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/mohitmishra786/low-level-dev-skills/cpp-modulesnpx skills add mohitmishra786/low-level-dev-skills --skill cpp-modulesgit clone --depth 1 https://github.com/mohitmishra786/low-level-dev-skillsWhat 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 | $0.00076 | $0.01605 |
| Opus 5 | $0.00038 | $0.00803 |
| Sonnet 5 | $0.00015 | $0.00321 |
| Haiku 4.5 | $0.00008 | $0.00161 |
Grade A, and why
cpp-modules 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.
How it starts
The opening of the file, as written. The whole thing — 203 lines — stays where its author put it; the contents beside it link to each section on GitHub.
C++20 Modules
Purpose
Guide agents through authoring, building, and debugging C++20 modules: named modules vs header units, module partitions, CMake integration, compiler-specific flags, and interoperability with legacy headers.
Triggers
- "How do I write a C++20 module?"
- "How do I import a module in CMake?"
- "What's the difference between a named module and a header unit?"
- "My module gives 'cannot find module' errors"
- "How do I use C++20 modules with Clang?"
- "How do I migrate from headers to modules?"
Workflow
1. Module concepts overview
C++20 module kinds:
├── Named module interface unit (.cppm / .ixx) — exports declarations
├── Module implementation unit (.cpp) — defines module members
├── Module partition (.cppm) — internal module subdivision
└── Header unit (any header) — import a legacy header as module
Named modules are the primary target. Header units are a bridge for legacy code. Avoid Global Module Fragment unless required for macro access.
2. Named module — minimal example
// math.cppm — module interface unit
export module math; // declares the module name
export int add(int a, int b) { return a + b; }
export double pi = 3.14159;
// Non-exported (module-private)
int internal_helper() { return 42; }
// main.cpp — consumer
import math; // import the module
#include <iostream> // legacy header (still works)
int main() {
std::cout << add(2, 3) << "\n"; // 5
std::cout << pi << "\n";
}
3. Module partitions
// math-core.cppm — partition
export module math:core; // partition 'core' of module 'math'
export int add(int a, int b) { return a + b; }
// math.cppm — primary module interface
export module math;
export import :core; // re-export the partition
// math-impl.cpp — implementation unit (no export)
module math; // belongs to 'math' module, not a partition
// has access to all math declarations, but exports nothing
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.
- 3d ago First seen · 203 lines · 76 tokens per session scan A fbbb5ea5d334
cpp-modules is a skill published in the GitHub repository mohitmishra786/low-level-dev-skills (192 stars, last pushed 2mo ago), licensed MIT. It adds 76 tokens to every session and 1,605 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
spanify-buffers
Find and fix unsafe buffer operations in a C++ file by removing UNSAFETODO markers and replacing unsafe raw pointers/C-style functions with base::span and standard safe containers. Use when the user asks to fix unsafe buffer warnings or -Wunsafe-buffer-usage errors. Don't use for other types of memory safety bugs like…
jni-type-conversion
How to use @JniType annotations for ergonomic JNI. Relevant for Java files that use @NativeMethods or @CalledByNative.
cpp-pro
Writes, optimizes, and debugs C++ applications using modern C++20/23 features, template metaprogramming, and high-performance systems techniques. Use when building or refactoring C++ code requiring concepts, ranges, coroutines, SIMD optimization, or careful memory management — or when addressing performance…
qt-cpp-docs
Generates standalone Markdown reference documentation for any Qt/C++ source files — Qt Widgets classes, Qt Quick backends, Qt/C++ modules, plain C++ utilities, structs, free-function headers, and entry points like main.cpp. Use this skill to document any .h or .cpp file: Qt classes, plain C++ code, utility helpers, or…
cpu-kernels
Provides guidance for writing, optimizing, and benchmarking C++ CPU kernels with SIMD intrinsics (AVX2/AVX512) for the Hugging Face kernels ecosystem. Includes a two-phase workflow: Phase 1 correctness (generic → AVX2) and Phase 2 performance exploration (AVX512 with branching trial loop), runtime CPU dispatch, OpenMP…
implementing-jsc-classes-cpp
Implements JavaScript classes in C++ using JavaScriptCore. Use when creating new JS classes with C++ bindings, prototypes, or constructors.