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 shape-ideagit 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/shape-idea)<a href="https://agentmods.dev/skills/shashankreddy509/claude-tdd-kit/shape-idea"><img src="https://agentmods.dev/badge/skills/shashankreddy509/claude-tdd-kit/shape-idea/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/shape-idea"><img src="https://agentmods.dev/badge/skills/shashankreddy509/claude-tdd-kit/shape-idea.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 | $0.00154 | $0.02179 |
| Opus 5.5 | $0.00062 | $0.00872 |
| Sonnet 5.5 | $0.00031 | $0.00436 |
| Haiku 4.5 | $0.00015 | $0.00218 |
Grade A, and why
shape-idea 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 — 146 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Shape idea — conversation in, prompt out
The user invoked /shape-idea with: {{args}}
One job: turn a raw idea into ONE prompt file the user pastes somewhere else. Utility bucket.
The value is the conversation BEFORE the prompt — pushback, what already exists, what is really
being asked — so the prompt's "Decided" section is settled and the next step does not re-ask it.
/groom-panel caps its own questions at four in one round; this skill is where the long argument
happens.
Steps
1. Get the idea and the target repo
If {{args}} is empty, ask for the idea. Then settle, in one AskUserQuestion call if not
already clear from the idea:
- Target repo — the repo where the prompt will be RUN (not necessarily the cwd). The prompt
file goes in THAT repo's
docs/. - Target kind —
groom(run/groom-panelin that repo: Jira Epic + tickets, no code) orcloud(paste into a claude.ai/code cloud session: builds on GitHub, opens a PR). Cloud only fits GitHub-only work; work bound to the user's machine (local schedulers, daemons, local data) and builds that need hosts the cloud cannot reach (e.g. Android Gradle against Google Maven) cannot run there — say so and steer togroom.
2. Inventory what already exists — before any question
Spawn ONE Explore agent on the target repo: its CLAUDE.md, handoff/status docs, existing
features, connectors, open Jira epics named in docs, anything in the idea that may already be
built, and the shared components and functions (UI pieces, data writers) the idea could call with
its own data instead of rebuilding. End its prompt with the verified-vs-inferred return contract. Spot-check any "already
exists" / "missing" claim yourself (one grep) before relaying it. Half of a past idea's asks
already existed; this step is what found it.
If the idea names an outside product, tool or model (often misheard in a voice dump), confirm the
exact name with the user, then research it with WebSearch in the same step: what it is, how it
plugs in, cost, what data leaves the machine, maturity. Cite the sources in your reply. Never build
questions on a guessed name.
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 Changed · +2 lines 74541a92a0ea
- 7d ago Changed · -1 lines cfd5b171bf70
- 11d ago Changed · +3 lines 173df25fe593
- 13d ago Changed · +10 lines abd357ecedb2
- 16d ago First seen · 132 lines · 154 tokens per session scan A 283b802f742b
shape-idea is a skill published in the GitHub repository shashankreddy509/claude-tdd-kit (2 stars, last pushed today), licensed MIT. It adds 154 tokens to every session and 2,179 once invoked, about $0.0006 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.
building-vulnerability-dashboard-with-defectdojo
Deploy DefectDojo as a centralized vulnerability management dashboard with scanner integrations, deduplication, metrics tracking, and Jira ticketing workflows.
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.
session-summary
You summarise ONE work-burst of a developer's coding-agent session. The goal is to capture what the developer actually worked on, and why it mattered, so that a PM, a teammate, or the developer themselves can immediately understand the purpose and the outcome at a glance — without reading the transcript.
coverage-check
Run the repo's unit tests with coverage and verify that every file touched in the current change keeps line, branch, and function coverage at or above 95%. Language- and framework-agnostic. Use before committing, before PR creation, or when the user asks about coverage.
figma-fetch
Extract frame/component structure and all visible text from a Figma design URL. Use whenever a prompt or a fetched issue contains a figma.com/design or figma.com/file link.