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 danweinerdev/claude-sdd-planner --skill cpp-specificationsgit clone --depth 1 https://github.com/danweinerdev/claude-sdd-plannerWrote 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/danweinerdev/claude-sdd-planner/cpp-specifications)<a href="https://agentmods.dev/skills/danweinerdev/claude-sdd-planner/cpp-specifications"><img src="https://agentmods.dev/badge/skills/danweinerdev/claude-sdd-planner/cpp-specifications/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/danweinerdev/claude-sdd-planner/cpp-specifications"><img src="https://agentmods.dev/badge/skills/danweinerdev/claude-sdd-planner/cpp-specifications.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 | $0.00074 | $0.00964 |
| Opus 5.5 | $0.00030 | $0.00386 |
| Sonnet 5.5 | $0.00015 | $0.00193 |
| Haiku 4.5 | $0.00007 | $0.00096 |
Grade A, and why
cpp-specifications 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.
How it starts
The opening of the file, as written. The whole thing — 68 lines — stays where its author put it; the contents beside it link to each section on GitHub.
C / C++ — What Good Looks Like
Sanitizers
| Tool | When | What it catches |
|---|---|---|
| ASAN (AddressSanitizer) | Always | Buffer overflows, use-after-free, double-free, stack overflows |
| UBSAN (UndefinedBehaviorSanitizer) | Always | Signed integer overflow, null pointer dereference, misaligned access |
| TSAN (ThreadSanitizer) | Threads, atomics, shared mutable state | Data races, lock order violations |
| MSAN (MemorySanitizer) | When processing external/untrusted input | Use of uninitialized memory |
Minimum bar: ASAN + UBSAN on every phase. Add TSAN when concurrency is involved.
Build integration: Typically -fsanitize=address,undefined (Clang/GCC). TSAN and ASAN cannot run simultaneously — use separate build configs.
Const Correctness
- Parameters: primitives/enums by
constvalue (const int32_t size), complex types byconst&(const std::string& name) - Methods: mark non-mutating methods
const - Local variables: use
constfor anything that doesn't change after initialization - Calculations: assign intermediate results to named
constvariables rather than inlining expressions
Ownership & Memory
- Smart pointers over raw:
std::unique_ptrfor exclusive ownership,std::shared_ptronly when genuinely shared std::span<T>for non-owning sequences: prefer overconst std::vector<T>&for function parameters — decouples the interface from the container- No naked
new/delete: usestd::make_unique/std::make_shared - Move semantics: use
std::movewhen transferring ownership, don't copy when a move suffices
Return Values & Error Handling
[[nodiscard]]on all functions returning values — forces callers to handle the result- Result/Expected pattern over exceptions: if the project uses
Result<T>,std::expected, or similar — use it consistently. Don't mix with exceptions - No silent failure: every failable operation must return an error path the caller can observe
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.
- 1mo ago First seen · 68 lines · 74 tokens per session scan A 3a2b82fdccd0
cpp-specifications is a skill published in the GitHub repository danweinerdev/claude-sdd-planner (2 stars, last pushed 22d ago), licensed MIT. It adds 74 tokens to every session and 964 once invoked, about $0.0003 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 2026-08-31.
Other skills, from other repositories
clean-code-cpp
Use when writing or reviewing C++ code — deeper idioms beyond the basics (ownership, noexcept/constexpr discipline, span/stringview, error-handling policy, concrete-before-abstract).
clean-code-c
Use when writing or reviewing C — deeper idioms (ownership discipline, bounded string ops, allocation checking, linkage, initialization) beyond clang-tidy.
cpp-coding-standards
C++ coding standards based on the C++ Core Guidelines (isocpp.github.io). Use when writing, reviewing, or refactoring C++ code to enforce modern, safe, and idiomatic practices.
cpp-coding-standards
C++ coding standards based on the C++ Core Guidelines (isocpp.github.io). Use when writing, reviewing, or refactoring C++ code to enforce modern, safe, and idiomatic practices.
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…
moai-ref-cross-model-audit
Cross-model audit convergence reference for the plan-auditor and sync-auditor agents. Documents how to invoke the auditmulti MCP tool to fan a code review out across the Claude subscription, codex, and GLM (z.ai) backends, converge their independent verdicts, and fold the resulting per-backend verdicts + disagreement…