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 skills add muchiny/bridge-mcp --skill ssh-deploygit clone --depth 1 https://github.com/muchiny/bridge-mcpWrote 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/skills/muchiny/bridge-mcp/ssh-deploy)<a href="https://agentmods.dev/skills/muchiny/bridge-mcp/ssh-deploy"><img src="https://agentmods.dev/badge/skills/muchiny/bridge-mcp/ssh-deploy/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/skills/muchiny/bridge-mcp/ssh-deploy"><img src="https://agentmods.dev/badge/skills/muchiny/bridge-mcp/ssh-deploy.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00061 | $0.00754 |
| Opus 5.5 | $0.00024 | $0.00302 |
| Sonnet 5.5 | $0.00012 | $0.00151 |
| Haiku 4.5 | $0.00006 | $0.00075 |
Grade A, and why
ssh-deploy 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 — 117 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Deployment Operations
Deploy changes to remote infrastructure via bridge-mcp CLI.
This skill is manual-only — invoke with /ssh-deploy.
Parse $ARGUMENTS: first word = host, second word = action (restart, canary, rolling, k8s, helm).
Pre-Deploy Checklist
Before ANY deployment, verify:
-
Health check — confirm the target is healthy BEFORE changing anything:
bridge-mcp tool ssh_diagnose host=HOST --json -
Confirm with user — always ask before proceeding with destructive operations.
-
Know the rollback — have a rollback command ready before executing.
Deployment Patterns
Service Restart
# Check current status
bridge-mcp tool ssh_service_status host=HOST service=SERVICE --json
# Restart
bridge-mcp tool ssh_service_restart host=HOST service=SERVICE
# Verify recovery
bridge-mcp tool ssh_service_status host=HOST service=SERVICE --json
Canary Deploy
Deploy to a single canary host first, verify, then decide:
# Execute on canary
bridge-mcp tool ssh_canary_exec host=HOST command="DEPLOY_COMMAND"
# Health check canary
bridge-mcp tool ssh_diagnose host=HOST --json
# ASK the user before continuing to remaining hosts
Rolling Deploy
Execute on one host at a time with health checks between:
bridge-mcp tool ssh_rolling_exec host=HOST command="DEPLOY_COMMAND"
Kubernetes Rollout
# Check current state
bridge-mcp tool ssh_k8s_get host=HOST resource=deployments namespace=NAMESPACE --json
# Apply update
bridge-mcp tool ssh_k8s_apply host=HOST manifest="PATH_TO_YAML" namespace=NAMESPACE
# Watch rollout
bridge-mcp tool ssh_k8s_rollout host=HOST action=status deployment=DEPLOYMENT namespace=NAMESPACE
# Rollback if needed
bridge-mcp tool ssh_k8s_rollout host=HOST action=undo deployment=DEPLOYMENT namespace=NAMESPACE
Helm Upgrade
# Check current release
bridge-mcp tool ssh_helm_status host=HOST release=RELEASE --json
# Upgrade
bridge-mcp tool ssh_helm_upgrade host=HOST release=RELEASE chart=CHART
# Verify
bridge-mcp tool ssh_helm_status host=HOST release=RELEASE --json
# Rollback if needed
bridge-mcp tool ssh_helm_rollback host=HOST release=RELEASE
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 · 117 lines · 61 tokens per session scan A 810d1db17b04
ssh-deploy is a skill published in the GitHub repository muchiny/bridge-mcp (10 stars, last pushed today), licensed MIT. It adds 61 tokens to every session and 754 once invoked, about $0.0002 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.
Other skills, from other repositories
tianji-worker
Use when creating, testing, deploying, invoking, debugging, scheduling, pausing, or rolling back Tianji Workers, or managing their environment variables and shared modules.
ecspresso
ECS deployment tool - deploy, manage, and troubleshoot ECS services.
gateway
Start and manage the Kurtosis gateway for Kubernetes. The gateway forwards local ports to the Kurtosis engine and services running in a k8s cluster. Required when using Kurtosis with Kubernetes. Use when kurtosis engine status shows nothing on k8s or services aren't reachable.
backup-recovery
Design and verify backups and restoration for owned databases, files and application state. Use when preparing recovery, migrating data or testing backups; protect the source and prove restore into an isolated destination before calling recovery ready.
cloudflare-workers
Build and maintain Cloudflare Workers with typed bindings, explicit compatibility and isolated validation. Use when implementing Workers handlers, integrating KV/R2/D1/Durable Objects/Queues or configuring Wrangler; deployment remains governed by the user task and target environment.
kubernetes-operations
Operate and deploy owned Kubernetes workloads with explicit cluster, namespace and rollout identity. Use when configuring Deployments, Services, probes, resources or diagnosing a known workload; do not expand an application task into uncontrolled cluster administration.