Borrowing it
Nothing to install: this file belongs to Coefficient-work/mcp-doctor. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/Coefficient-work/mcp-doctor/main/.cursor/skills/cross-machine-fetch/SKILL.mdgit clone --depth 1 https://github.com/Coefficient-work/mcp-doctorWrote 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/coefficient-work/mcp-doctor/cross-machine-fetch)<a href="https://agentmods.dev/skills/coefficient-work/mcp-doctor/cross-machine-fetch"><img src="https://agentmods.dev/badge/skills/coefficient-work/mcp-doctor/cross-machine-fetch/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/coefficient-work/mcp-doctor/cross-machine-fetch"><img src="https://agentmods.dev/badge/skills/coefficient-work/mcp-doctor/cross-machine-fetch.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 | $0.00079 | $0.01620 |
| Opus 5.5 | $0.00032 | $0.00648 |
| Sonnet 5.5 | $0.00016 | $0.00324 |
| Haiku 4.5 | $0.00008 | $0.00162 |
Grade D, and why
cross-machine-fetch scanned grade D with 2 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 2mo 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.
2. **Tailscale SSH** — optional: `sudo tailscale set --ssh` only when CLI and GUI share the same daemon. 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.
BatchMode (agent) fetches need a **pubkey** in the peer’s `~/.ssh/authorized_keys`. Password prompts will fail under BatchMode. How it starts
The opening of the file, as written. The whole thing — 144 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Cross-machine fetch (Tailscale / Remote Login SSH)
When to use
- User gives an absolute path under
/Users/louisreid/...but the agent runs on the Mini (roundtableopenclaw) - Local
lsfails with “No such file” for Downloads CSVs/PDFs that Louis just exported on the Air - User asks to SSH to the MacBook / Air and pull files
Do not invent file contents. Fetch or ask — never fake bank/CSV data.
Machine map (bidirectional)
| Role | Tailscale / Host alias | Typical IP | SSH user | Home |
|---|---|---|---|---|
| Mini (agents often here) | roundtableopenclaw / mini |
100.84.168.56 |
roundtableopenclaw |
/Users/roundtableopenclaw |
| MacBook Air (Louis daily) | louiss-macbook-air / air |
100.83.203.72 |
louisreid |
/Users/louisreid |
Resolve live: tailscale status (prefer MagicDNS name over hardcoding the IP).
Preferred auth
- macOS Remote Login (classic SSH on port 22) — preferred when Tailscale CLI/daemon versions disagree. System Settings → General → Sharing → Remote Login → On (allow the peer user).
- Tailscale SSH — optional:
sudo tailscale set --sshonly when CLI and GUI share the same daemon.
BatchMode (agent) fetches need a pubkey in the peer’s ~/.ssh/authorized_keys. Password prompts will fail under BatchMode.
Identity files
| Direction | Client | Key to offer | Where it must be authorized |
|---|---|---|---|
| Mini → Air | Mini | ~/.ssh/reid-finance-deploy (ed25519) |
Air: ~louisreid/.ssh/authorized_keys |
| Air → Mini | Air | Louis’s Mac key (matches Mini authorized_keys) |
Mini: ~roundtableopenclaw/.ssh/authorized_keys |
SSH config Host aliases (install script / manual):
Host air louiss-macbook-air
HostName 100.83.203.72
User louisreid
IdentityFile ~/.ssh/reid-finance-deploy
IdentitiesOnly yes
Host mini roundtableopenclaw
HostName 100.84.168.56
User roundtableopenclaw
IdentitiesOnly yes
What ships with it
1 file 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.
- 2mo ago First seen · 144 lines · 79 tokens per session scan D 1e96fe33d533
cross-machine-fetch is a skill published in the GitHub repository Coefficient-work/mcp-doctor (0 stars, last pushed 2mo ago), licensed MIT. It adds 79 tokens to every session and 1,620 once invoked, about $0.0003 per session on Opus 5.5. A static security scan graded it D with 2 findings (asks for root, reaches for credential files). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
cross-machine-fetch compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| cross-machine-fetchCoefficient-work/mcp-doctor | Skill | 0 | 2mo ago | MIT | D | 79 | Cursor |
| imagegenopenai/codex | Skill | 133k | yesterday | Apache-2.0 | A | 113 | Codex |
| playwright-climicrosoft/playwright | Skill | 99k | yesterday | Apache-2.0 | A | 19 | Claude Code |
| local-ai-agentsmicrosoft/ai-agents-for-beginners | Skill | 79k | 4d ago | MIT | A | 200 | Claude Code, Codex |
| systematic-debuggingobra/superpowers | Skill | 313k | 3d ago | MIT | A | 21 | Claude Code |
| next-cache-components-adoptionvercel/next.js | Skill | 143k | today | MIT | A | 95 | Claude Code |
| next-partial-prefetching-adoptionvercel/next.js | Skill | 143k | today | MIT | A | 103 | Claude Code |