A backlog-refinement workflow for preparing upcoming work items, called beads, before planning them.

Reviewing backlog items, identifying affected parts of a project, estimating effort, and deciding whether work is ready to build.

It checks whether each item has clear user value, a realistic size, dependencies, and acceptance criteria; acceptance criteria are the conditions that define done.

grooming — Skill for Claude Code by MotWakorb

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.

Any agent

npx skills add MotWakorb/ai-agent-dev-team --skill grooming

Clone the repo

git clone --depth 1 https://github.com/MotWakorb/ai-agent-dev-team

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/motwakorb/ai-agent-dev-team/grooming.svg)](https://agentmods.dev/skills/motwakorb/ai-agent-dev-team/grooming)

Your own site

<a href="https://agentmods.dev/skills/motwakorb/ai-agent-dev-team/grooming"><img src="https://agentmods.dev/badge/skills/motwakorb/ai-agent-dev-team/grooming.svg" alt="Measured on agentmods" height="20"></a>

Per session 40 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 3,042 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.

Model	Per session	Once invoked
Fable 5.1	$0.00040	$0.03042
Opus 5	$0.00020	$0.01521
Sonnet 5	$0.00008	$0.00608
Haiku 4.5	$0.00004	$0.00304

Measured 8d ago against content hash 3c6f27466b1c, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

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 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.

grooming/SKILL.md · 235 lines

How it starts

The opening of the file, as written. The whole thing — 235 lines — stays where its author put it; the contents beside it link to each section on GitHub.

This is not planning. This is preparing work to BE planned — but only work that delivers user value. Before an item gets sized, scoped, and handed to personas for evaluation, it passes through a user value gate. If we can't articulate who benefits and how we'll know, we don't refine it — we question whether it belongs on the board.

Preflight: Verify Onboarding & Effective Tier

Before any other step, verify deployment-tier setup. Defaulting to enterprise rigor across the board is the failure mode this preflight prevents.

Check COMPONENTS.md exists at the repo root. If missing, refuse to run and tell the PO:

This project hasn't been onboarded yet. Run /onboard first — it produces COMPONENTS.md, which records each component's deployment tier. Without it, grooming will inflate effort estimates and acceptance criteria with enterprise rigor. See _shared/deployment-tier.md for the tier model.

Do not proceed.
For each candidate bead being groomed, identify the in-scope component(s) and their tiers from COMPONENTS.md. Beads should reference components in their description; if not, ask the PO before grooming.
Resolve cross-tier conflicts per bead using strictest-wins by default. A bead that touches a startup-tier and a home-lab-tier component is groomed at startup tier.

Inject tier context into every agent prompt. Every prompt below must include, per bead:

Read ~/.claude/skills/_shared/deployment-tier.md.
Bead [ID] in-scope components and tiers: [component] ([tier]), ...
Effective tier for this bead: [tier]
Size effort, define acceptance criteria, and identify dependencies at the effective tier — not above. Do not require enterprise acceptance criteria for home-lab work.

Model Selection

When spawning agents, pass model: sonnet for all 10 grooming agents. Sizing and acceptance-criteria work is pattern-matching — sonnet handles it.

Tier modulation: at home-lab effective tier per bead, downshift to haiku for all personas except security-engineer (holds at sonnet).

Read the full file on GitHub · 235 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.

8d ago First seen · 235 lines · 40 tokens per session scan A 3c6f27466b1c

Subscribe to this mod's changes

grooming is a skill published in the GitHub repository MotWakorb/ai-agent-dev-team (2 stars, last pushed 26d ago), licensed MIT. It adds 40 tokens to every session and 3,042 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 2026-08-31.

Planning Project management

recipe-create-meet-space

Create a Google Meet meeting space and share the join link.

googleworkspace/cli · 18 tokens

workthreads

SpecStory Workthreads - a weekly work-thread rollup across a team's repos from SpecStory coding histories (any agent - Claude Code, Codex, Cursor, Gemini, and more). It groups the window's sessions into threads of work per project and labels each new / open / recently closed, so a lead sees what shipped, what is still…

specstoryai/getspecstory · 126 tokens

atmos-config

Atmos root configuration: atmos.yaml discovery, precedence, deep merging, basepath, imports, minimal bootstrap, and routing to narrower Atmos skills.

cloudposse/atmos · 31 tokens

story-readiness

Validate that a story file is implementation-ready. Checks for embedded GDD requirements, ADR references, engine notes, clear acceptance criteria, and no open design questions. Produces READY / NEEDS WORK / BLOCKED verdict with specific gaps. Use when user says 'is this story ready', 'can I start on this story', 'is…

Donchitos/Claude-Code-Game-Studios · 77 tokens

autotask-creator

Rules for automation CRUD from the group-chat commander. The commander does not call mutation tools and does not edit cloud/autotasks files directly. It emits one or more top-level ... containers in its final text; the bus parses and applies them after the turn.

Orkas-AI/Orkas · 5 tokens

monorepo-management

Master monorepo management with Turborepo, Nx, and pnpm workspaces to build efficient, scalable multi-package repositories with optimized builds and dependency management. Use when setting up monorepos, optimizing builds, or managing shared dependencies.

wshobson/agents · 54 tokens

grooming