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 skills/muchiny/bridge-mcp/ssh-opsnpx skills add muchiny/bridge-mcp --skill ssh-opsgit clone --depth 1 https://github.com/muchiny/bridge-mcpWhat 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 | $0.00061 | $0.01441 |
| Opus 5 | $0.00030 | $0.00720 |
| Sonnet 5 | $0.00012 | $0.00288 |
| Haiku 4.5 | $0.00006 | $0.00144 |
Grade B, and why
ssh-ops scanned grade B 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 2d 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.
Unrestricted tool accessmediumExcessive agency
A wildcard tool grant or "run any command" leaves no least-privilege boundary at all.
# Execute arbitrary command 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.
Remote Infrastructure Operations
476 tools are available via the bridge-mcp CLI for managing remote servers over SSH.
Golden Rule
ALWAYS use the CLI (bridge-mcp tool ... via Bash) instead of MCP tools.
CLI saves 10-32x tokens compared to MCP by loading schemas on-demand.
Progressive Discovery Workflow
To find the right tool, follow these steps:
Step 1 — Browse groups (~2K tokens)
bridge-mcp list-tools --groups-only
Step 2 — Explore a group (~500 tokens)
bridge-mcp list-tools --group docker
Step 3 — Get tool schema (~200 tokens)
bridge-mcp describe-tool ssh_docker_ps
Step 4 — Invoke the tool
bridge-mcp tool ssh_docker_ps host=myserver --json
Search by keyword: bridge-mcp list-tools --search kubernetes
Syntax Reference
# key=value arguments (auto type-coerced)
bridge-mcp tool ssh_exec host=prod command="df -h"
# Complex/nested args via JSON
bridge-mcp tool ssh_k8s_get --json-args '{"host":"k8s","resource":"pods","namespace":"default"}'
# Multi-file write (inline content + local file upload in one call)
bridge-mcp tool ssh_files_write --json-args '{"host":"prod","files":[{"remote_path":"/tmp/a.conf","content":"key=val"},{"remote_path":"/opt/b.bin","local_path":"/local/b.bin"}]}'
# JSON output for reliable parsing
bridge-mcp tool ssh_docker_ps host=prod --json
# Aliases: t = tool, dt = describe-tool
bridge-mcp t ssh_exec host=prod command="whoami"
bridge-mcp dt ssh_docker_ps
Output Reduction (server-side, runs BEFORE truncation)
describe-tool prints each tool's Reduction Strategy — apply it to avoid
losing data to the output cap:
# JSON output tools: jq filter + TSV (60-80% token savings)
bridge-mcp --jq '.items[] | [.name, .status]' --output-format=tsv tool ssh_k8s_get host=k8s resource=pods
# Tabular tools: keep only needed columns + row limit
bridge-mcp --columns NAME,STATUS --limit 20 tool ssh_docker_ps host=prod
# Raw text (logs, ssh_exec): save full output to a local file
bridge-mcp tool ssh_exec host=prod command="journalctl -u nginx" save_output=/tmp/out.txt
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.
- 2d ago First seen · 161 lines · 61 tokens per session scan B ab23801cfb31
ssh-ops is a skill published in the GitHub repository muchiny/bridge-mcp (8 stars, last pushed 2d ago), licensed MIT. It adds 61 tokens to every session and 1,441 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it B with 1 finding (unrestricted tool access). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
omh-jit-learn
This is a Hermes-native jit-learn workflow skill.
omh-instinct-ledger
This is a Hermes-native instinct-ledger workflow skill.
xiaohongshu-title
《小红书运营手册 · AI工作台》标题生成与优化技能。用于用户明确要为小红书笔记、封面短句、图文/短视频标题、种草、教程、测评、服务内容起标题、改标题、做标题方向选择时触发。输入可以是正文草稿、选题方向、产品卖点、账号定位、图片/视频描述或已有标题。默认用快速模式输出标题；用户要求分析、首推、理由、方向、诊断或优化时用诊断/优化模式。不要在普通文章标题、论文标题、新闻标题、课程命名等非小红书/社媒场景中自动触发。.
mulch-record-from-evidence
Turn the evidence of a finished work session — git commits, changed files, recently-touched seeds issues — into well-formed ml record invocations. Use at session close, when an agent has made changes worth preserving as mulch expertise but hasn't yet recorded them.
paper2poster
Convert academic papers (PDF) into conference posters (HTML/PNG). You are the conductor: you decide what each section needs — an original paper figure or text — write the outline, hand-author the poster HTML, and iterate on the render using your own visual read and a blind-reader content quiz. Use when the user wants…
memory-protocol
Universal protocol for total-agent-memory MCP server. Activate at session start, before any non-trivial task, after every significant action, on errors, and at session end. Relevant whenever the user mentions: memory, recall, past context, decisions history, conventions, lessons learned, "продолжаем", "сохранись"…