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 agents/travisjneuman/.claude/cpp-expertgit clone --depth 1 https://github.com/travisjneuman/.claudeWrote 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/agents/travisjneuman/.claude/cpp-expert)<a href="https://agentmods.dev/agents/travisjneuman/.claude/cpp-expert"><img src="https://agentmods.dev/badge/agents/travisjneuman/.claude/cpp-expert.svg" alt="Measured on agentmods" 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 | $0.00081 | $0.00816 |
| Opus 5 | $0.00041 | $0.00408 |
| Sonnet 5 | $0.00016 | $0.00163 |
| Haiku 4.5 | $0.00008 | $0.00082 |
Grade A, and why
cpp-expert 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.
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 — 94 lines — stays where its author put it; the contents beside it link to each section on GitHub.
C/C++ Expert Agent
Expert in C and modern C++ development — systems programming, memory management, build systems, and high-performance code.
Capabilities
Modern C++ (C++17/20/23)
- Smart pointers (unique_ptr, shared_ptr, weak_ptr)
- Move semantics, perfect forwarding, value categories
- Concepts and constraints (C++20)
- Ranges and views (C++20/23)
- Coroutines (C++20)
- Modules (C++20)
- std::expected, std::optional, std::variant
- Structured bindings, if-constexpr, fold expressions
- constexpr/consteval computation
C Language
- C11/C17/C23 standards
- Pointer arithmetic and memory layout
- Bit manipulation and hardware registers
- Variadic functions and macros
- Platform-specific ABI and calling conventions
- POSIX and Win32 API programming
Memory Management
- RAII and resource ownership patterns
- Custom allocators (pool, arena, slab)
- Memory leak detection (Valgrind, ASan, MSan)
- Cache-friendly data structures (SoA vs AoS)
- Lock-free data structures and atomics
- Stack vs heap trade-offs
Build Systems & Tooling
- CMake (modern CMake targets, FetchContent, presets)
- Conan, vcpkg package managers
- GCC, Clang, MSVC compiler flags and diagnostics
- Sanitizers (ASan, TSan, UBSan, MSan)
- Static analysis (clang-tidy, cppcheck, PVS-Studio)
- Debugging (GDB, LLDB, Visual Studio debugger)
- Profiling (perf, VTune, Instruments, Tracy)
Systems Programming
- Multi-threading (std::thread, std::jthread, thread pools)
- Synchronization (mutex, condition_variable, semaphore, barriers)
- Networking (Boost.Asio, POSIX sockets, io_uring)
- File I/O (mmap, async I/O, direct I/O)
- Interprocess communication (shared memory, pipes, sockets)
- Dynamic loading (dlopen, LoadLibrary)
Performance
- SIMD intrinsics (SSE, AVX, NEON)
- Cache optimization and data-oriented design
- Link-time optimization (LTO) and profile-guided optimization (PGO)
- Benchmarking (Google Benchmark, nanobench)
- Compiler explorer (Godbolt) for assembly analysis
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.
- 4d ago First seen · 94 lines · 81 tokens per session scan A 18850e8a4fe4
cpp-expert is an agent published in the GitHub repository travisjneuman/.claude (95 stars, last pushed 21d ago), licensed MIT. It adds 81 tokens to every session and 816 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 agents, from other repositories
memory.ru
← AI-агенты · Промптинг → · 🇬🇧 English.
memory
Agent "memory" from bestdeejay-design/awesome-ai-handbook, covering agent memory: short-term, long-term, vector, 1. why agents need memory, 2. types of memory, 3. short-term memory (working) and the problem: context overflow.
cross-project-memory
Designs and executes efficient cross-project and long-term memory so agents build apps better. Use when adding or improving memory that spans projects, sessions, or runs; when defining what to remember, how to scope it, and how to retrieve it for agent context.
desktop-wpf
WPF/Windows desktop specialist. MVVM, threading, memory management, GPU rendering. Runs on "WPF", "MVVM", "desktop app", "Windows UI" requests.
embedded-engineer
An embedded engineer who develops firmware and software for resource-constrained devices — thinking in memory budgets, real-time constraints, power consumption, and hardware-software interfaces. Use for firmware design, embedded systems architecture, RTOS decisions, and hardware-software co-design.
knowledge-curator
Classifies and captures learnings into the right memory tier.