llvm-tooling

llvm-tooling is a skill for Claude Code from gmh5225/awesome-llvm-security. It costs 52 tokens per session (1,997 once invoked), scanned A, original, MIT.

A set of methods for building tools with LLVM, Clang, and related developer tools. Clang is a compiler; LLDB is a debugger; Clangd provides code intelligence to editors; and LibTooling helps inspect or change source code.

In plain words
What is it for?
Use it to create Clang plugins, source analyzers, automated refactoring tools, LLDB debugger extensions, and editor integrations through Clangd or the language-server protocol.
Why use it?
It gives developers a way to extend compilation, debugging, source-code analysis, refactoring, and editor support. This avoids treating each tool as an unrelated system.

Skill for Claude Code

Written for Claude Code: installed under .claude/.

Good fit Use it to create Clang plugins, source analyzers, automated refactoring tools, LLDB debugger extensions, and editor integrations through Clangd or the language-server protocol.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/gmh5225/awesome-llvm-security/llvm-tooling
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.

Any agent
npx skills add gmh5225/awesome-llvm-security --skill llvm-tooling
Clone the repo
git clone --depth 1 https://github.com/gmh5225/awesome-llvm-security

Made for: Claude Code.

Wrote 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.

agentmods badge for llvm-tooling

README.md
[![agentmods](https://agentmods.dev/badge/skills/gmh5225/awesome-llvm-security/llvm-tooling/github.svg)](https://agentmods.dev/skills/gmh5225/awesome-llvm-security/llvm-tooling)
Your own site
<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.

agentmods 80×15 button for llvm-tooling

Your own site · 80×15
<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>
Per session 52 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,997 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 5.1 $0.00052 $0.01997
Opus 5 $0.00026 $0.00999
Sonnet 5 $0.00010 $0.00399
Haiku 4.5 $0.00005 $0.00200

Measured 10d ago against content hash 382d6821ce25, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

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.

.claude/skills/llvm-tooling/SKILL.md · 309 lines

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());
}

Read the full file on GitHub · 309 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. 10d ago First seen · 309 lines · 52 tokens per session scan A 382d6821ce25

Subscribe to this mod's changes

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.

Related

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…

buzzer-re/Rikugan · 114 tokens

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…

meltedinhex/analyst-ai-pack · 74 tokens

stop-chasing-the-optimizer-reduce-instead

After two failed anti-optimization patches, stop and reduce; don't keep bolting on volatile / noinline.

chen3feng/agent-skills · 36 tokens

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…

ChromeDevTools/chrome-devtools-mcp · 99 tokens

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.

open-metadata/OpenMetadata · 37 tokens

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.

emdash-cms/emdash · 43 tokens