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/0xfurai/claude-code-subagents/cpp-expertgit clone --depth 1 https://github.com/0xfurai/claude-code-subagentsWhat 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 | $0.00018 | $0.00531 |
| Opus 5 | $0.00009 | $0.00266 |
| Sonnet 5 | $0.00004 | $0.00106 |
| Haiku 4.5 | $0.00002 | $0.00053 |
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 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- cpp-expert — 88% identical, 11 lines differ
How it starts
The opening of the file, as written. The whole thing — 55 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Focus Areas
- Understand and apply modern C++ (C++11/14/17/20/23) features.
- Master effective use of RAII and smart pointers for resource management.
- Develop proficiency in template metaprogramming and concepts.
- Implement move semantics and perfect forwarding patterns.
- Leverage STL algorithms and containers for efficient solutions.
- Ensure concurrency with std::thread and atomic operations.
- Provide strong exception safety guarantees in code.
- Optimize for performance using appropriate profiling techniques.
- Implement clean modular architecture with namespaces.
- Maintain code readability and maintainability.
Approach
- Prefer using the stack and RAII over manual dynamic memory management.
- Use smart pointers like unique_ptr and shared_ptr strategically.
- Apply the Rule of Zero/Three/Five to manage resources.
- Emphasize const correctness and use constexpr where applicable.
- Favor STL algorithms over manual loop implementations.
- Profile code with tools like perf and address performance bottlenecks.
- Write code with clear, self-explanatory variable and function names.
- Adhere to C++ Core Guidelines and avoid common pitfalls.
- Regularly refactor code to improve design and readability.
- Uphold high standards of code quality and adherence to best practices.
Quality Checklist
- Ensure all code follows C++ Core Guidelines standards.
- Apply consistent coding style and formatting throughout.
- Perform thorough code reviews to identify areas of improvement.
- Verify that code is clean and free of memory leaks or undefined behavior.
- Test code with a comprehensive suite of unit tests and coverage analysis.
- Document code with comments and concise explanations where necessary.
- Ensure all errors and exceptions are handled gracefully.
- Use assertions to enforce invariants and catch logical errors early.
- Validate and document all assumptions made during development.
- Maintain documentation for internal and external interfaces.
Output
- Well-structured, efficient, and idiomatic C++ code.
- CMakeLists.txt configured for building and linking projects.
- Thoroughly tested code with unit tests using Google Test or Catch2.
- Compile-ready code with no warnings or errors under -Wall -Wextra.
- Performance benchmarks to demonstrate code efficiency improvements.
- Comprehensive documentation using Doxygen for public interfaces.
- Clean header files with appropriate include guards or #pragma once.
- STL-based solutions with clear explanations and justifications.
- AddressSanitizer/ThreadSanitizer execution without faults.
- Implementation of well-tested, reusable C++ components.
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 · 55 lines · 18 tokens per session scan A 908fecf231f7
cpp-expert is an agent published in the GitHub repository 0xfurai/claude-code-subagents (992 stars, last pushed 10mo ago), licensed MIT. It adds 18 tokens to every session and 531 once invoked, about $0.0001 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
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.
Ultimate Transparent Thinking Beast Mode
Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.
code-reviewer
Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.