bridge

bridge is a skill for Claude Code, Codex from muchiny/bridge-mcp. It costs 46 tokens per session (1,292 once invoked), scanned C, original, MIT.

A skill for using an SSH bridge, which connects the coding agent to remote computers, through a command-line interface.

In plain words
What is it for?
Use it to check a host, run tools on a remote server, add or validate hosts, and configure SSH authentication.
Why use it?
It helps you check connections, inspect available tool groups, and manage bridge settings without handling each remote command manually.

Skill for Claude CodeCodex

Install

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.

agentmods
npx agentmods add skills/muchiny/bridge-mcp/bridge
Any agent
npx skills add muchiny/bridge-mcp --skill bridge
Clone the repo
git clone --depth 1 https://github.com/muchiny/bridge-mcp

Made for: Claude Code, Codex.

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.

agentmods badge for bridge

README.md
[![agentmods](https://agentmods.dev/badge/skills/muchiny/bridge-mcp/bridge.svg)](https://agentmods.dev/skills/muchiny/bridge-mcp/bridge)
Your own site
<a href="https://agentmods.dev/skills/muchiny/bridge-mcp/bridge"><img src="https://agentmods.dev/badge/skills/muchiny/bridge-mcp/bridge.svg" alt="Measured on agentmods" height="20"></a>
Per session 46 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,292 The whole file, excluding the scripts and references it only reads on demand.
Security scan C 1 finding. Scan, not verified.
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.

ModelPer sessionOnce invoked
Fable 5 $0.00046 $0.01292
Opus 5 $0.00023 $0.00646
Sonnet 5 $0.00009 $0.00258
Haiku 4.5 $0.00005 $0.00129

Measured 4d ago against content hash 426d3f0bdd90, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade C, and why

bridge 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 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.

Reaches for credential fileshighPrivilege escalation

SSH keys, cloud credentials, git-credentials, .npmrc, /etc/shadow: reading these is how a config file becomes a credential leak.

path: ~/.ssh/id_ed25519
config/claude-code/skills/bridge/SKILL.md · 161 lines

How it starts

The opening of the file, as written. The whole thing — 161 lines — stays where its author put it; the contents beside it link to each section on GitHub.

SSH Bridge CLI — Remote Tool Execution and Configuration

Execute MCP tools on remote hosts or manage bridge configuration via the token-efficient CLI.

Current state

Host status: !bridge-mcp status 2>/dev/null || echo "CLI binary not found — run 'make build' or 'cargo install --path .'"

Instructions

No arguments or status

Show host status (above) and available tool groups: !bridge-mcp list-tools --groups-only

Then ask the user what they want to do.

Config mode

Help the user configure the bridge. Show current config state:

  1. Config file location: ~/.config/bridge-mcp/config.yaml
  2. Validate current config: !bridge-mcp validate 2>&1
  3. Show diff vs defaults: !bridge-mcp config-diff 2>&1

Then guide the user through configuration. The config file has these sections:

Adding a host:

hosts:
  my-server:
    hostname: 192.168.1.100
    port: 22
    user: admin
    description: "My server"
    auth:
      type: key              # key | password | agent
      path: ~/.ssh/id_ed25519
    # os_type: windows       # for Windows hosts
    # shell: powershell      # for Windows: cmd (default) or powershell
    # proxy_jump: bastion    # connect through a jump host

Security modes:

security:
  mode: standard     # strict = whitelist only | standard = whitelist for exec, blacklist for tools | permissive = blacklist only
  whitelist:
    - "^docker\\s+(ps|logs|inspect).*"   # regex patterns
  blacklist:
    - "rm\\s+(-[a-zA-Z]*r|--recursive)"  # always denied
  sanitize:
    enabled: true    # mask secrets in output (~50 builtin patterns)

Filtering tool groups (reduce MCP context):

tool_groups:
  groups:
    docker: false       # disable docker tools
    kubernetes: false   # disable k8s tools
    # Set any of the 74 groups to false to disable

SSH config auto-discovery:

ssh_config:
  enabled: true   # auto-import hosts from ~/.ssh/config

Reference: config/config.example.yaml has the full documented example.

Read the full file on GitHub · 161 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.

  1. 4d ago First seen · 161 lines · 46 tokens per session scan C 426d3f0bdd90

Subscribe to this mod's changes

bridge is a skill published in the GitHub repository muchiny/bridge-mcp (8 stars, last pushed 3d ago), licensed MIT. It adds 46 tokens to every session and 1,292 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it C with 1 finding (reaches for credential files). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other skills, from other repositories

eu-ai-act-compliance

EU AI Act compliance logging and requirements. Use this skill when ensuring transparency, human oversight, and record-keeping per Regulation (EU) 2024/1689 — even if they just say "add compliance logging" or "make sure this is EU AI Act compliant". Not for security-code-auditor, privacy-first.

d-o-hub/github-template-ai-agents · 72 tokens

release-and-publish

Ship a release end-to-end across every registry the project targets (npm, MCP Registry, GitHub Releases for .mcpb bundles, GHCR). Runs the final verification gate, pushes commits and tags, then publishes to each applicable destination. Assumes git wrapup (version bumps, changelog, commit, annotated tag) is already…

cyanheads/epa-mcp-server · 112 tokens

design-mcp-server

Design the tool surface, resources, and service layer for a new MCP server. Use when starting a new server, planning a major feature expansion, or when the user describes a domain/API they want to expose via MCP. Produces a design doc at docs/design.md that drives implementation.

cyanheads/epa-mcp-server · 62 tokens

add-tool

Scaffold a new MCP tool definition. Use when the user asks to add a tool, create a new tool, or implement a new capability for the server.

cyanheads/epa-mcp-server · 35 tokens

api-context

Canonical reference for the unified Context object passed to every tool and resource handler in @cyanheads/mcp-ts-core. Covers the full interface, its RequestContext base, all sub-APIs (ctx.log, ctx.state, ctx.requestInput, ctx.inputs, ctx.enrich, ctx.content), and when to use each.

cyanheads/epa-mcp-server · 79 tokens

api-linter

MCP definition linter rules reference. Use when bun run lint:mcp or bun run devcheck reports a lint error or warning (format-parity, schema-is-object, name-format, server-json-, etc.) and you need to understand the rule, its severity, and how to fix it. Every rule ID the linter emits has an entry in this doc.

cyanheads/epa-mcp-server · 86 tokens