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 iliaal/whetstone --skill ia-cpp-systemsgit clone --depth 1 https://github.com/iliaal/whetstoneWrote 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/iliaal/whetstone/ia-cpp-systems)<a href="https://agentmods.dev/skills/iliaal/whetstone/ia-cpp-systems"><img src="https://agentmods.dev/badge/skills/iliaal/whetstone/ia-cpp-systems/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/iliaal/whetstone/ia-cpp-systems"><img src="https://agentmods.dev/badge/skills/iliaal/whetstone/ia-cpp-systems.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 | $0.00080 | $0.01289 |
| Opus 5.5 | $0.00032 | $0.00516 |
| Sonnet 5.5 | $0.00016 | $0.00258 |
| Haiku 4.5 | $0.00008 | $0.00129 |
Grade A, and why
ia-cpp-systems 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 11d 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.
This is a copy
92% identical to cpp-systems — 2 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 90 lines — stays where its author put it; the contents beside it link to each section on GitHub.
C++ Systems & Libraries
Covers C++17 as the baseline, with C++20 features called out where a project's standard allows them. For plain C (manual lifetimes, status enums, native extensions), see the ia-c-systems skill.
Working rules
- Make resource ownership explicit and use RAII for release on every exit path.
- Keep borrowed views within backing-storage lifetimes and review copy/move behavior when special members change.
- Follow the project's error model and supported language standard.
- Preserve ABI and avoid invoking unknown callbacks while holding locks or invalidatable container iterators.
Repo conventions outrank this skill
Check CMakeLists.txt for CXX_STANDARD, read .clang-format and .clang-tidy, and read two adjacent translation units before writing. Where they conflict with the rules below, they win.
The conflicts that actually happen:
| Local constraint | Consequence |
|---|---|
-fno-exceptions |
Error handling is codes or expected-alikes. Constructors cannot report recoverable failure, so use a fallible factory or construct a valid fallback state. new (std::nothrow) only where the project's OOM policy is to observe null and recover; plain new is fine where the policy is termination |
| Standard pinned below C++17 | No std::optional/string_view/structured bindings/if constexpr; check before using any |
| Public header is ABI-stable | No layout changes, no inline-function changes, no added virtuals: load the ABI reference |
| Embedded or freestanding target | No RTTI, no dynamic allocation in hot paths, possibly no STL containers |
Ownership and RAII
Every resource has exactly one owner, and that owner is an object whose destructor releases it. A raw new or delete in application code is a defect.
std::unique_ptr<T>for sole ownership. It is the default; it costs nothing over a raw pointer.std::shared_ptr<T>only where lifetime is genuinely shared and cannot be expressed as "the owner outlives the users". Reach for it third, not first.std::weak_ptr<T>to break ownership cycles. LeakSanitizer does report a cycle that is unreachable from any root, but not one still reachable from a global or other registered root, and detection varies by platform and configuration. Do not rely on the sanitizer to find these.- Raw
T*andT&mean non-owning observation, and are correct in that role. A parameter takingunique_ptrby value is announcing that it consumes ownership; one takingT*is announcing it does not. std::span<T>(C++20) or a pointer-plus-length pair for a borrowed contiguous range in a new public API, sinceconst std::vector<T>&there refuses every other container. On a C++17 baseline, or for internal code whose callers all hold vectors anyway,const std::vector<T>&is fine and simpler.
What ships with it
6 files 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.
- 11d ago Changed · +8 lines 88e00629a618
- 27d ago Changed 560aef94b2b7
- 1mo ago Changed · -66 lines 9d38c6c40239
- 1mo ago First seen · 148 lines · 80 tokens per session scan A 20a2d0abc5e4
ia-cpp-systems is a skill published in the GitHub repository iliaal/whetstone (35 stars, last pushed today), licensed MIT. It adds 80 tokens to every session and 1,289 once invoked, about $0.0003 per session on Opus 5.5. A static security scan graded it A with 0 findings. It is 92% identical to cpp-systems, differing in 2 lines, and is treated as a copy.
Other skills, from other repositories
agent-cpp-expert
Specialist subagent: C and C++ development, modern C++ (C++17/20/23), CMake, systems programming, and memory management specialist. Use when writing C/C++ code, debugging memory issues, or building systems-level software. Trigger phrases: C++, C language, CMake, modern C++, systems programming, memory management…
rubber-ducky
Use when you've planned a non-trivial change and are about to implement it, finished a complex or multi-file piece of work, just wrote tests, or are stuck on repeated failures — and any time the user says "rubber duck this", "rubber ducky", "get a second opinion", "sanity-check my plan", "poke holes in this", "what am…
project-setup
Setup and hardening review for cross-platform modern-C++ (C++17) native projects, especially Node.js addons built with node-gyp / node-addon-api. Use when asked to "set up a native addon", "harden a C/C++ build", "review my binding.gyp", "add compiler hardening flags", "wire up AddressSanitizer/UBSan/TSan/clang-tidy"…
lsp-investigate
Investigate code using LSP tools. Register a project, then use definitions, references, call hierarchies, type hierarchies, hover, and diagnostics to understand code structure, trace bugs, and assess change impact.
TypeScript Null Safety Guardrails
Enforce null/undefined safety for changed TypeScript code and suggest safer patterns.
TypeScript Strictness Guard
Enforce TypeScript strictness by reducing any/unsafe assertions and ensuring null handling.