Borrowing it
Nothing to install: this file belongs to dyeoman2/clerk-mcp-template. 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/dyeoman2/clerk-mcp-template/main/AGENTS.mdgit clone --depth 1 https://github.com/dyeoman2/clerk-mcp-templateWrote 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/instructions/dyeoman2/clerk-mcp-template/agents-md)<a href="https://agentmods.dev/instructions/dyeoman2/clerk-mcp-template/agents-md"><img src="https://agentmods.dev/badge/instructions/dyeoman2/clerk-mcp-template/agents-md/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/instructions/dyeoman2/clerk-mcp-template/agents-md"><img src="https://agentmods.dev/badge/instructions/dyeoman2/clerk-mcp-template/agents-md.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 | $0.00314 | $0.00314 |
| Opus 5.5 | $0.00126 | $0.00126 |
| Sonnet 5.5 | $0.00063 | $0.00063 |
| Haiku 4.5 | $0.00031 | $0.00031 |
Grade C, and why
clerk-mcp-template AGENTS.md scanned grade C with 1 finding 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 2mo 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.
Hidden instructionshighPrompt injection
Directives inside HTML comments, invisible characters or bidirectional overrides are read by the model and not by the person reviewing the file.
<!-- Instructions for testing and formatting code --> What it actually says
After making the desired changes to the code, run npm run validate to check
for errors. Fix the errors and rerun npm run validate until there are no
errors. After npm run validate returns no errors, run npm run format to
format the code.
Instructions for AI Agents
This is a template for building MCP servers with Clerk authentication on Cloudflare Workers.
Key Points for Code Assistance
- This is a template - Users will customize it for their own applications
- Replace placeholders - Look for "TODO", "your-app", "ClerkAppMCP", etc.
- Clerk integration - Authentication flow is already implemented
- Example tools - Replace with user's actual business logic
- Environment variables - Users need to add their own app-specific vars
- Security - OAuth flow and token management are handled
Common Customizations
- Rename
ClerkAppMCPclass to something meaningful - Update server name and description
- Replace example tools with real functionality
- Add application-specific environment variables
- Implement the
/auth/mcproute in user's application - Update API endpoints to point to user's services
Validation
When helping users, ensure:
- Clerk keys are properly configured
- KV namespace is created and bound
- Authentication flow is implemented in their app
- Tools are properly typed with Zod schemas
- Error handling is maintained
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.
- 2mo ago First seen · 40 lines · 314 tokens per session scan C 03311bde9568
clerk-mcp-template AGENTS.md is an instructions file published in the GitHub repository dyeoman2/clerk-mcp-template (2 stars, last pushed 1y ago), licensed MIT. It adds 314 tokens to every session, about $0.0013 per session on Opus 5.5. A static security scan graded it C with 1 finding (hidden instructions). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
clerk-mcp-template AGENTS.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| clerk-mcp-template AGENTS.mddyeoman2/clerk-mcp-template | Instructions file | 2 | 1y ago | MIT | C | 314 | Codex, OpenCode |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 9,719 | GitHub Copilot |
| next.js AGENTS.mdvercel/next.js | Instructions file | 143k | yesterday | MIT | A | 7,461 | Codex, OpenCode |
| langchain AGENTS.mdlangchain-ai/langchain | Instructions file | 149k | yesterday | MIT | A | 4,680 | Codex, OpenCode |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 5,516 | GitHub Copilot |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 3,093 | GitHub Copilot |
| deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness | Instructions file | 274k | 2d ago | MIT | A | 4,313 | Codex, OpenCode |