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 shashankreddy509/claude-tdd-kit --skill groom-panelgit clone --depth 1 https://github.com/shashankreddy509/claude-tdd-kitWrote 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/shashankreddy509/claude-tdd-kit/groom-panel)<a href="https://agentmods.dev/skills/shashankreddy509/claude-tdd-kit/groom-panel"><img src="https://agentmods.dev/badge/skills/shashankreddy509/claude-tdd-kit/groom-panel/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/shashankreddy509/claude-tdd-kit/groom-panel"><img src="https://agentmods.dev/badge/skills/shashankreddy509/claude-tdd-kit/groom-panel.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00241 | $0.05079 |
| Opus 5.5 | $0.00096 | $0.02032 |
| Sonnet 5.5 | $0.00048 | $0.01016 |
| Haiku 4.5 | $0.00024 | $0.00508 |
Grade A, and why
groom-panel 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 7d 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 — 344 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Groom panel — four roles on one idea
The user invoked /groom-panel with: {{args}}
One job: turn a raw idea into a groomed ticket set that the existing plan step can consume. Orchestration bucket. It writes exactly one markdown artifact, and files the groomed set into Jira (one Epic up front, children after an approval gate); it still touches no code and no git. It runs BEFORE the plan gate, so nothing here needs code approval.
Not to be confused with /groom, which reads one existing Jira ticket and judges whether it is
ready to estimate. This skill produces the tickets in the first place.
Why four roles and not one strong pass
A single analysis anchors on whoever wrote it. Four independent roles reading the same brief disagree, and the disagreements are the value: a UI need that breaks a test strategy, a data model the designer assumed and the developer did not. Surfacing those before a plan is written is cheaper than discovering them in review. The BA never resolves a real conflict by picking a side — it carries the conflict to the user as a decision.
The panel
| Role | Reads the brief for | Never does |
|---|---|---|
| Business analyst (lead) | What the user actually wants, what is in and out, what success means | Design the UI, choose a library, write tests |
| UI designer | Screens, states, flows, what the user sees when things go wrong | Decide scope, pick an architecture |
| Developer | Feasibility, what it touches, the shape of the work, the risky parts | Expand scope, design the UI, write code |
| Tester | What could break, what is unverifiable, what needs a device or real data | Propose implementations |
Steps
0. Resolve each role's prompt — file first, inlined summary as fallback
Before spawning anyone, resolve the prompt for each of the four roles (ba, dev, ui,
tester): look for docs/business/<role>.md in the invoking project's cwd. If the file
exists, its body is that role's prompt for this run. If docs/business/ is absent, or a
given role's file is missing, fall back to that role's inlined summary in this skill (the BA
brief-writing/synthesis/resolution instructions in steps 1-5, or the bullet in "Role prompts,
in brief" below).
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.
- 7d ago Changed · -5 lines bf7ef844e2df
- 11d ago Changed · +2 lines 430ab568d4b4
- 13d ago Changed · +4 lines 9615f6bebf57
- 16d ago First seen · 343 lines · 241 tokens per session scan A 0211c26f99ba
groom-panel is a skill published in the GitHub repository shashankreddy509/claude-tdd-kit (2 stars, last pushed today), licensed MIT. It adds 241 tokens to every session and 5,079 once invoked, about $0.0010 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 2026-10-04.
Other skills, from other repositories
Jira QA Workflows
Run QA work in Jira like a professional, bug lifecycle and triage, JQL queries for testers, quality dashboards, sprint QA rituals, and REST API automation for bulk bug operations and reporting.
integration-rule-engine
A declarative routing engine that turns ticket / error attributes (reporter, label, project, area path, error class, environment) into a tag + AI agent + priority assignment, so cross-source workflows ("security tickets always go to the OWASP reviewer") stay out of code and in user-editable rules.
stale-ticket-triage
Replace the weekly "look at every ticket older than X days" meeting with a scheduled AI scan that picks close / snooze / keep per ticket plus a one-sentence reason, so a PM can bulk-approve in 90 seconds Monday morning.
plan-backlog
Turn an idea or description (in any format) into a well-formed backlog — epics, user stories with acceptance criteria, sub-tasks — and create it in the team's tracker after approval. Elaborates progressively (guided, the default) or in one shot (--quick). Supports Jira, Linear, GitHub Issues, and Azure DevOps via…
dev-kit-setup
First-use bootstrap for the dev kit. Detects the team's issue tracker, discovers what it can via MCP/CLI, asks only what cannot be discovered, and persists the result to .claude/dev-kit.json in the consuming repo. Use when that file is missing, when the user asks to set up or reconfigure the kit, or when issue-fetch…
issue-fetch
Fetch a work item (summary, status, description, acceptance criteria, comments) from the team's issue tracker and display a clean summary. Supports Jira, Linear, GitHub Issues, and Azure DevOps via adapters. Use whenever a prompt contains an issue reference (e.g. PROJ-1234, ENG-42.