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 gmh5225/awesome-llvm-security --skill llvm-toolinggit clone --depth 1 https://github.com/gmh5225/awesome-llvm-securityWrote 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/gmh5225/awesome-llvm-security/llvm-tooling)<a href="https://agentmods.dev/skills/gmh5225/awesome-llvm-security/llvm-tooling"><img src="https://agentmods.dev/badge/skills/gmh5225/awesome-llvm-security/llvm-tooling/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/gmh5225/awesome-llvm-security/llvm-tooling"><img src="https://agentmods.dev/badge/skills/gmh5225/awesome-llvm-security/llvm-tooling.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00052 | $0.01997 |
| Opus 5 | $0.00026 | $0.00999 |
| Sonnet 5 | $0.00010 | $0.00399 |
| Haiku 4.5 | $0.00005 | $0.00200 |
Grade A, and why
llvm-tooling 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 10d 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 — 309 lines — stays where its author put it; the contents beside it link to each section on GitHub.
LLVM Tooling Skill
This skill covers development of tools using LLVM/Clang infrastructure for source code analysis, debugging, and IDE integration.
Clang Plugin Development
Plugin Architecture
Clang plugins are dynamically loaded libraries that extend Clang's functionality during compilation.
#include "clang/Frontend/FrontendPluginRegistry.h"
#include "clang/AST/ASTConsumer.h"
#include "clang/AST/RecursiveASTVisitor.h"
class MyVisitor : public clang::RecursiveASTVisitor<MyVisitor> {
public:
bool VisitFunctionDecl(clang::FunctionDecl *FD) {
llvm::outs() << "Found function: " << FD->getName() << "\n";
return true;
}
};
class MyConsumer : public clang::ASTConsumer {
MyVisitor Visitor;
public:
void HandleTranslationUnit(clang::ASTContext &Context) override {
Visitor.TraverseDecl(Context.getTranslationUnitDecl());
}
};
class MyPlugin : public clang::PluginASTAction {
protected:
std::unique_ptr<clang::ASTConsumer> CreateASTConsumer(
clang::CompilerInstance &CI, llvm::StringRef) override {
return std::make_unique<MyConsumer>();
}
bool ParseArgs(const clang::CompilerInstance &CI,
const std::vector<std::string> &args) override {
return true;
}
};
static clang::FrontendPluginRegistry::Add<MyPlugin>
X("my-plugin", "My custom plugin description");
Running Clang Plugins
# Build plugin
clang++ -shared -fPIC -o MyPlugin.so MyPlugin.cpp \
$(llvm-config --cxxflags --ldflags)
# Run plugin
clang -Xclang -load -Xclang ./MyPlugin.so \
-Xclang -plugin -Xclang my-plugin \
source.cpp
LibTooling
Standalone Tools
#include "clang/Tooling/CommonOptionsParser.h"
#include "clang/Tooling/Tooling.h"
#include "clang/ASTMatchers/ASTMatchFinder.h"
using namespace clang::tooling;
using namespace clang::ast_matchers;
// Define matcher
auto functionMatcher = functionDecl(hasName("targetFunction")).bind("func");
// Callback handler
class FunctionCallback : public MatchFinder::MatchCallback {
public:
void run(const MatchFinder::MatchResult &Result) override {
if (auto *FD = Result.Nodes.getNodeAs<FunctionDecl>("func")) {
llvm::outs() << "Found: " << FD->getQualifiedNameAsString() << "\n";
}
}
};
int main(int argc, const char **argv) {
auto ExpectedParser = CommonOptionsParser::create(argc, argv, MyCategory);
ClangTool Tool(ExpectedParser->getCompilations(),
ExpectedParser->getSourcePathList());
FunctionCallback Callback;
MatchFinder Finder;
Finder.addMatcher(functionMatcher, &Callback);
return Tool.run(newFrontendActionFactory(&Finder).get());
}
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.
- 10d ago First seen · 309 lines · 52 tokens per session scan A 382d6821ce25
llvm-tooling is a skill published in the GitHub repository gmh5225/awesome-llvm-security (880 stars, last pushed 26d ago), licensed MIT. It adds 52 tokens to every session and 1,997 once invoked, about $0.0003 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.
Other skills, from other repositories
Deobfuscation
Systematic binary deobfuscation — string decryption, control flow flattening (CFF) removal, opaque predicate elimination, mixed boolean-arithmetic (MBA) simplification, bogus control flow, instruction substitution reversal, dead code removal, and anti-disassembly fixes. Trigger: deobfuscate, unobfuscate…
defeating-control-flow-flattening
Defeats control-flow-flattening obfuscation by identifying the dispatcher/state- variable structure and reconstructing the original control flow so the logic becomes readable. Activates for requests to defeat control-flow flattening, deobfuscate an OLLVM-flattened function, or recover original control flow from a…
stop-chasing-the-optimizer-reduce-instead
After two failed anti-optimization patches, stop and reduce; don't keep bolting on volatile / noinline.
debug-optimize-lcp
Guides debugging and optimizing Largest Contentful Paint (LCP) using Chrome DevTools MCP tools. Use this skill whenever the user asks about LCP performance, slow page loads, Core Web Vitals optimization, or wants to understand why their page's main content takes too long to appear. Also use when the user mentions…
systematic-debugging
Use when debugging a failing test, build error, or runtime issue that isn't immediately obvious. Guides a 4-phase root cause analysis instead of random fix attempts.
diagnose
Trace from a reproduced symptom to the source code that causes it. Pin the specific file and approximate line, rate confidence in the cause and clarity of the fix independently, and always propose a concrete fix.