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 instructions/knuckles-team/tunnel-manager/agents-mdgit clone --depth 1 https://github.com/Knuckles-Team/tunnel-managerWrote 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/knuckles-team/tunnel-manager/agents-md)<a href="https://agentmods.dev/instructions/knuckles-team/tunnel-manager/agents-md"><img src="https://agentmods.dev/badge/instructions/knuckles-team/tunnel-manager/agents-md.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 | $0.04710 | $0.04710 |
| Opus 5 | $0.02355 | $0.02355 |
| Sonnet 5 | $0.00942 | $0.00942 |
| Haiku 4.5 | $0.00471 | $0.00471 |
Grade A, and why
tunnel-manager AGENTS.md 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 4d 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 — 423 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Claude Code loads this file via
CLAUDE.md(@AGENTS.mdimport) — the two stay in sync. Edit this file, notCLAUDE.md.
Tech Stack & Architecture
- Language/Version: Python 3.10+
- Core Libraries:
agent-utilities,fastmcp,paramiko,pydantic-ai - Key principles: Functional patterns, Pydantic for data validation, asynchronous tool execution.
- Architecture:
mcp_server.py: Main MCP server entry point and tool registration for SSH tunnel operations.agent_server.py: Pydantic AI agent definition and logic for tunnel management.tunnel_manager.py: Core SSH tunnel functionality including HostManager and Tunnel classes.operation_manager.py: Enhanced operation tracking with streaming progress and cancellation.system_intelligence.py: Remote system discovery and intelligence gathering.advanced_file_manager.py: Advanced file operations including recursive ops, search, monitoring, and backup.security_auditor.py: Security and compliance auditing capabilities.tests/: Comprehensive test suite for tunnel management and MCP server functionality.
Architecture Diagram
graph TD
User([User/A2A]) --> Server[A2A Server / FastAPI]
Server --> Agent[Pydantic AI Agent]
Agent --> MCP[MCP Server / FastMCP]
MCP --> Tunnel[Tunnel Manager]
Tunnel --> SSH[SSH Connections]
SSH --> RemoteHosts[Remote Hosts]
MCP --> HostManager[Host Manager]
HostManager --> Inventory[Inventory Files]
MCP --> OperationManager[Operation Manager]
MCP --> SystemIntelligence[System Intelligence]
MCP --> AdvancedFileManager[Advanced File Manager]
MCP --> SecurityAuditor[Security Auditor]
OperationManager --> Tunnel
SystemIntelligence --> Tunnel
AdvancedFileManager --> Tunnel
SecurityAuditor --> Tunnel
Workflow Diagram
sequenceDiagram
participant U as User
participant S as Server
participant A as Agent
participant T as MCP Tool
participant TM as Tunnel Manager
participant SSH as SSH Connection
participant RH as Remote Host
U->>S: Request
S->>A: Process Query
A->>T: Invoke Tool
T->>TM: Execute Operation
TM->>SSH: Connect
SSH->>RH: Execute Command/Transfer
RH-->>SSH: Result
SSH-->>TM: Output
TM-->>T: Result
T-->>A: Tool Result
A-->>S: Final Response
S-->>U: Output
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.
- 4d ago First seen · 423 lines · 4,710 tokens per session scan A cc9b9fe15eb4
tunnel-manager AGENTS.md is an instructions file published in the GitHub repository Knuckles-Team/tunnel-manager (2 stars, last pushed 6d ago), licensed MIT. It adds 4,710 tokens to every session, about $0.0235 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 instructions, from other repositories
aks-mcp copilot-instructions.md
Instructions for Azure/aks-mcp, covering copilot instructions, project overview, architecture, high-level structure and key components.
hop CLAUDE.md
Instructions for danmartuszewski/hop: Use conventional commit format with imperative mood.
obsidian-multivault-mcp AGENTS.md
Instructions for bepitulaz/obsidian-multivault-mcp, covering agents.md — deploying this mcp server on the vps, vps facts (example — change to match yours), gather before you start, do (high level — exact commands in deploy.md) and definition of done (verify — do not assume).
remote-mcp-functions-python copilot-instructions.md
Instructions for Azure-Samples/remote-mcp-functions-python: You are an ai assistant tasked assisting the developer to build and deploy MCP Servers successfully using Azure Functions. Our ultimate goal is for the user to be able to complete this quickstart guide, where the app is deployed and healthy in azure, and the…
obsidian-multivault-mcp CLAUDE.md
Instructions for bepitulaz/obsidian-multivault-mcp: See AGENTS.md for the deployment brief, and DEPLOY.md for the full step-by-step VPS runbook.
runwhen-platform-mcp AGENTS.md
AGENTS.md instructions for runwhen-contrib/runwhen-platform-mcp, covering agents.md — runwhen platform mcp server, authentication, important: workspacename is required, tool routing — workspacechat vs direct tools and always prefer workspacechat for.