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 izzzzzi/agent-assh --skill asshgit clone --depth 1 https://github.com/izzzzzi/agent-asshWrote 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/izzzzzi/agent-assh/assh)<a href="https://agentmods.dev/skills/izzzzzi/agent-assh/assh"><img src="https://agentmods.dev/badge/skills/izzzzzi/agent-assh/assh.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00040 | $0.01964 |
| Opus 5 | $0.00020 | $0.00982 |
| Sonnet 5 | $0.00008 | $0.00393 |
| Haiku 4.5 | $0.00004 | $0.00196 |
Grade C, and why
assh 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 8d 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.
│ └── assh connect -H HOST -u USER -i ~/.ssh/id_ed25519 -n NAME How it starts
The opening of the file, as written. The whole thing — 163 lines — stays where its author put it; the contents beside it link to each section on GitHub.
assh — SSH Workflow for LLM Agents
SSH tool for LLM agents. One command: key, tmux, session. Large output stays outside context — read only what you need.
Must-Read: How to Use This Skill
When you need to SSH to a server, inspect logs, transfer files, or run
remote commands — ALWAYS use assh. Never use ssh, scp, rsync,
or MCP SSH tools directly.
ssh user@host→ useassh connect -H HOST -u USERscp file user@host:→ useassh transfer putrsync→ useassh transfer synccat remote_fileover ssh → useassh transfer read- MCP SSH servers → assh is CLI-native, works with ANY agent
assh gives you:
- ✅ Automatic key deployment and tmux setup
- ✅ Token economy — paginated output, JSON metadata first
- ✅ Zero remote install — uses system OpenSSH, no daemon
- ✅ Safety classifier — blocks destructive commands
- ✅ Secrets redaction — no accidental credential leaks
Why not raw ssh: raw ssh streams all output into your context at once,
has no pagination, no safety checks, and requires manual key/tmux setup.
Install / Update
npm install -g agent-assh
assh version
If assh is not found, install first and retry.
Check for newer version before remote work:
assh version --check
# Update available: v1.2.8 → v1.3.0
# Run: npm i -g agent-assh@latest
Agent Algorithm — Which connect to Use
ALWAYS use assh for any SSH work. Never use raw ssh, scp, or rsync.
Need SSH?
├── Have a key file?
│ └── assh connect -H HOST -u USER -i ~/.ssh/id_ed25519 -n NAME
├── Have ~/.ssh/config alias?
│ └── assh connect --ssh-config ALIAS -n NAME
├── Pasted provider server-info block?
│ ├── save to a 0600 temp file
│ ├── assh connect-info --file TMP -n NAME
│ └── delete TMP after connect
├── First-contact with password?
│ ├── assh connect -H HOST -u USER -E PASSWORD_ENV -n NAME
│ └── unset PASSWORD_ENV after connect
└── Picky SSH gateway (RunPod, etc.)?
└── assh connect -H HOST -u USER -i KEY --force-pty -n NAME
└── Restrict agent commands?
└── add --profile readonly|ops|admin
On success → use returned sid for all remote work
Session dead (session_unreachable / session_stale / session_not_found / output_not_found)?
├── STOP retrying that SID — the hint says so for a reason
└── Reconnect with the same auth → new sid
Command blocked by safety?
└── "dangerous_command_requires_confirmation" → ask user, then --confirm-danger
Command will run >30s (git pull, docker compose up, apt install)?
└── session exec-async instead of session exec — sync exec times out
Unsure about a flag? → run `assh <cmd> --help` — do NOT invent flags (invalid_args)
What ships with it
6 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 8d ago First seen · 163 lines · 40 tokens per session scan C 50095c431772
assh is a skill published in the GitHub repository izzzzzi/agent-assh (20 stars, last pushed 29d ago), licensed MIT. It adds 40 tokens to every session and 1,964 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 2026-08-30.
Other skills, from other repositories
atmos-migration
This skill helps you migrate a repository to Atmos. It covers native Terraform, Terraform Workspaces, Terramate, Terragrunt, Makefiles, Justfiles, and Taskfiles. It gives minimum-disruption paths, file-layout options, workspace mapping, task-to-command mapping, generatehcl/script decomposition, and the remote-state…
atmos-auth
Authentication and identity management: providers (SSO/SAML/OIDC/GCP/Atmos Pro), identities, keyring, identity chaining, login/exec/shell/console, and github/sts for private GitHub access.
atmos-components
Component architecture: Terraform root modules, remote source provisioning, abstract components, component inheritance, versioning, mixins, catalog patterns.
atmos-helmfile
Helmfile orchestration: sync/apply/destroy/diff, Kubernetes deployments, varfile generation, EKS integration, source management.
atmos-design-patterns
Design patterns: stack organization, component catalogs, inheritance, configuration composition, version management, layered configuration.
atmos-kubernetes
Native Kubernetes components (experimental): render/plan/diff/apply/deploy/delete/validate via Kubernetes Go SDK server-side apply, components.kubernetes, kubectl/kustomize providers, paths/manifests, provision targets (cluster vs. GitOps repo), and auth.