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.
npx skills add skyfox675/agents-skills --skill grooming-issuesgit clone --depth 1 https://github.com/skyfox675/agents-skillsWrote 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.
[](https://agentmods.dev/skills/skyfox675/agents-skills/grooming-issues)<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.
<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>- NVIDIA SkillSpector pass
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 | $0.00197 | $0.02068 |
| Opus 5 | $0.00098 | $0.01034 |
| Sonnet 5 | $0.00039 | $0.00414 |
| Haiku 4.5 | $0.00020 | $0.00207 |
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.
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.
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.
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.
- 6d ago First seen · 91 lines · 197 tokens per session scan A a360590f8739
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.
Other skills, from other repositories
recipe-create-meet-space
Create a Google Meet meeting space and share the join link.
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…
atmos-config
Atmos root configuration: atmos.yaml discovery, precedence, deep merging, basepath, imports, minimal bootstrap, and routing to narrower Atmos skills.
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…
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.
remove
Remove a deployed framework or addon from the current workspace.