grooming-issues

grooming-issues is a skill for Claude Code from skyfox675/agents-skills. It costs 197 tokens per session (2,068 once invoked), scanned A, original, MIT.

A question-driven process for turning an unclear Jira issue into a development-ready description. It clarifies the requested outcome and scope without deciding the technical solution or estimating the work.

In plain words
What is it for?
Use it to ask the engineering or project lead focused questions, write the agreed intent into the issue, and prepare it for technical investigation.
Why use it?
It prevents teams from sizing or building work before they agree on what the request actually means.

Skill for Claude Code

Written for Claude Code: installed under .claude/. Also seen: mentions CLAUDE.md; mentions subagents.

Good fit Use it to ask the engineering or project lead focused questions, write the agreed intent into the issue, and prepare it for technical investigation.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/skyfox675/agents-skills/grooming-issues
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 skyfox675/agents-skills --skill grooming-issues
Clone the repo
git clone --depth 1 https://github.com/skyfox675/agents-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 grooming-issues

README.md
[![agentmods](https://agentmods.dev/badge/skills/skyfox675/agents-skills/grooming-issues/github.svg)](https://agentmods.dev/skills/skyfox675/agents-skills/grooming-issues)
Your own site
<a href="https://agentmods.dev/skills/skyfox675/agents-skills/grooming-issues"><img src="https://agentmods.dev/badge/skills/skyfox675/agents-skills/grooming-issues/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 grooming-issues

Your own site · 80×15
<a href="https://agentmods.dev/skills/skyfox675/agents-skills/grooming-issues"><img src="https://agentmods.dev/badge/skills/skyfox675/agents-skills/grooming-issues.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 197 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,068 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. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 $0.00197 $0.02068
Opus 5 $0.00098 $0.01034
Sonnet 5 $0.00039 $0.00414
Haiku 4.5 $0.00020 $0.00207

Measured 6d ago against content hash a360590f8739, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

grooming-issues 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 6d 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/skills/grooming-issues/SKILL.md · 91 lines

How it starts

The opening of the file, as written. The whole thing — 91 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Grooming Issues: capture the intent before anyone sizes or builds it

An issue can exist — a title, a paragraph, maybe a stakeholder's wish — long before it is buildable. Grooming is the pass that turns that into a story the team can trust: through questions to the engineering/project lead, it pins the intent, scope, and direction until the written issue faithfully reflects the ask, then writes that into the body in the six-section groomed shape. It captures the what and why. It deliberately does not decide the how or the cost — that is the technical-recon skill, which runs next.

The pipeline: a raw issue → grooming (this skill: intent to ≥90%, body groomed) → technical-recon (dev-side approach + LoE) → dispatch (per the orchestrating-slots and issue-locking skills). Grooming hands a clean story to recon; recon hands a sized, vetted issue to dispatch.

Compose with the siblings: the six-section anatomy and label taxonomy come from the issue-filing skill (gh-issue-filing / jira-issue-filing); the emoji-answerable clarification loop is the same one the technical-recon skill documents (reuse its comment format and template); when grooming completes, the technical-recon skill picks the issue up.

Project bindings

Define in the adopting project's CLAUDE.md; referred to by placeholder.

Binding Meaning Example
<groomed-state> Label/status meaning "story is groomed, ready for technical recon" a groomed label, or a Ready for Tech Review status
<needs-input-state> "questions are pending the lead's answers" needs-spec-input
<ac-section-heading> The heading that marks the acceptance-criteria block in the body ## Acceptance criteria

Grooming reuses the issue-filing skill's body anatomy and the technical-recon skill's question channels; it adds no labels of its own beyond the two states above.

The one hard rule: do not touch existing acceptance criteria

If the issue already has acceptance criteria written, leave them exactly as they are — verbatim — unless the operator explicitly tells you to change them in this run. Existing AC is a contract that stakeholders may have negotiated and approved; an agent silently rewriting, tightening, or "improving" it changes the scope of work without anyone agreeing to the change. This has shipped the wrong thing in practice.

Read the full file on GitHub · 91 lines

Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 6d ago First seen · 91 lines · 197 tokens per session scan A a360590f8739

Subscribe to this mod's changes

grooming-issues is a skill published in the GitHub repository skyfox675/agents-skills (10 stars, last pushed 9d ago), licensed MIT. It adds 197 tokens to every session and 2,068 once invoked, about $0.0010 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.

Related

Other skills, from other repositories