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/saajunaid/caddis-pluginWrote 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/saajunaid/caddis-plugin/mcp-development)<a href="https://agentmods.dev/commands/saajunaid/caddis-plugin/mcp-development"><img src="https://agentmods.dev/badge/commands/saajunaid/caddis-plugin/mcp-development/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/saajunaid/caddis-plugin/mcp-development"><img src="https://agentmods.dev/badge/commands/saajunaid/caddis-plugin/mcp-development.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 | $0.00013 | $0.00650 |
| Opus 5.5 | $0.00005 | $0.00260 |
| Sonnet 5.5 | $0.00003 | $0.00130 |
| Haiku 4.5 | $0.00001 | $0.00065 |
Grade A, and why
mcp-development 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 — 127 lines — stays where its author put it; the contents beside it link to each section on GitHub.
MCP Server Development Prompt
Use this prompt template when asking AI to create or modify MCP (Model Context Protocol) servers.
Context Template
I need to create/modify an MCP server for [PURPOSE].
## Environment
- Language: Python 3.11+
- Framework: FastMCP / MCP Python SDK
- Target: VS Code Copilot / Claude Code / Cursor
## Required Capabilities
[List the tools/resources this MCP should provide]
## Integration Points
- [External API / Database / Service to connect to]
- Authentication method: [API key / OAuth / Connection string]
## Constraints
- [Air-gapped: Must work offline]
- [Security: No credential exposure]
- [Performance: Response time requirements]
Example: Database MCP
I need to create an MCP server for SQL Server database access.
## Environment
- Language: Python 3.11+
- Framework: FastMCP
- Target: VS Code Copilot Chat
## Required Capabilities
- query_database: Execute read-only SQL queries
- get_schema: Retrieve table schemas
- list_tables: Show available tables
- get_sample_data: Get sample rows from a table
## Integration Points
- SQL Server via pyodbc
- Connection string from environment variables
## Constraints
- Read-only queries only (no INSERT/UPDATE/DELETE)
- Query timeout: 30 seconds
- Result limit: 1000 rows
- No credential logging
Expected Output Structure
from mcp import FastMCP
from pydantic import BaseModel
from pydantic_settings import BaseSettings
class Settings(BaseSettings):
"""Environment configuration"""
db_server: str
db_name: str
db_user: str
db_password: str
class Config:
env_prefix = "DB_"
# Initialize MCP server
mcp = FastMCP("<APP_NAME>-database")
settings = Settings()
@mcp.tool()
def query_database(sql: str) -> dict:
"""Execute a read-only SQL query and return results"""
# Implementation
pass
@mcp.tool()
def get_schema(table_name: str) -> dict:
"""Get the schema for a specific table"""
# Implementation
pass
@mcp.resource("schema://tables")
def list_tables() -> str:
"""List all available tables in the database"""
# Implementation
pass
if __name__ == "__main__":
mcp.run()
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 · 127 lines · 13 tokens per session scan A 7dc4a1c32b76
mcp-development is a command published in the GitHub repository saajunaid/caddis-plugin (0 stars, last pushed today), licensed MIT. It adds 13 tokens to every session and 650 once invoked, about $0.0001 per session on Opus 5.5. 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 2026-09-09.
Other commands, from other repositories
end-session
Wrap up the work session with read-only evidence gathering, owner-classified documentation handoffs, gated issue sync, Kano refinement, and git hygiene checks.
test-feature
Test a React Native feature on the running simulator/emulator. Verifies UI, user flows, and internal state. Generates a persistent Maestro test file.
observe
Show the observability web UI URL (it autostarts with the session); stop or restart it.
accept
Command dispatcher for accept.
change
Command dispatcher for change.
checklist
Generate a custom checklist for the current feature based on user requirements.