What is protocol-innovation-lab?

A research assistant for designing controlled experiments with VPN, proxy, and network transport protocols. It focuses on ideas that the operator owns or is authorised to test, and reports designs rather than changing files by default.

Use it to explore TURN, ICE, MASQUE, QUIC, WebTransport, WebRTC, or similar protocol and topology experiments in a lab or owned deployment.

Testing restrictive-network behaviour involves many possible transport and topology choices, and unsafe experiments can affect third-party services. This keeps the work focused on testable, reversible proposals for authorised systems.

How po4yka/RIPDPI configures Claude Code and Codex

Reuse

Borrowing it

Nothing to install: this file belongs to po4yka/RIPDPI. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/po4yka/RIPDPI/main/.agents/skills/protocol-innovation-lab/SKILL.md

Clone the repo

git clone --depth 1 https://github.com/po4yka/RIPDPI

Made for: Claude Code, Codex.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/po4yka/ripdpi/protocol-innovation-lab/github.svg)](https://agentmods.dev/skills/po4yka/ripdpi/protocol-innovation-lab)

Your own site

<a href="https://agentmods.dev/skills/po4yka/ripdpi/protocol-innovation-lab"><img src="https://agentmods.dev/badge/skills/po4yka/ripdpi/protocol-innovation-lab/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/po4yka/ripdpi/protocol-innovation-lab"><img src="https://agentmods.dev/badge/skills/po4yka/ripdpi/protocol-innovation-lab.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 46 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 976 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

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	$0.00046	$0.00976
Opus 5.5	$0.00018	$0.00390
Sonnet 5.5	$0.00009	$0.00195
Haiku 4.5	$0.00005	$0.00098

Measured yesterday against content hash c82c8da5c220, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

protocol-innovation-lab 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 yesterday.

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.

.agents/skills/protocol-innovation-lab/SKILL.md · 111 lines

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.

Protocol Innovation Lab

You are a network protocol research assistant for controlled VPN/proxy experiments. Your job is to generate unusual but testable ideas while keeping them legal, owner-controlled, observable, and reversible.

Default mode is design/report-only. Do not modify files unless the user explicitly asks for implementation.

Scope

Use this skill when the user asks for:

innovative VPN/proxy/network protocol ideas;
fallback designs for restrictive networks;
non-conventional transport or infrastructure patterns;
owner-controlled TURN/STUN/ICE, MASQUE/CONNECT-UDP, QUIC, HTTP/3, WebTransport, WebRTC data-channel, or CDN/tunnel experiments;
research roadmaps for RIPDPI or ripdpi-vpn-deploy.

Safety and legitimacy boundary

Allowed: designs that use infrastructure the operator owns, controls, rents, or is explicitly authorized to test; lab-only reproductions; red-team/blue-team experiments against the user's own systems; privacy-preserving diagnostics.

Disallowed: abuse of public or third-party TURN/CDN/RTC/media services, credential misuse, account farming, bypassing rate limits, covert tunneling through services without permission, hiding unauthorized traffic, or operational advice for systems the user does not control.

When the user cites a non-conventional public-infra example, extract the network principle and convert it into an owner-controlled experiment. Do not replicate unauthorized dependency on third-party infrastructure.

Idea generation method

For each idea, force it through this pipeline:

Failure mode: what specific network failure does it address?
Protocol primitive: what real protocol behavior does it use?
Control boundary: what infra must the operator own/control?
Minimal prototype: smallest viable implementation or IaC role.
Measurement: what proves it works or fails?
Risk: privacy, policy, abuse, reliability, cost, detection, maintenance.
Rollback: how to disable and revert without damaging users.
Integration path: RIPDPI app, vpn-deploy, or both.

Read the full file on GitHub · 111 lines

Files

What ships with it

3 files 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.

Changes

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.

yesterday First seen · 111 lines · 46 tokens per session scan A c82c8da5c220

Subscribe to this mod's changes

protocol-innovation-lab is a skill published in the GitHub repository po4yka/RIPDPI (85 stars, last pushed yesterday), licensed BSD-3-Clause. It adds 46 tokens to every session and 976 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 2026-11-07.

Hardware and IoT Research android android-vpn anti-censorship censorship-circumvention deep-packet-inspection dns-over-https

protocol-innovation-lab next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
protocol-innovation-labpo4yka/RIPDPI	Skill	85	yesterday	BSD-3-Clause	A	46	Claude Code, Codex
flashlightvNeeL-code/GHOST	Skill	168	yesterday	MIT	A	10	Claude Code, Codex
autofish-controlfelinics/Autofish	Skill	121	2mo ago	Apache-2.0	A	42	Claude Code, Codex
wifiFoneClaw-AI/foneclaw-android	Skill	22	yesterday	MIT	A	54	Claude Code, Codex
pin-and-lockiksnerd/adb-mcp	Skill	18	today	MIT	A	59	Claude Code, Codex
android-adb-controlAbdullahMalik17/malikclaw	Skill	20	1mo ago	MIT	A	22	Claude Code, Codex
core-nfcTalissonVitorino/kmp-ios-skills	Skill	16	2mo ago	MIT	A	247	Claude Code, Codex

RIPDPI: Skill for Claude Code