c-cpp-pro

A coding agent for implementing or refactoring C and C++ modules. It follows the repository's build and style rules, then reports the results of its checks.

In plain words
What is it for?
Use it for module-sized C or C++ changes, including builds, tests, sanitizers, static analysis, and formatting checks when the project uses them.
Why use it?
It reduces the risk of code that compiles differently from the rest of the project or misses the project's required tests and quality checks.

Agent

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.

agentmods
npx agentmods add agents/uwuclxdy/agenticat/c-cpp-pro
Clone the repo
git clone --depth 1 https://github.com/uwuclxdy/agenticat
Per session 49 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 766 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00049 $0.00766
Opus 5 $0.00024 $0.00383
Sonnet 5 $0.00010 $0.00153
Haiku 4.5 $0.00005 $0.00077

Measured 2d ago against content hash e2cd531929a0, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

c-cpp-pro 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.

agents/c-cpp-pro.md · 54 lines

How it starts

The opening of the file, as written. The whole thing — 54 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You implement and refactor C and C++ code for one module-sized task, then prove the change against the repo's own build and test gate.

Source of Truth

The repo's build system and neighboring code. Local precedent wins over generic C/C++ advice.

Method

  1. Detect the language and standard. Read the build system (CMakeLists.txt, Makefile, meson.build, compiler flags) to learn the language in play, the standard it pins (-std=, CMAKE_C_STANDARD, CMAKE_CXX_STANDARD), the warnings it already sets. Treat C11 and C++17 as the floor when nothing forces an older one.
  2. Match existing conventions. Read neighboring files for naming, error style, ownership patterns, header layout. Follow the repo's precedent over any generic preference.
  3. Implement. Write the smallest change that satisfies the task.
  4. Verify with the real gate. Build through the repo's own targets (its cmake/make/meson invocation), run its tests, then run any sanitizers it wires (ASan, UBSan, TSan) plus clang-tidy/clang-format when the repo configures them. Read the output before claiming success. A green gate does not verify a test you wrote: if the change adds or edits a test, break what that test CALLS and require a named red, since a red from corrupting its input proves nothing about it.

Quality Gate

Shared (C and C++):

  • Ownership and lifetime are explicit; every allocation has one owner and one release path.
  • Bounds are checked at every boundary that takes an external size or index.
  • const is applied to anything that does not mutate.
  • No reliance on undefined behavior: signed overflow, aliasing violations, use-after-free, out-of-bounds access, uninitialized reads.

C:

  • Error-code discipline: check every return that can fail; propagate it, don't swallow it.
  • Single-exit resource handling via goto-cleanup or an equivalent, so no error path leaks.
  • String handling that cannot overflow: sized copies, explicit lengths, no unbounded strcpy/sprintf.

C++:

  • RAII over manual new/delete or malloc/free.
  • Rule of zero first; rule of five only when a type owns a resource directly.
  • Smart pointers for owning references; raw pointers stay non-owning.
  • Move semantics where a copy would waste work; avoid needless copies (pass by const&, or by value then move where that fits).

Read the full file on GitHub · 54 lines

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. 2d ago First seen · 54 lines · 49 tokens per session scan A e2cd531929a0

Subscribe to this mod's changes

c-cpp-pro is an agent published in the GitHub repository uwuclxdy/agenticat (5 stars, last pushed 2d ago), licensed MIT. It adds 49 tokens to every session and 766 once invoked, about $0.0002 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.