llvm-passes

llvm-passes is a skill for Claude Code, Codex from mohitmishra786/low-level-dev-skills. It costs 67 tokens per session (1,744 once invoked), scanned A, original, MIT.

A guide to LLVM passes, which are compiler steps that analyze or change a program's internal representation. It focuses on writing C++ optimization passes and connecting them to LLVM's newer pass system.

In plain words
What is it for?
Use it to write function- or module-level optimizations, register a pass plugin, run it with opt, use analyses such as loop information, test with llvm-lit and FileCheck, or debug changed IR.
Why use it?
It provides the structure and commands needed to build, register, run, test, and debug custom compiler transformations. This avoids common mistakes in pass ordering, analysis use, and generated output.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is opt -load-pass-plugin ./build/MyPass.so -passes=my-pass -S input.ll -o output.ll.

Good fit Use it to write function- or module-level optimizations, register a pass plugin, run it with opt, use analyses such as loop information, test with llvm-lit and FileCheck, or debug changed IR.

Compare 6 skills from other repositories ↓
Install

Getting it into your agent

It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.

Clone the repo
git clone --depth 1 https://github.com/mohitmishra786/low-level-dev-skills
agentmods
npx agentmods add skills/mohitmishra786/low-level-dev-skills/llvm-passes

Made for: Claude Code, Codex.

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-passes

README.md
[![agentmods](https://agentmods.dev/badge/skills/mohitmishra786/low-level-dev-skills/llvm-passes/github.svg)](https://agentmods.dev/skills/mohitmishra786/low-level-dev-skills/llvm-passes)
Your own site
<a href="https://agentmods.dev/skills/mohitmishra786/low-level-dev-skills/llvm-passes"><img src="https://agentmods.dev/badge/skills/mohitmishra786/low-level-dev-skills/llvm-passes/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-passes

Your own site · 80×15
<a href="https://agentmods.dev/skills/mohitmishra786/low-level-dev-skills/llvm-passes"><img src="https://agentmods.dev/badge/skills/mohitmishra786/low-level-dev-skills/llvm-passes.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 67 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,744 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 $0.00067 $0.01744
Opus 5 $0.00034 $0.00872
Sonnet 5 $0.00013 $0.00349
Haiku 4.5 $0.00007 $0.00174

Measured 11d ago against content hash d2b69a67c395, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

llvm-passes 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 11d 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.

skills/compiler-internals/llvm-passes/SKILL.md · 240 lines

How it starts

The opening of the file, as written. The whole thing — 240 lines — stays where its author put it; the contents beside it link to each section on GitHub.

LLVM Passes

Purpose

Guide agents through writing LLVM optimization passes with the New Pass Manager: FunctionPass and ModulePass structure, PassPluginLibraryInfo registration, running via opt -load-pass-plugin, common analysis utilities (DominatorTree, LoopInfo, AliasAnalysis), IR modification patterns, llvm-lit testing, and debugging with opt -print-after-all.

When to Use

  • Adding a custom optimization to an LLVM-based compiler
  • Writing an IR transformation pass (inlining, DCE, custom lowering)
  • Analyzing control flow with dominator trees or loop info
  • Testing passes with FileCheck and llvm-lit
  • Debugging pass ordering and IR corruption
  • Integrating passes into Clang via plugin

Workflow

1. New Pass Manager architecture

opt / clang
├── ModulePassManager
│   └── FunctionPassManager (per function)
│       └── FunctionPass instances
└── AnalysisManager (cached analyses)

Passes declare analysis usage; analyses are invalidated on IR mutation.

2. Minimal FunctionPass (C++ plugin)

// MyPass.cpp
#include "llvm/IR/PassManager.h"
#include "llvm/Passes/PassBuilder.h"
#include "llvm/Passes/PassPlugin.h"
#include "llvm/Support/raw_ostream.h"

using namespace llvm;

namespace {

struct MyPass : PassInfoMixin<MyPass> {
    PreservedAnalyses run(Function &F, FunctionAnalysisManager &AM) {
        bool changed = false;
        for (BasicBlock &BB : F) {
            for (Instruction &I : BB) {
                if (auto *Call = dyn_cast<CallInst>(&I)) {
                    if (Call->getCalledFunction() &&
                        Call->getCalledFunction()->getName() == "dead_func") {
                        Call->eraseFromParent();
                        changed = true;
                    }
                }
            }
        }
        return changed ? PreservedAnalyses::none() : PreservedAnalyses::all();
    }
};

} // namespace

extern "C" LLVM_ATTRIBUTE_WEAK PassPluginLibraryInfo llvmGetPassPluginInfo() {
    return {
        LLVM_PLUGIN_API_VERSION, "MyPass", "v0.1",
        [](PassBuilder &PB) {
            PB.registerPipelineParsingCallback(
                [](StringRef Name, FunctionPassManager &FPM,
                   ArrayRef<PassBuilder::PipelineElement>) {
                    if (Name == "my-pass") {
                        FPM.addPass(MyPass());
                        return true;
                    }
                    return false;
                });
        }
    };
}

Read the full file on GitHub · 240 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. 11d ago First seen · 240 lines · 67 tokens per session scan A d2b69a67c395

Subscribe to this mod's changes

llvm-passes is a skill published in the GitHub repository mohitmishra786/low-level-dev-skills (202 stars, last pushed 2mo ago), licensed MIT. It adds 67 tokens to every session and 1,744 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

header-only-c-cpp-ingestion

How autonomous agents inspect .h/.hpp header files first to understand class contracts and struct layouts before reading heavy .cpp implementation files, slashing C++ context token spend by 85%.

alivirgo/Major-AI-Skills · 45 tokens

zoom-meeting-sdk-unreal

Zoom Meeting SDK for Unreal Engine wrapper integrations. Use when building Unreal projects that embed Zoom meetings with C++ and Blueprint wrappers, including wrapper-to-SDK mapping concerns.

anthropics/knowledge-work-plugins · 41 tokens

embedded-stm32

Best practices for embedded C/C++ development on STM32 microcontrollers using the HAL, covering peripherals, DMA, interrupts, memory constraints, and hardware-focused testing. Use when writing STM32 HAL code, configuring peripherals generated by STM32CubeMX, working with interrupts or DMA, debugging with SWD/JTAG…

Mindrally/skills · 87 tokens

carbon-lang

Use when evaluating Carbon for a C++ code base, running the carbon toolchain from a nightly or Bazel build, or comparing Carbon with staying on C++. Not for C++ modules: use cpp-modules.

OutlineDriven/outline-driven-development · 46 tokens

abi-and-calling-conventions

Use when explaining System V AMD64, ARM AAPCS, RISC-V psABI, stack frames, variadic calls, or FFI register rules. Not for the Rust FFI binding layer: use rust-ffi.

OutlineDriven/outline-driven-development · 53 tokens

acad-arx-wizard

Agentic ObjectARX project scaffolding for AutoCAD 2027 / Visual Studio 2026. Replaces the broken .vsz VsWizardEngine wizard with a PowerShell script that generates identical C++ project files. Works for new ARX/DBX/CRX projects and add-on class wizards (Jig, Reactors, Custom Object, MFC, .NET Wrapper, COM Wrapper…

autodesk-platform-services/skills · 92 tokens