Borrowing it
Nothing to install: this file belongs to Rethunk-AI/clodbridge. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/Rethunk-AI/clodbridge/main/.cursor/skills/validate-design-early/SKILL.mdgit clone --depth 1 https://github.com/Rethunk-AI/clodbridgeWrote 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/rethunk-ai/clodbridge/validate-design-early)<a href="https://agentmods.dev/skills/rethunk-ai/clodbridge/validate-design-early"><img src="https://agentmods.dev/badge/skills/rethunk-ai/clodbridge/validate-design-early.svg" alt="Measured on agentmods" 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 | $0.00025 | $0.00953 |
| Opus 5 | $0.00013 | $0.00477 |
| Sonnet 5 | $0.00005 | $0.00191 |
| Haiku 4.5 | $0.00003 | $0.00095 |
Grade A, and why
validate-design-early 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 — 131 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Validate Design Early
The Principle
Ask about major design decisions BEFORE you implement them, not after.
What Counts as "Major"
| Decision | Ask? | Example |
|---|---|---|
| New subsystem | YES | "Should we add file watching?" |
| Multiple valid approaches | YES | "MCP Resources: raw files, JSON index, or both?" |
| Architectural direction | YES | "Should rules use glob matching or simple string matching?" |
| Unstated requirement | YES | "I'm adding --dump-always-rules for hook integration" |
| New CLI flag | YES | "Should the server support a --config flag?" |
| Low-level implementation | NO | "Should I use Map or object for caching?" |
| Code style | NO | "Tabs or spaces?" |
| Obvious from context | NO | "Should I test this?" (Yes, always) |
When to Ask
After planning, before writing code.
Timeline
❌ DON'T:
Plan the feature → Write 200 lines → Commit → Ask approval
✅ DO:
Plan the feature → Ask for approval → Write code → Commit
The "100-line rule"
If you're about to write 100+ lines for a feature, ask first.
If you're writing 30 lines of straightforward implementation, you can skip asking (it's unlikely to be wrong).
How to Ask
Use AskUserQuestion with concrete options:
Example 1: Binary Decision
Question: "Should clodbridge expose MCP Resources (cursor:// URIs)?"
Options:
A) Yes - users will want direct file access via URIs
B) No - tools are sufficient; resources add complexity
C) Yes, but only for rules (not skills/agents)
Example 2: Choice Among Options
Question: "For MCP Resources, should we expose:"
Options:
A) Raw file content only (cursor://rules/{name} returns .mdc text)
B) JSON indices only (cursor://rules returns list of rules)
C) Both (raw content + JSON indices)
D) Neither (just use tools, not resources)
Example 3: Clarifying Scope
Question: "I'm planning to add a --dump-always-rules flag for Claude Code
hook integration. This outputs rule content as JSON for UserPromptSubmit hooks."
Options:
A) Yes, this is useful
B) No, skip it (CLAUDE.md instructions are enough)
C) Yes, but make it a separate tool instead of a CLI flag
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 First seen · 131 lines · 25 tokens per session scan A c95c6f9e8401
validate-design-early is a skill published in the GitHub repository Rethunk-AI/clodbridge (0 stars, last pushed 2mo ago), licensed MIT. It adds 25 tokens to every session and 953 once invoked, about $0.0001 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
create-workflow-diagram
Create FigJam/Miro-style workflow diagrams as high-quality PNG images from plain-text workflow descriptions. Renders beautiful HTML diagrams with connected nodes, arrows, and labels, then screenshots them for sharing.
vercel-composition-patterns
React composition patterns that scale. Use when refactoring components with boolean prop proliferation, building flexible component libraries, or designing reusable APIs. Triggers on tasks involving compound components, render props, context providers, or component architecture. Includes React 19 API changes.
layout-skill
Layer A layout-mechanics reference. Stacks on any style skill when the screen is an app shell, dashboard, settings, list-detail, mail/inbox, or any layout with fixed regions plus a scrolling body — or when a layout breaks under long, empty, or unbroken content. Owns spatial structure and scroll ownership; owns zero…
web-artifacts-builder
Suite of tools for creating elaborate, multi-component claude.ai HTML artifacts using modern frontend web technologies (React, Tailwind CSS, shadcn/ui). Use for complex artifacts requiring state management, routing, or shadcn/ui components - not for simple single-file HTML/JSX artifacts.
baoyu-design
Create polished design artifacts as self-contained HTML: UI mockups, interactive prototypes, wireframes, landing pages, dashboards, app screens, mobile apps, slide decks (a.k.a. PPT / PowerPoint presentations), documents and résumés, animations, 3D objects, research reports, HTML email, diagrams, fliers, and visual…
requirements-authoring
To author, update, and validate functional/non-functional requirements as atomic units with user approval.