ssh-remote-operations

A controlled way to perform DevOps work on a remote virtual machine or bare server through the project's SSH configuration. SSH is a secure protocol for logging into and running commands on another computer.

In plain words
What is it for?
Use it to inspect a remote host, install software, stage release files, run approved commands, perform health checks, and document rollback notes.
Why use it?
It provides remote-operation evidence while keeping private keys, passwords, and SSH configuration contents hidden.

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/evolplus/talos/ssh-remote-operations
Any agent
npx skills add evolplus/talos --skill ssh-remote-operations
Clone the repo
git clone --depth 1 https://github.com/evolplus/talos

Made for: Claude Code, Codex.

Per session 68 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,002 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. 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 $0.00068 $0.01002
Opus 5 $0.00034 $0.00501
Sonnet 5 $0.00014 $0.00200
Haiku 4.5 $0.00007 $0.00100

Measured 2d ago against content hash 1783f35561a8, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

ssh-remote-operations 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 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.

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.

skills/ssh-remote-operations/SKILL.md · 45 lines

How it starts

The opening of the file, as written. The whole thing — 45 lines — stays where its author put it; the contents beside it link to each section on GitHub.

SSH Remote Operations

When to use

Use this skill when a DevOps task targets a remote VM or bare server and the project provides SSH connection configuration under project-root .ssh/. The SSH files are operator-owned credential material: DevOps may reference them in commands, but must not read, summarize, copy, or print their contents.

Inputs and outputs

  • Inputs: task ID, target environment, approved SSH host alias, project-root .ssh/config, architecture/deploy docs, package/software requirements, and any human approval required for non-dev environments.
  • Outputs: remote preflight evidence, command/package-change summary, health-check evidence, rollback notes, and docs/deploy-reports/<task-id>.md or docs/devops/<task-id>/ artifacts with secrets redacted.

Procedure

  1. Resolve the target host alias. Use only a named host alias from project-root .ssh/config. Do not read .ssh/config; ask the operator for the alias if the task does not name it. Use ssh -F .ssh/config <alias> <command> for remote execution.
  2. Gate the target environment. Local/dev/test servers may proceed when the task explicitly names the target. Staging requires task approval evidence. Production requires a human-approved change record, a dry-run or written execution plan, and rollback instructions before any mutation.
  3. Run a safe preflight. Verify connectivity with a non-secret command such as ssh -F .ssh/config <alias> 'printf "%s\n" ok; uname -s; uname -m; id -un'. Do not run env, printenv, set, cat ~/.ssh/*, or commands that dump service credentials.
  4. Detect the remote OS before installing packages. Read non-secret OS metadata (/etc/os-release, uname) and choose the native package manager. Use non-interactive flags and exact package names from the task or architecture docs. If sudo prompts for a password, stop with NEEDS_CONTEXT; never ask the model to handle passwords.
  5. Install only declared software. Package installation is allowed only when the task explicitly requires it. Record package names and versions in the report. Do not run broad upgrades (apt upgrade, yum update, brew upgrade) unless the task is specifically an OS maintenance task with approval.
  6. Stage artifacts without copying secrets. Use scp -F .ssh/config or rsync -e 'ssh -F .ssh/config' only for build artifacts, compose files, manifests, or generated release bundles. Never copy .env*, .ssh/, .k8s/ kubeconfigs, private keys, registry credentials, or raw secret manifests.
  7. Make commands reproducible. Prefer checked-in scripts or task-scoped scripts under docs/devops/<task-id>/ for multi-step remote work. Remote one-liners should use set -euo pipefail when run through bash -lc.
  8. Capture redacted evidence. Store command summaries, package changes, remote host alias, target environment, health-check URLs, and rollback commands. Do not store host private IPs, usernames, tokens, key paths beyond the alias/config path, or raw command output that contains secrets.

Read the full file on GitHub · 45 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. 2d ago First seen · 45 lines · 68 tokens per session scan A 1783f35561a8

Subscribe to this mod's changes

ssh-remote-operations is a skill published in the GitHub repository evolplus/talos (8 stars, last pushed 28d ago), licensed Apache-2.0. It adds 68 tokens to every session and 1,002 once invoked, about $0.0003 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.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

brainstorming

You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.

obra/superpowers · 37 tokens

auto-perf-optimize

Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.

microsoft/vscode · 62 tokens

chat-perf

Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.

microsoft/vscode · 51 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens