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.
npx agentmods add skills/hlnd2t/cs2_vibesignatures/create-cpp-testsnpx skills add HLND2T/CS2_VibeSignatures --skill create-cpp-testsgit clone --depth 1 https://github.com/HLND2T/CS2_VibeSignaturesWhat 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 | $0.00074 | $0.01858 |
| Opus 5 | $0.00037 | $0.00929 |
| Sonnet 5 | $0.00015 | $0.00372 |
| Haiku 4.5 | $0.00007 | $0.00186 |
Grade A, and why
create-cpp-tests scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 191 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Create cpp_tests for Interface Vtable Validation
Create a cpp_tests/<interface_lowercase>.cpp test file and append a matching configs/<GAMEVER>.yaml
entry so that run_cpp_tests.py can compile the header with clang, dump the vtable layout,
and compare it against reference YAML files from the binary analysis.
Resolve GAMEVER from the user's explicit request or CS2VIBE_GAMEVER, set the edit target to
configs/$GAMEVER.yaml, and stop if that exact file does not exist.
When to Use
- User asks to create cpp_tests for an interface (e.g., "create cpp_tests for ILoopMode")
- User provides or references a header file from
hl2sdk_cs2/
Inputs
The user will provide some or all of:
| Field | Required | Description | Example |
|---|---|---|---|
| Interface name | Yes | The abstract class to validate | ILoopMode |
| Header path | Yes | Path to the header in hl2sdk_cs2 | hl2sdk_cs2/public/iloopmode.h |
| Alias symbols | No | Concrete class name(s) used in binary YAML files | CLoopModeGame |
| Reference modules | No | Modules where vtable YAMLs live | client, server |
Step-by-Step Procedure
Step 1: Read the target header
Read the header file to understand:
- What
#includedirectives it uses - What types are referenced in virtual method signatures
- Whether it inherits from another interface (e.g.,
IAppSystem)
Step 2: Identify compilation dependencies
Check if the header's transitive includes will compile cleanly with the standard include set:
hl2sdk_cs2/game/sharedhl2sdk_cs2/publichl2sdk_cs2/public/tier0hl2sdk_cs2/public/tier1
Common issues to watch for:
- Missing types referenced in method signatures (e.g.,
CSplitScreenSlotneeds<tier1/convar.h>) - Heavy transitive includes that pull in protobuf or other unavailable deps (e.g.,
eiface.h-> protobuf chain)
For heavy transitive includes, pre-define include guards to block them and forward-declare/stub the minimum needed types. See the inetworkmessages.cpp and inetworksystem.cpp examples for this technique:
What ships with it
1 file 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.
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.
- 2d ago First seen · 191 lines · 74 tokens per session scan A 02f80300f89e
create-cpp-tests is a skill published in the GitHub repository HLND2T/CS2_VibeSignatures (65 stars, last pushed 3d ago), licensed MIT. It adds 74 tokens to every session and 1,858 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 2026-08-30.
Other skills, from other repositories
run-c-unit-tests
Run C/C++ unit tests to verify correctness. Use this after making changes to C code to verify nothing is broken.
cpp-project-setup
Modern C++ project setup: CMake/CMakePresets, vcpkg, Ninja, VS Code/clangd, GoogleTest, clang-format/tidy, Doxygen, CI, macOS/Linux/Windows. Use for bootstrapping or modernizing host-side C++ apps and libraries; prefer embedded-project-setup for MCU firmware and cross-debug flows.
cpp-testing
Use only when writing/updating/fixing C++ tests, configuring GoogleTest/CTest, diagnosing failing or flaky tests, or adding coverage/sanitizers.
c-testing
C testing workflow for unit and integration tests: deterministic harnesses, CMake/CTest execution strategy, sanitizer-first debugging, and fuzzing escalation. Use when writing or fixing tests for C (C11+) modules, stabilizing flaky suites, or reproducing memory/UB bugs.
cpp-testing
C++ testing workflow for unit and integration tests: GoogleTest/GoogleMock, CMake/CTest integration, diagnosing flaky tests, and running sanitizers and coverage for correctness signal. Use when writing or fixing C++ tests and test infrastructure.
cpp-testing
Use only when writing/updating/fixing C++ tests, configuring GoogleTest/CTest, diagnosing failing or flaky tests, or adding coverage/sanitizers.