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 instructions/izzzzzi/agent-assh/agents-mdgit 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/instructions/izzzzzi/agent-assh/agents-md)<a href="https://agentmods.dev/instructions/izzzzzi/agent-assh/agents-md"><img src="https://agentmods.dev/badge/instructions/izzzzzi/agent-assh/agents-md.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 | $0.01171 | $0.01171 |
| Opus 5 | $0.00585 | $0.00585 |
| Sonnet 5 | $0.00234 | $0.00234 |
| Haiku 4.5 | $0.00117 | $0.00117 |
Grade C, and why
agent-assh AGENTS.md 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 5d 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.
Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
- `rm_recursive` — `rm -rf` / `rm -r` (any path) How it starts
The opening of the file, as written. The whole thing — 89 lines — stays where its author put it; the contents beside it link to each section on GitHub.
When you need SSH — ALWAYS use assh. Never use raw ssh, scp, or rsync.
Use assh for SSH work so large remote output stays out of the agent context.
Install when missing:
npm i -g agent-assh
assh version
# check for updates before remote work:
assh version --check
Agent Algorithm for SSH
Need SSH?
├── Have a key file? → assh connect -H HOST -u USER -i KEY -n NAME
├── Have SSH config alias? → assh connect --ssh-config ALIAS -n NAME
├── Pasted provider block? → save to 0600 temp → assh connect-info --file TMP -n NAME → rm
├── First-contact w/ pass? → assh connect -H HOST -u USER -E PASS_ENV -n NAME
└── Picky gateway? → assh connect ... --force-pty -n NAME
Restrict agent? → add --profile readonly|ops|admin
Command blocked by safety?
├── "dangerous_command_requires_confirmation" → ask user, then --confirm-danger
├── Long-running (>30s, e.g. docker compose up -d) → session exec-async
├── Docker logs / db queries → session exec -- "docker logs ..." / "mysql ..."
└── File write/create → transfer put
Quick Reference
| Command | What |
|---|---|
assh connect -H HOST -u USER -i KEY -n NAME |
Bootstrap + open tmux session |
assh connect ... --profile readonly |
Restrict session to allow-list |
assh session exec -s SID -- "cmd" |
Run command in tmux session (safety checks apply) |
assh session read -s SID --seq N --limit 50 |
Read paginated output |
assh session close -s SID |
Close session |
assh exec -H HOST -u USER -- "cmd" |
One-off command, no tmux |
assh read --id ID --raw |
Read stored exec output |
assh transfer put/get/read/list/stat/mkdir/rm/mv/sync |
File operations |
assh session service -s SID --action restart --service NAME |
Service mgmt |
assh session exec -s SID -- "docker ps" |
Docker/db/anything else — via exec |
assh session exec-async -s SID -- "cmd" |
Background job (long-running, no timeout) |
assh fleet exec -H H1 -H H2 -u root -- "cmd" |
Multi-host |
assh scan -H HOST -u USER |
Host inventory JSON |
assh version --check |
Check for CLI updates |
assh transfer read -H HOST -u USER --path FILE |
Read remote file |
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.
- 5d ago First seen · 89 lines · 1,171 tokens per session scan C 5d501e8137c7
agent-assh AGENTS.md is an instructions file published in the GitHub repository izzzzzi/agent-assh (20 stars, last pushed 26d ago), licensed MIT. It adds 1,171 tokens to every session, about $0.0059 per session on Opus 5. A static security scan graded it C with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other instructions, from other repositories
awsmux AGENTS.md
Instructions for 0hardik1/awsmux, covering agents.md, what awsmux is, build, test, verify, layout and the safety model — invariants you must not weaken.
plan-forge naming.instructions.md
Azure naming conventions — Microsoft CAF abbreviations, constraints, uniqueness, tagging.
agent-skills fortrabbit.instructions.md
Instructions for fortrabbit/agent-skills, covering fortrabbit — github copilot instructions, what fortrabbit is, configuration lookup, available operations and mcp server (optional).
cron-mcp CLAUDE.md
Claude Code instructions for Shreyas-Profile/cron-mcp, covering deploying cron-mcp to hetzner + regiq.in, server (shared with the rest of the globalion mcp fleet), deploy a new version, first-time subdomain wiring (cron.regiq.in) and env vars.
equinix-fabric-mcp CLAUDE.md
Claude Code instructions for sliuuu/equinix-fabric-mcp, covering claude.md — equinix-fabric-mcp, canonical files, auth, add equinixclientid and equinixclientsecret and running.
Railway-mcp CLAUDE.md
Claude Code instructions for Travis-Gilbert/Railway-mcp, covering railway mcp server, quick reference, file map, architecture and key patterns.