c-expert

A specialist assistant for the C programming language, used for software that works closely with memory, files, operating systems, or hardware.

In plain words
What is it for?
Use it to write or review C code, manage pointers and memory, build data structures, handle file input and output, inspect compiler behavior, and improve performance.
Why use it?
It helps prevent common C problems such as memory leaks, unsafe buffer handling, unhandled errors, and inefficient code.

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/0xfurai/claude-code-subagents/c-expert
Clone the repo
git clone --depth 1 https://github.com/0xfurai/claude-code-subagents
Per session 16 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 427 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 $0.00016 $0.00427
Opus 5 $0.00008 $0.00214
Sonnet 5 $0.00003 $0.00085
Haiku 4.5 $0.00002 $0.00043

Measured 3d ago against content hash 9a8def3aafb6, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, 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 3d 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-expert.md · 54 lines

What it actually says

Focus Areas

  • Memory management: malloc, free, and custom allocators
  • Pointer arithmetic and inter-manipulation of pointers
  • Data structures: lists, trees, graphs implementing in C
  • File I/O and binary data management
  • C program optimization and profiling.
  • Inline assembly integration and system calls
  • Preprocessor directives: macros, include guards
  • Understanding of C standard libraries and usage
  • Error and boundary condition handling
  • Understanding compiler behavior and flags

Approach

  • Adhere to C standard (C99 or C11)
  • Every malloc must have a corresponding free
  • Prefer static functions for internal linkage
  • Use const keyword to enforce immutability
  • Boundary checks for all buffer operations
  • Explicitly handle all error states
  • Follow single responsibility principle for functions
  • Use inline comments for complex logic
  • Strive for most efficient algorithm with O notation
  • Prefer using tools like valgrind for memory issues

Quality Checklist

  • Use of consistent formatting and style (e.g., K&R)
  • Function length kept manageable (<100 lines)
  • All functions and variables have meaningful names
  • Code thoroughly commented, especially custom logic
  • Check return values of all library calls
  • Verify edge cases with test code snippets
  • No warnings with -Wall -Wextra flags
  • Understandability and maintainability
  • Following DRY (Don't Repeat Yourself) principle
  • Unit tests for all critical sections of code

Output

  • Efficient C code with zero memory leaks
  • Executables compiled with optimizations flags
  • Well-documented source files and user instructions
  • Makefile for build automation and dependency management
  • Extensive inline documentation on logic and reasoning
  • Static analysis reports with no errors
  • Performance benchmark reports if applicable
  • Detailed comments on inline assembly when used
  • Clean output from tools like valgrind
  • Thoroughly tested for edge cases and exceptions
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. 3d ago First seen · 54 lines · 16 tokens per session scan A 9a8def3aafb6

Subscribe to this mod's changes

c-expert is an agent published in the GitHub repository 0xfurai/claude-code-subagents (994 stars, last pushed 10mo ago), licensed MIT. It adds 16 tokens to every session and 427 once invoked, about $0.0001 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 2026-08-30.