reality-inbound

reality-inbound is a skill for Claude Code, Codex from pyworkload/3x-ui-mcp. It costs 94 tokens per session (1,512 once invoked), scanned A, original, MIT.

A setup and repair guide for a VLESS-REALITY inbound, a proxy connection that uses a real website's TLS handshake as camouflage. It checks a chosen destination, creates keys, configures the connection, and attaches a client.

In plain words
What is it for?
Use it to create or repair a REALITY inbound, choose and verify a camouflage target, configure its stream settings, and produce a client link.
Why use it?
It helps avoid broken or conspicuous REALITY configurations by checking the target's TLS and network properties first. It also avoids needing to register a domain or renew a certificate for this setup.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Install

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.

agentmods
npx agentmods add skills/pyworkload/3x-ui-mcp/reality-inbound
Any agent
npx skills add pyworkload/3x-ui-mcp --skill reality-inbound
Clone the repo
git clone --depth 1 https://github.com/pyworkload/3x-ui-mcp

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.

agentmods badge for reality-inbound

README.md
[![agentmods](https://agentmods.dev/badge/skills/pyworkload/3x-ui-mcp/reality-inbound.svg)](https://agentmods.dev/skills/pyworkload/3x-ui-mcp/reality-inbound)
Your own site
<a href="https://agentmods.dev/skills/pyworkload/3x-ui-mcp/reality-inbound"><img src="https://agentmods.dev/badge/skills/pyworkload/3x-ui-mcp/reality-inbound.svg" alt="Measured on agentmods" height="20"></a>
Per session 94 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,512 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00094 $0.01512
Opus 5 $0.00047 $0.00756
Sonnet 5 $0.00019 $0.00302
Haiku 4.5 $0.00009 $0.00151

Measured yesterday against content hash 8bc7379b0a5d, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

reality-inbound 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.

skills/reality-inbound/SKILL.md · 121 lines

How it starts

The opening of the file, as written. The whole thing — 121 lines — stays where its author put it; the contents beside it link to each section on GitHub.

REALITY inbound

REALITY hides the server by completing a real TLS 1.3 handshake with a third-party site (dest) and stealing its certificate for anyone who is not a genuine client. There is no domain to register and no certificate to renew — but the whole design rests on picking a good dest, and that choice is not something the panel checks for you.

Choosing the target

Four properties are mandatory, and scan_reality_target verifies all of them: TLS 1.3, HTTP/2 in ALPN, X25519 key exchange, and a certificate that chains to a trusted root. A candidate failing any one of them cannot be used at all.

The rest is judgment the scanner cannot make:

  1. Not fronted by a CDN with nodes in your users' country. Two separate problems: your server becomes a port-forwarder into that CDN for anyone who probes it, and a censor sees traffic leaving to a foreign IP for a domain that resolves locally — an anomaly that stands out precisely because the domain is popular.
  2. Not one of the giants. google.com, microsoft.com, apple.com and friends are the most-analysed SNIs on earth and are usually CDN'd locally. Xray-core agrees loudly enough to have hard-coded it: a serverNames entry containing apple or icloud logs "REALITY: Choosing apple, icloud, etc. as the target may get your IP blocked by the GFW" at startup.
  3. Reachable and not itself blocked where the users are. A blocked SNI is worse than no camouflage.
  4. Low RTT from the panel server, not from you. Every client handshake is proxied to dest, so its latency is added to connection setup. scan_reality_targets ranks candidates by feasibility first, then latency.
  5. Plausibly close to the VPS. A site in the same datacenter or AS as the server is both fast and unremarkable.

The trick worth knowing: scan_reality_targets accepts CIDR ranges and discovers candidates by reading the certificates hosts actually serve. Scanning the neighbourhood of your own VPS finds local, low-latency, unpopular targets that no published "good dest" list contains — and published lists are exactly the ones a censor also reads.

Read the full file on GitHub · 121 lines

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.

  1. yesterday First seen · 121 lines · 94 tokens per session scan A 8bc7379b0a5d

Subscribe to this mod's changes

reality-inbound is a skill published in the GitHub repository pyworkload/3x-ui-mcp (5 stars, last pushed 4d ago), licensed MIT. It adds 94 tokens to every session and 1,512 once invoked, about $0.0005 per session on Opus 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 2026-09-05.

Related

Other skills, from other repositories

opik-diagnose

Surface the Opik traces worth a developer's attention, ranked by signal — errors, failed tool calls, latency, regressions, and low online-eval scores — plus Diagnostics issues. Reads live/production traces via the SDK (searchtraces and agentinsights) and works with no MCP; uses the MCP issue entity when connected.…

comet-ml/opik-mcp · 147 tokens

cortex-explore-memory

Explore the memory system's state, find gaps in knowledge, assess coverage, and get diagnostic information. Use when the user asks 'what does my memory look like', 'show me memory stats', 'what am I missing', 'how good is my knowledge', 'memory health', 'show coverage', 'find gaps', 'what topics are weak', or when you…

cdeust/Cortex · 91 tokens

quick-capture

Use this skill to drop a new task into GSD Task Manager from any AI assistant that has the gsd-mcp-server connected.

vscarpenter/gsd-task-manager · 0 tokens

event-staffing-ordering

Order W-2 event staff for US/CA events through TempGuru.

Tempguru-co/tempguru-mcp · 22 tokens

chainstack

Work with the Chainstack MCP server to manage blockchain nodes and projects. Use when deploying nodes, migrating to Chainstack from another RPC provider such as QuickNode or Alchemy, checking platform status, searching Chainstack docs, contacting the Chainstack team, or interacting with the Chainstack platform API via…

chainstacklabs/mcp-server · 66 tokens

mcp2cli

Use mcp2cli to connect to, explore, and execute commands against any MCP (Model Context Protocol) server from the terminal. Covers discovery, tool invocation, resource reading, prompt execution, alias creation, config management, background jobs, authentication, and JSON output pipelines.

mcp2cli/source-code · 60 tokens