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 daidaiJ/2native-ssh-mcp --skill 2native-ssh-mcp-agentgit clone --depth 1 https://github.com/daidaiJ/2native-ssh-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/daidaij/2native-ssh-mcp/2native-ssh-mcp-agent)<a href="https://agentmods.dev/skills/daidaij/2native-ssh-mcp/2native-ssh-mcp-agent"><img src="https://agentmods.dev/badge/skills/daidaij/2native-ssh-mcp/2native-ssh-mcp-agent/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/daidaij/2native-ssh-mcp/2native-ssh-mcp-agent"><img src="https://agentmods.dev/badge/skills/daidaij/2native-ssh-mcp/2native-ssh-mcp-agent.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00063 | $0.02081 |
| Opus 5.5 | $0.00025 | $0.00832 |
| Sonnet 5.5 | $0.00013 | $0.00416 |
| Haiku 4.5 | $0.00006 | $0.00208 |
Grade B, and why
2native-ssh-mcp-agent 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 22d 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.
Asks for rootmediumPrivilege escalation
A mod that escalates privileges can change anything on the machine, not only the project.
- **sudo over exec has no TTY.** Password prompts fail fast (~1s) with `sudo: a terminal is required...` — pipe the password via `sudo -S` (never a CLI argument), or set `"pty": true` for commands that insist on a termin How it starts
The opening of the file, as written. The whole thing — 111 lines — stays where its author put it; the contents beside it link to each section on GitHub.
2native-ssh-mcp-agent
Defensive playbook for agents using 2native-ssh-mcp. Read this before executing on production hosts.
Golden rules
- Call
list-serversfirst — read metadata, aliases, notes; pickconnectionNameor plan asessionName. Avia=<name>label means the host is only reachable through that jump-host connection — no direct TCP path exists, and jump-host failures name it. - Always pass
connectionNameexplicitly — taken fromlist-servers. Omitting it only works when a connection nameddefaultexists (markeddefault=truein list-servers); otherwise the call fails. Never guess a connection: running on the wrong host is worse than a failed call. - Never use root — use a dedicated low-privilege account.
- Prefer narrow commands — scope with
head,tail,grep,wc, paths; avoid blindcaton large files. - Respect whitelist/blacklist — if a command is rejected, do not bypass; ask the operator to widen policy.
- Secrets — redaction is off by default (
"redactSecrets": trueenables it per connection); regardless, avoid printing credentials. - Host key rejection — if a connection fails with a host key mismatch (server reimaged / key rotated), do not bypass; report it. Fix is operator-side: remove the stale line from
known_hosts(or set"hostKeyCheck": "none"for dynamic-IP hosts). - Assume everything is recorded — executed commands land in a per-connection append-only, hash-chained audit log (failures included); act accordingly on production hosts.
Output & tokens
Built-in (automatic)
2native-ssh-mcp layers large output automatically:
- Directories transfer recursively via
file-transfer(per-file atomic upload,files/failedin the result; single files get a sha256 check). - ≥ 8KB (
outputSpillThreshold,-1disables): the full output is written to a local file (default.ssh-mcp-out/,outputSpillDirconfigurable, newest 32 kept). The result carries only a short notice, the absolute path, byte/line counts and a ~12-line preview. Grep/Read that local file — never re-run the command orcatit remotely. - 4–8KB: light compression — head + tail lines, middle replaced with
... [N lines omitted] ..., duplicate/blank lines collapsed. - Disable compression per connection:
"outputCompressLight": false; tune threshold:"outputCompressThreshold": 8192.
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.
- 22d ago Changed · +1 lines 7681bc2b6a66
- 1mo ago Changed · +2 lines e865b6ba2bf4
- 1mo ago Changed · +2 lines 5a5657207bdc
- 1mo ago Changed · +7 lines scan A → B 4d71da490c4d
- 1mo ago Changed · -3 lines 00cf9db19bb4
- 1mo ago First seen · 102 lines · 63 tokens per session scan A 9acf30c069b9
2native-ssh-mcp-agent is a skill published in the GitHub repository daidaiJ/2native-ssh-mcp (0 stars, last pushed 21d ago), licensed ISC. It adds 63 tokens to every session and 2,081 once invoked, about $0.0003 per session on Opus 5.5. A static security scan graded it B with 1 finding (asks for root). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
code-review
Structured code review prompt with language and focus area.
explain-error
Explain an error message with optional context.
gopls-mcp
Semantic Go code analysis using gopls — type-aware definitions, references, implementations, call hierarchy, dependency graphs, and rename previews. Use these tools for semantic Go tasks; never fall back to grep — gopls sees types, scopes, and interfaces that text search misses.
vibeshell
Control SSH and SFTP through VibeShell's visible Agent Gateway. Use for shared terminal sessions, remote commands, logs, files, and transfers.
incident-triage
Triage a network incident from symptoms to a suspected layer.
productplan-pm
Generates comprehensive workflows for product managers to manage roadmaps, OKRs, ideas, and launches in ProductPlan. Use when doing day-to-day product management work, updating feature timelines, tracking objectives, or triaging customer feedback.