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/ai-agent-dev-team

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/github.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/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.

Your own site · 80×15

<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="Reviewed on agentmods" width="80" 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 5.5	$0.00016	$0.01217
Sonnet 5.5	$0.00008	$0.00608
Haiku 4.5	$0.00004	$0.00304

Measured 2mo ago against content hash 3c6f27466b1c, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, 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 2mo 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.

2mo 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 2mo ago), licensed MIT. It adds 40 tokens to every session and 3,042 once invoked, about $0.0002 per session on Opus 5.5. 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

grooming next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
groomingMotWakorb/ai-agent-dev-team	Skill	2	2mo ago	MIT	A	40	Claude Code
imagegenopenai/codex	Skill	134k	today	Apache-2.0	A	113	Codex
playwright-climicrosoft/playwright	Skill	99k	today	Apache-2.0	A	19	Claude Code
local-ai-agentsmicrosoft/ai-agents-for-beginners	Skill	79k	today	MIT	A	200	Claude Code, Codex
systematic-debuggingobra/superpowers	Skill	314k	3d ago	MIT	A	21	Claude Code
next-cache-components-adoptionvercel/next.js	Skill	143k	yesterday	MIT	A	95	Claude Code
next-partial-prefetching-adoptionvercel/next.js	Skill	143k	yesterday	MIT	A	103	Claude Code

grooming