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 groomgit 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)<a href="https://agentmods.dev/skills/shashankreddy509/claude-tdd-kit/groom"><img src="https://agentmods.dev/badge/skills/shashankreddy509/claude-tdd-kit/groom/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"><img src="https://agentmods.dev/badge/skills/shashankreddy509/claude-tdd-kit/groom.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 | $0.00134 | $0.01504 |
| Opus 5 | $0.00067 | $0.00752 |
| Sonnet 5 | $0.00027 | $0.00301 |
| Haiku 4.5 | $0.00013 | $0.00150 |
Grade A, and why
groom 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 10d 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 — 98 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Groom — pre-grooming readiness brief
The user invoked /groom with: {{args}}
Pre-grooming analysis of a Jira ticket: a readiness + spec brief so the ticket can be groomed/estimated. Read-only — writes ONE artifact, touches no code and no Jira. If no argument, ask which ticket.
This runs BEFORE a ticket is approved to work. It answers "is this ready to estimate, and what will
it touch" — not "how do I fix/build it" (that's /build, after grooming). It never plans an
implementation, never assigns a story-point number, never edits Jira.
Discover the project's Jira config (cloudId + key) from the project CLAUDE.md — scan it for a
line of the form Jira: cloudId=<uuid> key=<PROJECTKEY> and use those values;
never hardcode a cloudId. If not found, ask for the cloudId + key.
Then resolve the Jira MCP dialect. Atlassian MCP servers differ per machine: one exposes
camelCase names (mcp__atlassian__getJiraIssue) with cloudId REQUIRED; another exposes snake_case
under a jira prefix and resolves the site internally, with no cloudId at all. If the
tdd-pipeline plugin is installed, follow its references/jira-mcp.md. Otherwise probe inline: try
the camelCase name via ToolSearch; if nothing resolves, search by keyword (ToolSearch "+jira issue") and use what comes back. Pass cloudId ONLY when the resolved schema has it — otherwise
omit it and ignore the cloudId= half of the line. Never hardcode a tool name.
Steps
-
Fetch the ticket. Using the get-issue verb resolved above:
<get-issue tool>(issueIdOrKey=<TICKET>), addingcloudId=<discovered>only if its schema requires it. Also pull linked/sibling issues and attachments if referenced. Capture summary, description, issuetype, acceptance criteria, parent epic, comments. -
Restate the ask. One paragraph: what is actually being requested, in your own words, so a wrong reading surfaces at grooming — not mid-sprint. State assumptions explicitly.
-
Acceptance-criteria audit. List the ACs verbatim. For each, judge: present? testable (observable pass/fail)? Flag missing, vague, or contradictory ACs as blockers to estimate — a ticket without testable ACs is not groom-ready.
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.
- 10d ago First seen · 98 lines · 134 tokens per session scan A 5862ed92145e
groom is a skill published in the GitHub repository shashankreddy509/claude-tdd-kit (2 stars, last pushed 18d ago), licensed MIT. It adds 134 tokens to every session and 1,504 once invoked, about $0.0007 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 2026-08-31.
Other skills, from other repositories
timeline-creator
Create HTML timelines and project roadmaps with Gantt charts, milestones, phase groupings, and progress indicators. Use when users request timelines, roadmaps, Gantt charts, project schedules, or milestone visualizations.
implement-issue
Drive a GitHub issue from branch to pull request — read the issue, create a feature branch, implement the change, run the project's build and tests, then commit, push, and open a PR. Language and build-tool agnostic. Use when asked to implement, fix, or resolve a GitHub issue by number.
jira-administration
Complete JIRA project and system administration including projects, automation rules, permissions, users, notifications, screens, issue types, and workflows. Use when managing project structure, automating work, configuring team access, or setting up issue tracking.
jira-time-tracking
Time tracking, worklogs, and time reports. TRIGGERS: 'log time', 'time spent on', 'log hours', 'log work', 'worklog', 'time tracking', 'timesheet', 'how much time', 'time logged', 'time report', 'export timesheet', 'set estimate', 'remaining estimate', 'original estimate'. Use for time-related queries and operations…
jira-custom-fields
Custom field discovery and configuration. TRIGGERS: 'field ID for', 'what's the field ID', 'what is the field ID', 'list custom fields', 'what fields are available', 'what custom fields', 'show custom fields', 'customfield', 'find field', 'agile fields', 'configure agile fields', 'story points field'. Use for JIRA…
jira-issue-management
Core JIRA issue CRUD - create bugs/tasks/stories, get issue details, update fields, delete issues. TRIGGERS: 'show me [KEY]', 'get issue [KEY]', 'view issue', 'create a bug/task/story', 'update [KEY]', 'delete [KEY]', 'details of [KEY]', 'look up [KEY]', 'what's in [KEY]'. NOT FOR: epics (use jira-agile)…