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/verify-design)<a href="https://agentmods.dev/commands/codeready-toolchain/tarsy/verify-design"><img src="https://agentmods.dev/badge/commands/codeready-toolchain/tarsy/verify-design/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/verify-design"><img src="https://agentmods.dev/badge/commands/codeready-toolchain/tarsy/verify-design.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 | $0.00438 |
| Opus 5.5 | $0.00000 | $0.00175 |
| Sonnet 5.5 | $0.00000 | $0.00088 |
| Haiku 4.5 | $0.00000 | $0.00044 |
Grade A, and why
verify-design 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 1mo 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 — 59 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Verify Design Document
Carefully and systematically review the provided design document to verify it is consistent, aligned with the current codebase, and free of meaningful gaps. Fix everything you can, then ask about the rest.
Before you start
Build a thorough understanding of the relevant parts of the system:
- Read the design document fully — understand its goals, architecture, concepts, and implementation plan
- If a companion questions doc exists (e.g.
{name}-questions.md), read it too — check that resolved decisions are reflected accurately in the design - Explore the codebase: look at the packages, types, interfaces, and patterns that the design touches or depends on
- Read existing documentation in
docs/that relates to the same area
What to verify
1. Internal consistency
- Do all sections of the document agree with each other?
- Are terms, names, and concepts used consistently throughout?
- Do examples and diagrams match the described architecture?
- If there are phases or steps, do they form a coherent sequence?
2. Alignment with the codebase
- Do referenced types, interfaces, packages, and files actually exist?
- Does the design correctly describe current behavior where it references it?
- Are proposed changes compatible with existing patterns and conventions?
- Are there recent code changes that the design doesn't account for?
3. Gaps and omissions
- Are there edge cases or failure modes not addressed?
- Are migration or backward-compatibility concerns covered where needed?
- Does the implementation plan have enough detail to act on?
- Are there implicit assumptions that should be stated explicitly?
- Are there dependencies between components that aren't acknowledged?
4. Open questions
- Are all open questions clearly marked?
- Are there unmarked decisions that should be questions?
- Have any "resolved" questions been left inconsistent with the design text?
Act on findings
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.
- 1mo ago First seen · 59 lines · 0 tokens per session scan A ef81d979a2e6
verify-design 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 438 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
proof-capture
Capture PR-ready proof artifacts for a feature, with an attested fail-closed controller in strict mode.
review-ui
Run a UI code review on the current snippet — Before / After / Why table per review-format, scoped to review-checklist.
translate-review-to-single-human
Translate a multi-reviewer code review into a single human-voice GitHub PR comment.
address
Address code review feedback — corroborate, validate, and implement changes from a review's final.md.
map
Generate a Code Review Map to help navigate large, complex changesets.
post
Post the current OCR review to a GitHub PR.