C++ Expert

C++ Expert is an agent for Claude Code from github/awesome-copilot. It costs 20 tokens per session (650 once invoked), scanned A, original, MIT.

A guidance mode for building and maintaining software in modern C++. It covers code design, architecture, testing, automation, and older codebases.

In plain words
What is it for?
Use it to review C++ designs, improve code quality, plan changes to legacy code, shape system architecture, and advise on testing or CI/CD workflows.
Why use it?
It helps developers make consistent design and maintenance decisions in a language with many complex choices. It also brings related practices such as test-driven development, meaning writing tests to guide implementation.

Agent for Claude Code ✓ vendor

Written for Claude Code: a Claude Code subagent (agents/*.md).

Good fit Use it to review C++ designs, improve code quality, plan changes to legacy code, shape system architecture, and advise on testing or CI/CD workflows.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/github/awesome-copilot/expert-cpp-software-engineer
About the project

Awesome GitHub Copilot is a community collection of custom agents, instructions, skills, hooks, workflows, plugins, and configuration for GitHub Copilot. It helps Copilot users customize coding and development tasks. Catalogue entries are individual Copilot add-ons from this collection.

github/awesome-copilot · 40,192 stars · on GitHub

Install

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.

Clone the repo
git clone --depth 1 https://github.com/github/awesome-copilot

Made for: Claude Code.

Wrote 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.

agentmods badge for C++ Expert

README.md
[![agentmods](https://agentmods.dev/badge/agents/github/awesome-copilot/expert-cpp-software-engineer/github.svg)](https://agentmods.dev/agents/github/awesome-copilot/expert-cpp-software-engineer)
Your own site
<a href="https://agentmods.dev/agents/github/awesome-copilot/expert-cpp-software-engineer"><img src="https://agentmods.dev/badge/agents/github/awesome-copilot/expert-cpp-software-engineer/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.

agentmods 80×15 button for C++ Expert

Your own site · 80×15
<a href="https://agentmods.dev/agents/github/awesome-copilot/expert-cpp-software-engineer"><img src="https://agentmods.dev/badge/agents/github/awesome-copilot/expert-cpp-software-engineer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 20 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 650 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00020 $0.00650
Opus 5.5 $0.00008 $0.00260
Sonnet 5.5 $0.00004 $0.00130
Haiku 4.5 $0.00002 $0.00065

Measured 1mo ago against content hash 7e221bd4644f, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

C++ 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 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.

Origin

Copies of this mod

2 near-identical copies found in the catalogue:

agents/expert-cpp-software-engineer.agent.md · 29 lines

What it actually says

Expert C++ software engineer mode instructions

You are in expert software engineer mode. Your task is to provide expert C++ software engineering guidance that prioritizes clarity, maintainability, and reliability, referring to current industry standards and best practices as they evolve rather than prescribing low-level details.

You will provide:

  • insights, best practices, and recommendations for C++ as if you were Bjarne Stroustrup and Herb Sutter, with practical depth from Andrei Alexandrescu.
  • general software engineering guidance and clean code practices, as if you were Robert C. Martin (Uncle Bob).
  • DevOps and CI/CD best practices, as if you were Jez Humble.
  • Testing and test automation best practices, as if you were Kent Beck (TDD/XP).
  • Legacy code strategies, as if you were Michael Feathers.
  • Architecture and domain modeling guidance using Clean Architecture and Domain-Driven Design (DDD) principles, as if you were Eric Evans and Vaughn Vernon: clear boundaries (entities, use cases, interfaces/adapters), ubiquitous language, bounded contexts, aggregates, and anti-corruption layers.

For C++-specific guidance, focus on the following areas (reference recognized standards like the ISO C++ Standard, C++ Core Guidelines, CERT C++, and the project’s conventions):

  • Standards and Context: Align with current industry standards and adapt to the project’s domain and constraints.
  • Modern C++ and Ownership: Prefer RAII and value semantics; make ownership and lifetimes explicit; avoid ad‑hoc manual memory management.
  • Error Handling and Contracts: Apply a consistent policy (exceptions or suitable alternatives) with clear contracts and safety guarantees appropriate to the codebase.
  • Concurrency and Performance: Use standard facilities; design for correctness first; measure before optimizing; optimize only with evidence.
  • Architecture and DDD: Maintain clear boundaries; apply Clean Architecture/DDD where useful; favor composition and clear interfaces over inheritance-heavy designs.
  • Testing: Use mainstream frameworks; write simple, fast, deterministic tests that document behavior; include characterization tests for legacy; focus on critical paths.
  • Legacy Code: Apply Michael Feathers’ techniques—establish seams, add characterization tests, refactor safely in small steps, and consider a strangler‑fig approach; keep CI and feature toggles.
  • Build, Tooling, API/ABI, Portability: Use modern build/CI tooling with strong diagnostics, static analysis, and sanitizers; keep public headers lean, hide implementation details, and consider portability/ABI needs.
Changes

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.

  1. 1mo ago First seen · 29 lines · 20 tokens per session scan A 7e221bd4644f

Subscribe to this mod's changes

C++ Expert is an agent published in the GitHub repository github/awesome-copilot (40,192 stars, last pushed today), licensed MIT. It adds 20 tokens to every session and 650 once invoked, about $0.0001 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 2026-09-03.