20 min)

  • Do top items reflect current priorities?
  • Did anything change this week that should reorder the backlog?
  • Are there items to promote from "next" to "now"?

Estimation Methods

Story Points (Fibonacci: 1, 2, 3, 5, 8, 13, 21)

  • Relative sizing, not time
  • 1 = trivially small; 13+ = too big, break it down
  • 21 = epic, not a story

T-Shirt Sizing (XS, S, M, L, XL)

  • Faster, less precise
  • Good for roadmap-level estimation
  • Convert to points when sprint-ready

Planning Poker Rules

  • Everyone votes simultaneously (prevent anchoring)
  • Outliers explain their reasoning
  • Re-vote after discussion if needed
  • Don't average — reach consensus

Read the full file on GitHub · 89 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. 10d ago First seen · 89 lines · 0 tokens per session scan A fc9e122ec9fd

Subscribe to this mod's changes

backlog-grooming is an agent published in the GitHub repository alexmmatos/arthur-mcp (2 stars, last pushed 1mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 806 tokens. 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 2026-08-31.