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 agentmods add rules/rethunk-ai/clodbridge/validate-design-earlygit clone --depth 1 https://github.com/Rethunk-AI/clodbridgeWhat 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 | $0.00227 | $0.00227 |
| Opus 5 | $0.00113 | $0.00113 |
| Sonnet 5 | $0.00045 | $0.00045 |
| Haiku 4.5 | $0.00023 | $0.00023 |
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 2d 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.
What it actually says
Validate Design Early
Before implementing a major feature, confirm the design with the user.
What Counts as Major
- A new subsystem (file watching, MCP resources, etc.)
- A design choice with multiple valid approaches
- A requirement not explicitly stated
- Any architectural direction you're committing the user to
When to Ask
Before writing 100+ lines for that feature. After planning, before implementing.
How to Ask
Use AskUserQuestion with concrete options:
"Should clodbridge expose MCP Resources (cursor:// URIs)?"
Options:
A) Yes - users will want direct file access
B) No - tools are sufficient
C) Yes, but only for rules
What NOT to Ask
- Low-level implementation details (map vs object?)
- Code style (tabs vs spaces?)
- Questions you can answer from user's prior feedback
For design decision patterns and examples, see the validate-design-early skill.
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.
- 2d ago First seen · 42 lines · 227 tokens per session scan A 41c46ebc3e49
validate-design-early is a cursor rule published in the GitHub repository Rethunk-AI/clodbridge (0 stars, last pushed 1mo ago), licensed MIT. It adds 227 tokens to every session, about $0.0011 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 cursor rules, from other repositories
savee
Use the Savee MCP tools when the task involves design inspiration, visual references, moodboards, or the user's own saved work.
cursorrules
Cursor rule "cursorrules" from ifmelate/n8n-workflow-builder-mcp, covering start every chat message with symbol "🤖" and do not call initializeproject mcp tool.
qring-workflow
Use q-ring MCP tools for all secret operations — never access the OS keychain directly.
mcp-tools-readme
Keep README in sync when MCP tools change.
example
You are in a workspace with Bifrost MCP tools enabled. Use them for code navigation, understanding, and modification. Follow these guidelines.
angular-20
This rule provides comprehensive best practices and coding standards for Angular development, focusing on modern TypeScript, standalone components, signals, and performance optimizations.