CS2_VibeSignatures: Skill for Claude Code

.claude/skills/find-CNetworkGameServerBase_CreateFakeClient/SKILL.md

find-CNetworkGameServerBase_CreateFakeClient is a skill for Claude Code from HLND2T/CS2_VibeSignatures. It costs 87 tokens per session (1,063 once invoked), scanned A, original, MIT.

A fallback procedure for finding a specific Counter-Strike 2 game-engine function in compiled program files using IDA Pro, a reverse-engineering tool. It is used only when an earlier automated finder cannot resolve the function.

In plain words
What is it for?
Use it to investigate the `CNetworkGameServerBase_CreateFakeClient` function in the Windows or Linux Counter-Strike 2 engine binary.
Why use it?
It provides another way to locate the function when a string-based search has failed, but the input does not describe the full recovery procedure.

Skill for Claude Code

Written for Claude Code: disable-model-invocation in frontmatter.

This is HLND2T/CS2_VibeSignatures's own configuration. It tells Claude Code how to work on CS2_VibeSignatures itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything CS2_VibeSignatures configures →

Reuse

Borrowing it

Nothing to install: this file belongs to HLND2T/CS2_VibeSignatures. 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/HLND2T/CS2_VibeSignatures/main/.claude/skills/find-CNetworkGameServerBase_CreateFakeClient/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/HLND2T/CS2_VibeSignatures

Made for: Claude Code.

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 find-CNetworkGameServerBase_CreateFakeClient

README.md
[![agentmods](https://agentmods.dev/badge/skills/hlnd2t/cs2_vibesignatures/find-cnetworkgameserverbase_createfakeclient/github.svg)](https://agentmods.dev/skills/hlnd2t/cs2_vibesignatures/find-cnetworkgameserverbase_createfakeclient)
Your own site
<a href="https://agentmods.dev/skills/hlnd2t/cs2_vibesignatures/find-cnetworkgameserverbase_createfakeclient"><img src="https://agentmods.dev/badge/skills/hlnd2t/cs2_vibesignatures/find-cnetworkgameserverbase_createfakeclient/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.

agentmods 80×15 button for find-CNetworkGameServerBase_CreateFakeClient

Your own site · 80×15
<a href="https://agentmods.dev/skills/hlnd2t/cs2_vibesignatures/find-cnetworkgameserverbase_createfakeclient"><img src="https://agentmods.dev/badge/skills/hlnd2t/cs2_vibesignatures/find-cnetworkgameserverbase_createfakeclient.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 87 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,063 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. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 $0.00087 $0.01063
Opus 5 $0.00044 $0.00531
Sonnet 5 $0.00017 $0.00213
Haiku 4.5 $0.00009 $0.00106

Measured 3d ago against content hash a3fdf7c8dfdf, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

find-CNetworkGameServerBase_CreateFakeClient 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 3d 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.

.claude/skills/find-CNetworkGameServerBase_CreateFakeClient/SKILL.md · 89 lines

How it starts

The opening of the file, as written. The whole thing — 89 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Find CNetworkGameServerBase_CreateFakeClient (final-guarantee fallback)

Recover the concrete CNetworkGameServerBase_CreateFakeClient function in CS2 engine2.dll / libengine2.so using IDA Pro MCP tools. This is an Agent fallback: it runs only when ida_preprocessor_scripts/find-CNetworkGameServerBase_CreateFakeClient.py cannot resolve the target.

Realworld Function References

The finder has no dedicated predecessor reference YAML. Use these related references for the class and calling conventions; their addresses and offsets are reference-build values and must be verified against the current binary.

  • ida_preprocessor_scripts/references/engine/CNetworkGameServerBase_Init.windows.yaml
  • ida_preprocessor_scripts/references/engine/CNetworkGameServerBase_Init.linux.yaml
  • ida_preprocessor_scripts/references/engine/CNetworkGameServerBase_ConnectClient.windows.yaml
  • ida_preprocessor_scripts/references/engine/CNetworkGameServerBase_ConnectClient.linux.yaml

Semantic fingerprint

CNetworkGameServerBase_CreateFakeClient is a member of CNetworkGameServerBase that creates and initializes a fake network client. The deterministic finder anchors it with both exact string references 30000 and rate. Those literals identify the rate initialization in the target or in a small helper it calls; do not identify the function from either literal alone.

The first argument is the server object (rcx on Windows, usually rdi/r12 on Linux). Confirm that the candidate allocates or initializes a client and that the 30000/rate values belong to that initialization path, not to an unrelated command or diagnostic routine.

Step 0. Skip an existing output

If CNetworkGameServerBase_CreateFakeClient.<platform>.yaml already exists in the active artifact module directory and parses to a non-empty mapping, skip that platform. Never derive the artifact path from bin.

Step 1. Locate the target in IDA

  1. Search the current binary for the exact string literals 30000 and rate (including command-table or format string variants), then enumerate their code xrefs.
  2. Decompile each function that references both anchors. Prefer the candidate whose first parameter is the CNetworkGameServerBase object and whose body creates a client, sets its connection/rate state, or calls the client initialization helper.
  3. If the two strings occur in a helper, follow callers and callees one level in each direction until the containing CNetworkGameServerBase member is identified. The helper may be inlined or outlined on either platform, so use the client-construction and rate-initialization semantics rather than a fixed address.
  4. Reject candidates that only register a console command, format a message, or initialize an unrelated rate.

Read the full file on GitHub · 89 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. 3d ago First seen · 89 lines · 87 tokens per session scan A a3fdf7c8dfdf

Subscribe to this mod's changes

find-CNetworkGameServerBase_CreateFakeClient is a skill published in the GitHub repository HLND2T/CS2_VibeSignatures (65 stars, last pushed today), licensed MIT. It adds 87 tokens to every session and 1,063 once invoked, about $0.0004 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 2026-09-06.