Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/Victory-7291/project-scaffold-setup-skillsnpx agentmods add skills/victory-7291/project-scaffold-setup-skills/cpp-project-setupWrote 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.
[](https://agentmods.dev/skills/victory-7291/project-scaffold-setup-skills/cpp-project-setup)<a href="https://agentmods.dev/skills/victory-7291/project-scaffold-setup-skills/cpp-project-setup"><img src="https://agentmods.dev/badge/skills/victory-7291/project-scaffold-setup-skills/cpp-project-setup/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.
<a href="https://agentmods.dev/skills/victory-7291/project-scaffold-setup-skills/cpp-project-setup"><img src="https://agentmods.dev/badge/skills/victory-7291/project-scaffold-setup-skills/cpp-project-setup.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00078 | $0.01270 |
| Opus 5.5 | $0.00031 | $0.00508 |
| Sonnet 5.5 | $0.00016 | $0.00254 |
| Haiku 4.5 | $0.00008 | $0.00127 |
Grade A, and why
cpp-project-setup 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 1mo 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 — 88 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Modern C++ Project Setup
Overview
Create or modernize a C++ project around a reproducible toolchain:
Git -> GitHub -> VS Code -> CMakePresets + vcpkg -> Ninja -> compiler -> tests/lint/docs
Prefer project-local, repeatable setup over global machine assumptions. First classify the user's working directory and host platform, then either generate a greenfield scaffold or patch the existing project without erasing its current pipeline.
Workflow
-
Determine the user's working directory and whether a project already exists.
- Check the user-provided path or current working directory before writing files.
- Treat the directory as an existing project if it already has source files,
CMakeLists.txt, build scripts, package metadata, editor config, CI, docs, or a git history. - For existing work, inventory the full development pipeline before editing: build system, dependency manager, compiler and standard, presets/tasks/scripts, tests, format/lint/static analysis, docs, debugger/editor integration, CI, packaging/install rules, and generated artifacts.
- For greenfield work, default to an app plus reusable library target, C++20, Ninja, vcpkg manifest mode, GoogleTest, clang-format, clang-tidy, Doxygen, and VS Code settings.
- If the request is about MCU firmware, OpenOCD, linker scripts, startup code,
arm-none-eabi, or Cortex-Debug, switch toembedded-project-setup.
-
Detect the user's host development environment.
- Determine OS and architecture: macOS/Linux/Windows plus arm64 or x64. Use local commands such as
uname -s,uname -m,sysctl -n machdep.cpu.brand_string, or PowerShell/.NET runtime information where appropriate. - Select a host profile:
macos-arm64,macos-x64,linux-x64,linux-arm64,windows-x64, orwindows-arm64. - If the agent is running somewhere other than the user's real development machine, ask for the user's OS/architecture instead of assuming the sandbox matches their workstation.
- Determine OS and architecture: macOS/Linux/Windows plus arm64 or x64. Use local commands such as
What ships with it
9 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.
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.
- 1mo ago First seen · 88 lines · 78 tokens per session scan A e1f1f5348a73
cpp-project-setup is a skill published in the GitHub repository Victory-7291/project-scaffold-setup-skills (8 stars, last pushed 3mo ago), licensed MIT. It adds 78 tokens to every session and 1,270 once invoked, about $0.0003 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 2026-08-31.
Other skills, from other repositories
go-testing
Use when writing, reviewing, or running Go tests in test.go files — writing tests for a Go package, adding table-driven tests with t.Run subtests, testing a Go HTTP handler with httptest, adding a Go fuzz test or seed corpus, running or choosing go test flags (-race, -fuzz, -fuzztime), or deciding whether to use…
python-testing
Python test authoring and review with pytest. Use when writing, adding, generating, or reviewing Python tests or unit tests for a function, module, or class; running pytest or a single test (the -k flag and other invocation flags for a Makefile or CI); parametrizing test cases into the table-driven pattern; setting up…
blink-gc-plugin
Develop, build, test, and roll changes to the Blink GC Clang plugin (//tools/clang/blinkgcplugin). Use when modifying or adding Oilpan/Blink GC Clang plugin checks, running plugin unit tests, checking Chromium/Blink targets for new plugin violations, suppressing violations with GCPLUGINIGNORE, or force-rolling Clang…
test-quality
Write high-quality JUnit 5 tests with AssertJ assertions. Use when user says "add tests", "write tests", "improve test coverage", or when reviewing/creating test classes for Java code.
111-java-maven-dependencies
Use when you need to add or evaluate Maven dependencies that improve code quality or domain modeling — including nullness annotations (JSpecify), static analysis (Error Prone + NullAway), functional programming (VAVR), architecture testing (ArchUnit), or money and currency support (JavaMoney) — and want a…
130-java-testing-strategies
Use when you need to apply testing strategies for Java code — RIGHT-BICEP to guide test creation, A-TRIP for test quality characteristics, or CORRECT for verifying boundary conditions. This should trigger for requests such as Review Java code for testing strategies; Apply RIGHT-BICEP testing strategies in Java code…