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 skills add Miaoge-Ge/coding-agent-skills --skill cpp-expertgit clone --depth 1 https://github.com/Miaoge-Ge/coding-agent-skillsWrote 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/miaoge-ge/coding-agent-skills/cpp-expert)<a href="https://agentmods.dev/skills/miaoge-ge/coding-agent-skills/cpp-expert"><img src="https://agentmods.dev/badge/skills/miaoge-ge/coding-agent-skills/cpp-expert/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/miaoge-ge/coding-agent-skills/cpp-expert"><img src="https://agentmods.dev/badge/skills/miaoge-ge/coding-agent-skills/cpp-expert.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 | $0.00098 | $0.01051 |
| Opus 5 | $0.00049 | $0.00526 |
| Sonnet 5 | $0.00020 | $0.00210 |
| Haiku 4.5 | $0.00010 | $0.00105 |
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 9d 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 — 85 lines — stays where its author put it; the contents beside it link to each section on GitHub.
C++ Expert
RAII owns every resource; values move, don't copy. Make ownership explicit, lean on the STL, and treat undefined behavior as a bug to prevent — not a surprise to debug.
When to Use
- Writing or reviewing C++.
- Modern features (C++17/20/23), templates/metaprogramming, STL.
- Performance/memory tuning; smart pointers and ownership.
- Compile errors, crashes, leaks, or undefined behavior (UB).
When NOT to Use
- Another language → relevant language skill.
- Contest algorithms (language incidental) →
competitive-programming-expert. - System/architecture design →
software-architect.
Core Principles
1. Modern by default
- Target C++17/20 unless constrained. Prefer
auto, range-basedfor, structured bindings,std::optional/variant/string_view/span. - Constrain templates with Concepts (C++20) or
static_assertso errors surface at the call site, not deep in instantiation.
2. Ownership & RAII
- No owning raw pointers.
std::unique_ptrfor sole ownership,shared_ptronly when ownership is genuinely shared; create withmake_unique/make_shared. Raw pointers/references are non-owning observers. - Every resource (memory, file, lock, socket) is owned by an object that releases it in its destructor. Locks via
std::scoped_lock/lock_guard. - Follow the Rule of 0 (no manual special members) — or Rule of 5 if you manage a resource directly.
3. Value semantics & performance
- Pass
const&for read-only, by value +std::moveto sink,string_view/spanfor non-owning views. Rely on (N)RVO — return by value. - Avoid premature
shared_ptr(atomic refcount cost) and needless copies;emplace_back,reserve. Choose containers deliberately (vectorby default).constexpr/constevalfor compile-time work. Profile before micro-optimizing.
4. Avoid UB proactively
- Dangling refs/views, use-after-move, out-of-bounds, signed overflow, uninitialized reads, iterator invalidation, data races. Build with warnings (
-Wall -Wextra), sanitizers (ASan/UBSan/TSan), and tools (clang-tidy).
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.
- 9d ago First seen · 85 lines · 98 tokens per session scan A 1de1bf2e5789
cpp-expert is a skill published in the GitHub repository Miaoge-Ge/coding-agent-skills (5 stars, last pushed 3mo ago), licensed MIT. It adds 98 tokens to every session and 1,051 once invoked, about $0.0005 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 2026-08-31.
Other skills, from other repositories
qt-cpp-review
Invoke when the user asks to review, check, audit, or look over Qt6 C++ code — or suggest before committing. Runs deterministic linting (60+ rules) then six parallel deep- analysis agents covering model contracts, ownership, threading, API correctness, error handling, and performance. Reports only high-confidence…
code-review-csharp
Perform structured code reviews of C# source code covering naming conventions, performance, security, readability, and .NET best practices. Trigger phrases include "review this C# code", "check my C# for best practices", "analyze this C# class", "find issues in my C# code".
unreal-live-coding
Trigger Live Coding compilation via UCP. Use when the user asks to recompile C++ code, trigger live coding, hot reload C++ changes, or check compilation status in Unreal Engine.
torchtalk-analyzer
Analyze PyTorch internals across Python, C++, and CUDA layers using the TorchTalk MCP server. Use when asked about how PyTorch operators work internally, where functions are implemented, what would break if code is modified, or finding tests for PyTorch operators.
torchtalk-trace
Trace a PyTorch function's cross-language binding chain (Python -> C++ -> CUDA).
audit
Audits recent work against its Definition of Done and project patterns. Runs the test suite, compares code against the spec, and reports PASS / PARTIAL / FAIL. Also runs the Critical Gate — a safety scan of the diff for destructive or dangerous operations. Generates an incremental prompt pack for any gaps found. With…