lua-client-server-contract-audit

lua-client-server-contract-audit is a skill for Claude Code, Codex from hoatv2211/GameStudio-CodexKIT. It costs 36 tokens per session (770 once invoked), scanned A, original, MIT.

A read-only comparison process for Lua client and server RPC contracts, the agreed message formats used between the two sides of a game or service.

In plain words
What is it for?
Use it to investigate packet failures, RPC mismatches, missing response fields, wrong operation codes, and duplicated or outdated protocol copies.
Why use it?
It finds disagreements in operation codes, fields, types, ordering, and source ownership that can cause requests to be dropped or responses to fail.

Skill for Claude CodeCodex

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/hoatv2211/gamestudio-codexkit/lua-client-server-contract-audit
Any agent
npx skills add hoatv2211/GameStudio-CodexKIT --skill lua-client-server-contract-audit
Clone the repo
git clone --depth 1 https://github.com/hoatv2211/GameStudio-CodexKIT

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 lua-client-server-contract-audit

README.md
[![agentmods](https://agentmods.dev/badge/skills/hoatv2211/gamestudio-codexkit/lua-client-server-contract-audit.svg)](https://agentmods.dev/skills/hoatv2211/gamestudio-codexkit/lua-client-server-contract-audit)
Your own site
<a href="https://agentmods.dev/skills/hoatv2211/gamestudio-codexkit/lua-client-server-contract-audit"><img src="https://agentmods.dev/badge/skills/hoatv2211/gamestudio-codexkit/lua-client-server-contract-audit.svg" alt="Measured on agentmods" height="20"></a>
Per session 36 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 770 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 $0.00036 $0.00770
Opus 5 $0.00018 $0.00385
Sonnet 5 $0.00007 $0.00154
Haiku 4.5 $0.00004 $0.00077

Measured 4d ago against content hash fdbef8b1413b, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

lua-client-server-contract-audit 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 4d ago.

The scan reads SKILL.md. This mod also ships 1 executable file (scripts/lua_contract_audit.py), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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/lua-client-server-contract-audit/SKILL.md · 79 lines

How it starts

The opening of the file, as written. The whole thing — 79 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Lua Client Server Contract Audit

Overview

Compare normalized client and server protocol contracts without editing either copy, then identify missing packets, opcode drift, field drift, and authority ambiguity.

When to use

Use for Lua packet failures, RPC mismatch, silent request drops, wrong opcodes, missing response fields, duplicated protocol tables, or client/server copy drift.

When NOT to use

Do not use for translation text authority, generic localization keys, or runtime network capture that requires service control or credentials.

Required inputs and context discovery

Collect authoritative and copied protocol paths, generation pipeline, packet names, opcodes, field order/types, request/response direction, client/server versions, and no-touch generated paths.

Safety and risk level

Read-only. Never edit generated protocol copies directly, send live exploit packets, start servers, or mutate network state during the audit.

Workflow

  1. Identify source-of-truth and generated/copied protocol files. Completion criterion: every compared file is labeled source, generated, copy, or unknown.
  2. Normalize packet names, opcodes, direction, and fields into deterministic maps. Completion criterion: parsing ambiguity is reported rather than guessed.
  3. Compare presence, opcode, field names/order/types, and request/response pairing. Completion criterion: mismatches cite both client and server paths.
  4. Trace the generation or synchronization path for each mismatch. Completion criterion: the correct editable source is identified or BLOCKED.
  5. Propose source-first fixes and regression fixtures without mutating live services. Completion criterion: generated copies are never hand-edited.

Evidence and output contract

Produce lua-contract-audit.json with source/copy classification, missing packets, opcode mismatches, field mismatches, authority, generation path, limitations, and recommended source fixes.

Handoff contract

Record client/server paths, versions, source authority, mismatches, generated no-touch files, parsing limitations, and next source-first action.

Read the full file on GitHub · 79 lines

Files

What ships with it

2 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.

  1. 4d ago First seen · 79 lines · 36 tokens per session scan A fdbef8b1413b

Subscribe to this mod's changes

lua-client-server-contract-audit is a skill published in the GitHub repository hoatv2211/GameStudio-CodexKIT (3 stars, last pushed yesterday), licensed MIT. It adds 36 tokens to every session and 770 once invoked, about $0.0002 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 2026-08-31.