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.
git clone --depth 1 https://github.com/codeready-toolchain/tarsyWrote 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/commands/codeready-toolchain/tarsy/sketch-with-questions)<a href="https://agentmods.dev/commands/codeready-toolchain/tarsy/sketch-with-questions"><img src="https://agentmods.dev/badge/commands/codeready-toolchain/tarsy/sketch-with-questions/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/commands/codeready-toolchain/tarsy/sketch-with-questions"><img src="https://agentmods.dev/badge/commands/codeready-toolchain/tarsy/sketch-with-questions.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 | $0.00000 | $0.01036 |
| Opus 5 | $0.00000 | $0.00518 |
| Sonnet 5 | $0.00000 | $0.00207 |
| Haiku 4.5 | $0.00000 | $0.00104 |
Grade A, and why
sketch-with-questions 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 — 116 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/sketch-with-questions
You are in sketch mode. The feature or idea is not yet well-defined enough for a detailed design. Your job is to produce a high-level technical sketch and a questions document, then walk through the questions one at a time to form the sketch. Do not attempt detailed architecture, implementation plans, or interface definitions — those belong in a /design-with-questions session.
Before you start
Do a thorough analysis before generating anything. You need to understand the existing system well enough to place this feature in context.
- Explore the codebase: understand the overall structure, relevant components, and how related features currently work
- Read existing documentation in
docs/— especially any sketches, designs, or proposals that relate to this feature - If the feature involves external technologies, libraries, or patterns you're not confident about, research them first
Only start generating documents once you have enough context to do so accurately.
Phase 1: Generate two documents
1. docs/proposals/{name}-sketch.md — Sketch Document
A high-level technical description of the feature. Structure it however best fits the idea — not every feature is alike, and a rigid template can get in the way. Use judgment.
The document should always include:
- Status header:
Draft — sketch in progress, see [{name}-questions.md]({name}-questions.md) - A clear explanation of what this is and what problem it solves
- How it relates to the existing system
- Key concepts and rough behavior
- What is out of scope
- Open question markers cross-referencing the questions doc
Beyond that, choose sections that make sense for this specific feature. Use diagrams where they add clarity. Keep it high-level — no detailed architecture, implementation plans, or interface definitions. Those come later.
For uncertain areas, add an inline marker:
> **Open question:** {brief description} — see [questions document]({name}-questions.md), Q{N}.
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 · 116 lines · 0 tokens per session scan A 93a01986d11a
sketch-with-questions is a command published in the GitHub repository codeready-toolchain/tarsy (10 stars, last pushed today), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 1,036 tokens. 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 commands, from other repositories
refactor-clean
You are a code refactoring expert specializing in clean code principles, SOLID design patterns, and modern software engineering best practices. Analyze and refactor the provided code to improve its quality, maintainability, and performance.
deps-audit
Audit project dependencies for vulnerabilities, outdated packages, license conflicts, and supply chain risks — then provide actionable remediation strategies.
status
Display project status, active tracks, and next actions.
post
Post the current OCR review to a GitHub PR.
show
Display a past OCR review session.
test-feature
Test a React Native feature on the running simulator/emulator. Verifies UI, user flows, and internal state. Generates a persistent Maestro test file.