remote-access SKILL.md skillA

remote-access from douglasjunior/agent-remote-control is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned
mdr add douglasjunior/agent-remote-control/remote-access@git:20261117.f1d7156

Pins git:20261117.f1d7156 in mdr.lock. Pin the fingerprint instead.

Audit grade
A, 17 of 17 checks passed
Kind
SKILL.md skill
Repository
douglasjunior/agent-remote-control
Path
.agents/skills/remote-access/SKILL.md
Versions recorded
3
Latest version
git:20261117.f1d7156, committed Nov 17, 2026
First version recorded
Nov 14, 2026
Size
14,357 bytes
Repository stars
10
License
MIT

Remote access from anywhere over WebRTC: the signaling protocol, data channel frames, remote link and certificate fingerprint in packages/protocol, the NestJS signaling server in packages/p2p-server (host registration, sessions, STUN and TURN credentials, the hosted web app), the remote module of the server (instance identity, signaling client, node-datachannel peers, the transport of the web channel) and the coturn relay in deploy/. Use when working with remote access, signaling, WebRTC…

Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.

What the file says

# Remote access

> **Maintaining this skill**
>
> Update this document whenever any rule described here changes. The criterion is not
> *which* rule — it is the nature of the change: a signaling, trust, framing, relay or deployment rule
> changed → update; a refactor that preserves the described behavior → leave it alone.

Anyone who reaches the web channel of a host runs agents on it with full autonomy. The signaling server and the TURN
relay are not trusted with that: they introduce and relay, and every rule below keeps them unable to read the messages,
to stand in for a host or to learn the access token. They do serve the web app, though, so whoever operates them could
serve a page that reads the token: remote access is off unless `REMOTE_ENABLED=true`, a choice of trust in the operator
of `REMOTE_URL`, documented in the README and in `docs/remote-access.md`.

## Protocol (`packages/protocol`)

- `signaling.ts`: four zod unions, one per direction — `hostSignalSchema` (`host.register`, `host.accept`,
  `host.reject`, `host.answer`, `host.candidate`, `host.close`), `toHostSignalSchema` (`host.challenge`,
…

Read the whole file at its exact version.

How to install

No tool to install first
claude plugin marketplace add https://markdownregistry.com/mp/a/art_qlw6zxvz5ggdepgg/eb3aa9bca8a586105048ee99a4d22127e607b64aa4df18c928a3d55d40015112.json

Then /plugin install remote-access@markdownregistry-qlw6zxvz5ggdepgg in Claude Code. It installs git:20261117.f1d7156, the one graded A here, pinned to the commit it was graded at, and leaves it there.

The exact contents, by fingerprint
mdr add douglasjunior/agent-remote-control/remote-access@sha256:eb3aa9bca8a58610

The line at the top of this page pins the label git:20261117.f1d7156, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.

Badge

mdr badge

[![mdr](https://markdownregistry.com/badge/art_qlw6zxvz5ggdepgg.svg)](https://markdownregistry.com/a/art_qlw6zxvz5ggdepgg)

2 badge image fetches in 30 days. What the badge shows.

Ask from your agent
claude mcp add --transport http markdownregistry https://markdownregistry.com/mcp/registry

Then ask it: what changed in douglasjunior/agent-remote-control/remote-access since the version I have? It reads every saved version here, no key and no account. Any agent that speaks MCP can add it.

Got a copy of remote-access from somewhere else? Ask it: where did my remote-access come from, and what was changed? It names the public original, the version yours is closest to and every changed line. The text is not kept.

Versions

The registry has recorded 3 versions of this file, between Nov 14, 2026 and Nov 17, 2026, about one every day.

Watch this file (sign in, one email per new version)

versioncommittedcommitsizeaudit
git:20261117.f1d7156 latest2026-11-17 f1d7156 14,357 BA view · diff
git:20261115.39512b82026-11-15 39512b8 14,350 BA view · diff
git:20261114.dfd0f2e2026-11-14 dfd0f2e 14,042 BA view
Keep it current by itself, install once

Committed this skill to a repository? Install the markdownregistry skill updates app on it, or on all of them. When the registry saves a newer version, a pull request brings your copy to it within minutes, the newest version first, then what changed and any check it newly trips. A copy you edited is never touched, and nothing is deleted.

Install on GitHub

It asks to read and write contents and pull requests, and to read metadata. No workflow file, no Actions setting, nothing runs on your runners. Uninstall it and everything the registry kept about your repository is deleted.

Keep it current by itself

Committed this skill to a repository? Add one workflow file, and when a newer version is saved, a pull request brings your copy to it, the newest version first, then what changed and any check it newly trips. A copy you edited is never touched, and nothing is deleted.

mkdir -p .github/workflows && curl -fsSL https://markdownregistry.com/ci/skill-updates.yml -o .github/workflows/skill-updates.yml

It runs daily on GitHub Actions, no key and no account. Read the workflow before you add it.

Check a whole project

From the root of your project, one line hashes each installed skill's SKILL.md, your AGENTS.md and your CLAUDE.md, and asks the registry once. Only the fingerprints and paths are sent.

sha256sum .claude/skills/*/SKILL.md AGENTS.md CLAUDE.md | curl -s --data-binary @- https://markdownregistry.com/api/v1/check-copies

In CI, add --fail-with-body: the answer is 409 when any file is behind, so the step fails and still prints which files.

sha256sum .claude/skills/*/SKILL.md AGENTS.md CLAUDE.md | curl -s --fail-with-body --data-binary @- https://markdownregistry.com/api/v1/check-copies

No sha256sum on your machine? shasum -a 256 prints the same lines.

Audit of the latest version

A  17 of 17 checks passed. Fixed automatic checks with no AI involved, so the same checks give the same answer every run.
  • pass: Frontmatter block present
  • pass: Frontmatter declares a name
  • pass: Frontmatter declares a description
  • pass: Size between 200 bytes and 200 KB (14357 bytes)
  • pass: No zero-width or bidi control characters
  • pass: No instruction hidden inside an HTML comment
  • pass: No link to an exfiltration or paste host
  • pass: No credential-shaped string
  • pass: No instruction to send local credentials anywhere
  • pass: No text hidden with inline styles
  • pass: No prompt-injection phrasing
  • pass: No curl or wget piped into a shell
  • pass: No recursive delete of root, home or parent
  • pass: No instruction to read or print local credentials
  • pass: No base64 blob over 200 characters
  • pass: No link to a raw IP address
  • pass: No script tag

Source

GitHub

douglasjunior/agent-remote-control · 10 stars · license MIT · pushed 2026-11-17 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_qlw6zxvz5ggdepgg
GET https://markdownregistry.com/api/v1/resolve?ref=douglasjunior/agent-remote-control/remote-access
GET https://markdownregistry.com/api/v1/blob/eb3aa9bca8a586105048ee99a4d22127e607b64aa4df18c928a3d55d40015112

Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.

Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.

More from douglasjunior/agent-remote-control

agent-definitions SKILL.md skill
douglasjunior/agent-remote-control · .agents/skills/agent-definitions/SKILL.md · Standard for defining, parameterizing and registering AI agent personas in the system. Governs the AgentRole roles…
git:20261117.73c5996 · audit A · 10 stars
agent-port SKILL.md skill
douglasjunior/agent-remote-control · .agents/skills/agent-port/SKILL.md · Integrates AI coding agent CLIs over the Agent Client Protocol (ACP) behind the IAgentPort port: session lifecycle and…
git:20261114.74435bb · audit A · 10 stars
artifacts SKILL.md skill
douglasjunior/agent-remote-control · .agents/skills/artifacts/SKILL.md · Board of features and tasks of each conversation: the artifacts module, the IArtifactsPort and its rules (two levels…
git:20261114.74435bb · audit A · 10 stars
clean-architecture-nestjs SKILL.md skill
douglasjunior/agent-remote-control · .agents/skills/clean-architecture-nestjs/SKILL.md · Clean Architecture with Ports & Adapters architectural pattern in NestJS. Defines the split into vertical modules…
git:20261107.40807bc · audit A · 10 stars
code-comments SKILL.md skill
douglasjunior/agent-remote-control · .agents/skills/code-comments/SKILL.md · Defines when a comment is allowed and when it is noise in TypeScript and NestJS code. Eliminates obvious comments that…
git:20261025.9e7b1fb · audit A · 10 stars
code-organization SKILL.md skill
douglasjunior/agent-remote-control · .agents/skills/code-organization/SKILL.md · Defines the internal organization of files and modules in TypeScript and NestJS: minimal public surface, a total ban on…
git:20261107.40807bc · audit A · 10 stars
discord-bot SKILL.md skill
douglasjunior/agent-remote-control · .agents/skills/discord-bot/SKILL.md · Discord bot as the primary input adapter for AI agents. Covers the slash commands (/agent, /model, /profiles, /usage…
git:20261114.74435bb · audit A · 10 stars
logging SKILL.md skill
douglasjunior/agent-remote-control · .agents/skills/logging/SKILL.md · Server logging: Nest's Logger as the only logging API, the provider bound to IAppLoggerPort, conversation-tagged JSON…
git:20261114.dfd0f2e · audit A · 10 stars
orchestrator SKILL.md skill
douglasjunior/agent-remote-control · .agents/skills/orchestrator/SKILL.md · Channel-agnostic agent orchestration: turns, CEO delegation (<delegate>/<agent_result>), questions agents ask the user…
git:20261114.74435bb · audit A · 10 stars
shadcn-ui SKILL.md skill
douglasjunior/agent-remote-control · .agents/skills/shadcn-ui/SKILL.md · How to use the shadcn CLI in packages/web: searching and installing components, the preset and style in…
git:20261107.ef2986e · audit A · 10 stars
skill-authoring SKILL.md skill
douglasjunior/agent-remote-control · .agents/skills/skill-authoring/SKILL.md · Standard for creating, reviewing, updating or splitting any skill (domain or technical) in .agents/skills/. Defines…
git:20261114.74435bb · audit A · 10 stars
tests-best-practices SKILL.md skill
douglasjunior/agent-remote-control · .agents/skills/tests-best-practices/SKILL.md · Rules for automated tests with Rstest and the NestJS Testing Module. Covers the golden rule of rs.mock only for…
git:20261117.f1d7156 · audit A · 10 stars

Every file in douglasjunior/agent-remote-control

Browse by kind, by grade A, or by owner.

Kept in .agents/skills, the folder Codex reads. More agent skills for Codex.