What is tunnel-manager AGENTS.md?

Project instructions for Knuckles-Team/tunnel-manager, a Python system for managing SSH tunnels and related remote-machine operations. They describe its architecture, tools, and required commands.

They guide work on SSH tunnel management, remote file operations, system discovery, security auditing, asynchronous tools, and tests.

They give Claude Code the project context needed to make changes that fit the existing structure and workflow.

How Knuckles-Team/tunnel-manager configures Codex and OpenCode

Reuse

Borrowing it

Nothing to install: this file belongs to Knuckles-Team/tunnel-manager. 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/Knuckles-Team/tunnel-manager/main/AGENTS.md

Clone the repo

git clone --depth 1 https://github.com/Knuckles-Team/tunnel-manager

Made for: Codex, OpenCode.

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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/knuckles-team/tunnel-manager/agents-md/github.svg)](https://agentmods.dev/instructions/knuckles-team/tunnel-manager/agents-md)

Your own site

<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/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.

Your own site · 80×15

<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="Reviewed on agentmods" width="80" height="20"></a>

Per session 5,160 This file is loaded in full into every session.

When invoked 5,160 The same file — it is already loaded in full.

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.

Model	Per session	Once invoked
Fable 5.1	$0.05160	$0.05160
Opus 5.5	$0.02064	$0.02064
Sonnet 5.5	$0.01032	$0.01032
Haiku 4.5	$0.00516	$0.00516

Measured 6d ago against content hash 85fcaf22a93d, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

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 6d 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.

AGENTS.md · 439 lines

How it starts

The opening of the file, as written. The whole thing — 439 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md

Agent contract

Tool-neutral rules for any AI agent or human working in this repository. This block is maintained by the fleet standard; edit outside the markers.

Owner boundary: this repository owns one external system's calls, mappings and MCP tools (spec prefix CONN-TUNNEL-MANAGER-); it depends on the connector SDK only. Feature routing across repositories: ecosystem boundaries.
Setup: run uv sync --locked, then uvx pre-commit install --hook-type pre-commit --hook-type pre-push.
Gates: uvx pre-commit run --all-files must pass before you push. Do not bypass hooks to get green.
Commits: one logical change per commit with a Spec: <ID> trailer (or Spec: none (<reason>)), plus a Co-Authored-By: trailer naming the assisting agent. Stage explicit paths only; never git add -A or git add .. Use your own configured Git identity, never a tool or bot name.
Org rules: organization AGENTS.md.

Canonical guidance for any AI coding agent or human; tool-specific entry files (for example CLAUDE.md) only import this file. Edit this file.

Tech Stack & Architecture

Language/Version: Python 3.10+
Core Libraries: scion-sdk, 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 feature 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/: Complete test suite for tunnel management and MCP server feature.

Read the full file on GitHub · 439 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.

6d ago Changed · -9 tokens per session 85fcaf22a93d
12d ago Changed · -10 tokens per session 6eba9cf5c197
14d ago Changed · +12 lines · +284 tokens per session 6781a6df88a3
20d ago Changed · +10 tokens per session 45df71961938
26d ago Changed · +4 lines · +153 tokens per session b491749cfcb7
27d ago Changed · +22 tokens per session 430a275aa90c
2mo ago First seen · 423 lines · 4,710 tokens per session scan A cc9b9fe15eb4

Subscribe to this mod's changes

tunnel-manager AGENTS.md is an instructions file published in the GitHub repository Knuckles-Team/tunnel-manager (3 stars, last pushed 2d ago), licensed MIT. It adds 5,160 tokens to every session, about $0.0206 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 2026-08-31.

Cloud DevOps and cloud Python agentic-ai ai mcp-server paramiko ssh

tunnel-manager AGENTS.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
tunnel-manager AGENTS.mdKnuckles-Team/tunnel-manager	Instructions file	3	2d ago	MIT	A	5,160	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

tunnel-manager: Instructions file for Codex