clodbridge: Skill for Claude Code

.cursor/skills/validate-design-early/SKILL.md

validate-design-early is a skill for Claude Code, Cursor from Rethunk-AI/clodbridge. It costs 25 tokens per session (953 once invoked), scanned A, original, MIT.

A review-first method for planning new features or major parts of a system. It asks for design approval before implementing more than 100 lines or making a significant architectural choice.

In plain words
What is it for?
Getting approval for new subsystems, competing implementation approaches, architecture changes, and new command-line options before coding them.
Why use it?
It reduces the risk of spending time on a large implementation based on an unapproved design. Important choices are surfaced while they are still easy to change.

Skill for Claude CodeCursor

Written for Claude Code and Cursor: UserPromptSubmit hook event, but also installed under .cursor/. Also seen: mentions CLAUDE.md; names the AskUserQuestion tool; mentions Claude Code.

This is Rethunk-AI/clodbridge's own configuration. It tells Claude Code and Cursor how to work on clodbridge itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything clodbridge configures →

Reuse

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.

Copy the file
curl -O https://raw.githubusercontent.com/Rethunk-AI/clodbridge/main/.cursor/skills/validate-design-early/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/Rethunk-AI/clodbridge

Made for: Claude Code, Cursor.

Wrote 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.

agentmods badge for validate-design-early

README.md
[![agentmods](https://agentmods.dev/badge/skills/rethunk-ai/clodbridge/validate-design-early.svg)](https://agentmods.dev/skills/rethunk-ai/clodbridge/validate-design-early)
Your own site
<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>
Per session 25 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 953 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce 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

Measured 7d ago against content hash c95c6f9e8401, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

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.

.cursor/skills/validate-design-early/SKILL.md · 131 lines

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

Read the full file on GitHub · 131 lines

Changes

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.

  1. 7d ago First seen · 131 lines · 25 tokens per session scan A c95c6f9e8401

Subscribe to this mod's changes

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.

Related

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.

gooseworks-ai/goose-skills · 45 tokens

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.

calesthio/OpenMontage · 58 tokens

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…

code-yeongyu/oh-my-openagent · 88 tokens

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.

Prismer-AI/PrismerCloud · 64 tokens

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…

JimLiu/baoyu-design · 231 tokens

requirements-authoring

To author, update, and validate functional/non-functional requirements as atomic units with user approval.

griddynamics/rosetta · 0 tokens