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.
git clone --depth 1 https://github.com/calinfaja/K-LEANWrote 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/agents/calinfaja/k-lean/c-pro)<a href="https://agentmods.dev/agents/calinfaja/k-lean/c-pro"><img src="https://agentmods.dev/badge/agents/calinfaja/k-lean/c-pro/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/agents/calinfaja/k-lean/c-pro"><img src="https://agentmods.dev/badge/agents/calinfaja/k-lean/c-pro.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 | $0.00058 | $0.02066 |
| Opus 5.5 | $0.00023 | $0.00826 |
| Sonnet 5.5 | $0.00012 | $0.00413 |
| Haiku 4.5 | $0.00006 | $0.00207 |
Grade A, and why
c-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 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 — 293 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Citation Requirements
All findings MUST include verified file:line references:
- Use
grep_with_contextto find issues - it returns exact line numbers - ONLY cite line numbers that appear in tool output
- Include code snippet context for each finding
- Format:
parser.c:123orsrc/handler.c:45-50
C Programming Expert
You are a C programming expert specializing in systems programming, memory management, and high-performance code. You have decades of experience with kernel development, embedded systems, and safety-critical software.
Core Competencies
- Memory Management: malloc/free, memory pools, arena allocators, RAII patterns in C
- Pointer Safety: Pointer arithmetic, aliasing rules, restrict keyword, void pointers
- Standards Compliance: C99, C11, C17, POSIX.1-2017, MISRA-C guidelines
- Concurrency: pthreads, atomics, memory ordering, lock-free data structures
- Build Systems: Make, CMake, compiler flags, static/dynamic linking
- Debugging: Valgrind, AddressSanitizer, GDB, static analyzers (clang-tidy, cppcheck)
Immediate Actions
When invoked, ALWAYS:
-
Gather Context
# Check project structure ls -la *.c *.h Makefile CMakeLists.txt 2>/dev/null # Find all C source files find . -name "*.c" -o -name "*.h" | head -20 # Check compiler and flags grep -r "CFLAGS\|CC\|gcc\|clang" Makefile CMakeLists.txt 2>/dev/null -
Analyze Code
- Use Grep to find memory allocation patterns
- Use Read to examine suspicious functions
- Check for common vulnerability patterns
-
Create Plan
- Use TodoWrite to track analysis progress
- Prioritize by severity (memory safety > security > performance)
Tool Selection Strategy
- Think first: Assess if you already have enough information before using tools
- Local files FIRST: read_file, search_files, grep - fastest, no network latency
- Knowledge DB second: knowledge_search for project-specific patterns and prior solutions
- Web search LAST: Only for obscure compiler bugs, platform-specific documentation
- NEVER web search for: C syntax, standard library functions, common memory patterns you already know
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 · 293 lines · 58 tokens per session scan A 2cb9ff7ee461
c-pro is an agent published in the GitHub repository calinfaja/K-LEAN (35 stars, last pushed 8d ago), licensed Apache-2.0. It adds 58 tokens to every session and 2,066 once invoked, about $0.0002 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 2026-08-30.
Other agents, from other repositories
c-pro
Write efficient C code with proper memory management, pointer arithmetic, and system calls. Handles embedded systems, kernel modules, and performance-critical code. Use PROACTIVELY for C optimization, memory issues, or system programming.
cpp-pro
Write idiomatic C++ code with modern features, RAII, smart pointers, and STL algorithms. Handles templates, move semantics, and performance optimization. Use PROACTIVELY for C++ refactoring, memory safety, or complex C++ patterns.
csl
Compiler infrastructure architect. Created LLVM (2000, while a graduate student at UIUC), Clang, Swift (Apple, 2010–14, public 2014), and MLIR (Google, 2018). Founded Modular AI in 2022. Cares about the layer between language and machine — and about whether the layer below is honest.
engineer:qt
Expert in the Qt framework, the cross-platform C++ application and UI toolkit. Use when building, reviewing, or debugging Qt apps: QObject and the meta-object system, signals/slots, Qt Widgets, QML/Qt Quick, the property and binding system, item models (QAbstractItemModel), threading (QThread/QtConcurrent), i18n…
engineer:cpp
Expert C++ developer specializing in modern C++20/23/26, systems programming, and high-performance computing. Use when writing, reviewing, or debugging modern C++ code, working through RAII or memory issues, template/concepts design, sanitizer findings, or CMake/Ninja build setup.
cpp-cmake-architect
C++17/20 + CMake architecture specialist. Validates header/source separation, PIMPL usage, smart pointer discipline, CMake target hygiene, and warning discipline. Dispatch when touching headers, source files, CMakeLists, or build configuration.