groom

A backlog review that examines open GitHub issues and the skills available in a repository. It adds missing skill labels, checks priorities, and identifies work that has been in progress too long.

In plain words
What is it for?
Use it to discover available skills, create missing GitHub labels, tag issues, verify priority labels, and flag stale in-progress work.
Why use it?
It helps teams understand what each issue concerns and which work needs attention. This reduces unlabelled tasks, unclear priorities, and forgotten in-progress issues.

Skill for Claude CodeCodex

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 skills/abilityai/abilities/groom
Any agent
npx skills add Abilityai/abilities --skill groom
Clone the repo
git clone --depth 1 https://github.com/Abilityai/abilities

Made for: Claude Code, Codex.

Per session 26 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 999 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 1 finding. 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.

ModelPer sessionOnce invoked
Fable 5 $0.00026 $0.00999
Opus 5 $0.00013 $0.00500
Sonnet 5 $0.00005 $0.00200
Haiku 4.5 $0.00003 $0.00100

Measured 2d ago against content hash 9f5d12ac7e59, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade B, and why

groom scanned grade B with 1 finding 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 2d 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.

Enumerates other installed skillsmediumAgent snooping

Other skills' SKILL.md files reveal prompts, capabilities and secrets that should be invisible to peers.

ls .claude/skills/
plugins/agent-dev/skills/groom/SKILL.md · 130 lines

How it starts

The opening of the file, as written. The whole thing — 130 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Groom

ℹ️ First, set expectations: before anything else, print one short line with this skill's version and its most recent change — the top entry of metadata.changelog above — e.g. groom vX.Y — recent: <summary>. Then proceed.

Audit the open issue backlog for this agent. Tags issues with the skill they affect, surfaces missing priorities, and flags stale in-progress work. This is the agent-dev equivalent of backlog grooming — but the "areas" are skills, not features.

State Dependencies

Source Location Read Write Description
GitHub Issues Current repo Yes Yes Backlog issues
GitHub Labels skill:, status:, priority:* Yes Yes Apply missing labels
Agent Skills .claude/skills/ Yes No Available skills to tag against

Process

Step 1: Discover Available Skills

ls .claude/skills/

Build a list of skill names from the directory. These become the valid skill:* label values.

Also check if skill:* labels already exist in the repo:

gh label list --json name --jq '.[].name' | grep '^skill:'

Create any missing skill labels (one per skill directory):

gh label create "skill:$SKILL_NAME" --color "0075CA" --description "Issues affecting the $SKILL_NAME skill" 2>/dev/null || true

Step 2: Fetch All Open Issues

gh issue list --state open --json number,title,body,labels --limit 100

Step 3: Tag Untagged Issues

For each issue that has NO skill:* label:

  1. Show the issue title and first 3 lines of body
  2. List available skills
  3. Ask (in one message, not per-issue): suggest which skill this issue most likely affects based on the title/body, then confirm or let user override

Tagging options per issue:

  • A specific skill from .claude/skills/ → apply skill:<name>
  • Project-level → no skill tag (affects the agent as a whole, not a specific skill)
  • Skip → leave untagged for now

Apply the label:

Read the full file on GitHub · 130 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. 2d ago First seen · 130 lines · 26 tokens per session scan B 9f5d12ac7e59

Subscribe to this mod's changes

groom is a skill published in the GitHub repository Abilityai/abilities (11 stars, last pushed 14d ago), licensed MIT. It adds 26 tokens to every session and 999 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it B with 1 finding (enumerates other installed skills). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.