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 aayushmau5/eva --skill write-extension-remotegit clone --depth 1 https://github.com/aayushmau5/evaWrote 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/aayushmau5/eva/write-extension-remote)<a href="https://agentmods.dev/skills/aayushmau5/eva/write-extension-remote"><img src="https://agentmods.dev/badge/skills/aayushmau5/eva/write-extension-remote/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/aayushmau5/eva/write-extension-remote"><img src="https://agentmods.dev/badge/skills/aayushmau5/eva/write-extension-remote.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 | $0.00049 | $0.01917 |
| Opus 5.5 | $0.00020 | $0.00767 |
| Sonnet 5.5 | $0.00010 | $0.00383 |
| Haiku 4.5 | $0.00005 | $0.00192 |
Grade A, and why
write-extension-remote 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 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.
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.
How it starts
The opening of the file, as written. The whole thing — 160 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Writing a remote Eva extension
A remote extension is a project extension that runs on another machine. The contract is
identical to a local one — same setup/1, same %Spec{}, same callbacks, same API, same
module namespace. Read the write-extension-local skill for all of that. This skill covers
what is different about running one elsewhere:
- how the node offers itself to other machines (
:port,:serve) - how the two machines agree on a secret (the cluster cookie)
- how the session's Eva is pointed at it (
mix eva.ext.remote) - what changes in the code you write (paths, and tool/command names)
When it is remote
Only projects, and only if you ask for it. A script (.exs) always compiles into the
session's own VM and can never run on another machine. A project node is loopback-only
until you pass :port, so "remote" is one option, not a different kind of extension.
The scaffolding is the same as any project — a mix.exs depending on eva_core, and an
application that starts Eva.Core.Extension.Node (see write-extension-local). Only the
node's options change:
children = [
{Eva.Core.Extension.Node,
name: "gpu",
module: Eva.Extension.Gpu,
port: 9001, # offer this node to your tailnet
serve: [:"[email protected]"]} # ...to these Evas only
]
:port is the whole of "another machine may dial me". It picks the interface, the port,
and the node's name together — the node names itself for this machine's address and listens
on exactly that port. Without it, the node listens on loopback and only its own machine can
see it.
:serve is your veto over who gets answered. Being dialable means anything reaching the
cookie can ask this node to instantiate an extension; :serve names the Evas that get an
answer. It defaults to :any, which is right for a loopback-only node — everything able to
reach it is already you, on your own machine. Being listed in someone else's config cannot
open a socket here. Eva names itself eva_<pid>@<host>, which is what an entry here matches.
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 · 160 lines · 49 tokens per session scan A ce68b084c042
write-extension-remote is a skill published in the GitHub repository aayushmau5/eva (7 stars, last pushed 2mo ago), licensed MIT. It adds 49 tokens to every session and 1,917 once invoked, about $0.0002 per session on Opus 5.5. 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.
write-extension-remote compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| write-extension-remoteaayushmau5/eva | Skill | 7 | 2mo ago | MIT | A | 49 | Claude Code, Codex |
| mem0-oss-to-platformmem0ai/mem0 | Skill | 68k | 2d ago | Apache-2.0 | A | 217 | Claude Code, Codex |
| azure-mgmt-botservice-dotnetmicrosoft/skills | Skill | 3.2k | yesterday | MIT | A | 78 | Claude Code |
| fastapi-router-pymicrosoft/skills | Skill | 3.2k | yesterday | MIT | A | 46 | Claude Code |
| dev-runtimelangwatch/langwatch | Skill | 5.0k | yesterday | Apache-2.0 | A | 172 | Claude Code |
| api-designericrisco/rsc-harness | Skill | 503 | 2d ago | MIT | A | 105 | Claude Code, Codex |
| migrate-segw-to-raparc-mcp/arc-1 | Skill | 252 | yesterday | MIT | A | 106 | Claude Code |