code-generation-and-backends

code-generation-and-backends is a skill for Codex from OutlineDriven/outline-driven-development. It costs 42 tokens per session (1,586 once invoked), scanned A, original, Apache-2.0.

A guide to how LLVM turns intermediate code into machine instructions for a target processor. LLVM is a compiler framework; its intermediate representation is a portable form of code used between the source program and the final assembly.

In plain words
What is it for?
Use it to trace instruction selection and legalization, inspect compiler output, diagnose llc failures, or plan support for a new processor target.
Why use it?
It helps locate failures or unexpected instructions in the stages between LLVM IR and assembly. It also explains differences between outputs from tools such as llc and Clang.

Skill for Codex

Written for Codex: agents/openai.yaml present.

Good fit Use it to trace instruction selection and legalization, inspect compiler output, diagnose llc failures, or plan support for a new processor target.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/outlinedriven/outline-driven-development/code-generation-and-backends
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 OutlineDriven/outline-driven-development --skill code-generation-and-backends
Clone the repo
git clone --depth 1 https://github.com/OutlineDriven/outline-driven-development

Made for: 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 code-generation-and-backends

README.md
[![agentmods](https://agentmods.dev/badge/skills/outlinedriven/outline-driven-development/code-generation-and-backends/github.svg)](https://agentmods.dev/skills/outlinedriven/outline-driven-development/code-generation-and-backends)
Your own site
<a href="https://agentmods.dev/skills/outlinedriven/outline-driven-development/code-generation-and-backends"><img src="https://agentmods.dev/badge/skills/outlinedriven/outline-driven-development/code-generation-and-backends/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 code-generation-and-backends

Your own site · 80×15
<a href="https://agentmods.dev/skills/outlinedriven/outline-driven-development/code-generation-and-backends"><img src="https://agentmods.dev/badge/skills/outlinedriven/outline-driven-development/code-generation-and-backends.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 42 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,586 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 $0.00042 $0.01586
Opus 5 $0.00021 $0.00793
Sonnet 5 $0.00008 $0.00317
Haiku 4.5 $0.00004 $0.00159

Measured 3d ago against content hash caa974eeeb61, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

code-generation-and-backends 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.

.devin/skills/code-generation-and-backends/SKILL.md · 62 lines

How it starts

The opening of the file, as written. The whole thing — 62 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Code generation and backends

Contract

Field Bound contract
Trigger A user asks how LLVM IR becomes machine code for a target, why the legalizer inserted extra operations, why llc and clang emit different assembly, what an llc fatal error at instruction selection means, or what a port to a new architecture involves.
Authority Reversible local: writes only bitcode and assembly files under a scratch directory named in the report; rollback is deleting that directory. No remote mutation.
Side effect Runs clang and llc on the supplied source or bitcode and reads the emitted assembly. Project files are not modified.
Done A codegen report names the stage that produced each observed instruction sequence or failure, the triple and feature set in effect, and the fix or expansion path for every failure.

Inputs

  1. Source file, LLVM IR (.ll), or bitcode (.bc) (required).
  2. Target triple and CPU features (required if not inferrable from the build): for example aarch64-linux-gnu, riscv64-unknown-elf, thumbv7em-none-eabi with +neon or +crc.
  3. The observed symptom (required): the assembly region, the llc error text, or the question about the pipeline.
  4. Installed LLVM version (llc --version) (gathered by the skill). Grounded current stable is LLVM 23.1.0; tool flags below are confirmed against that release.

Procedure

  1. Map the question onto the backend pipeline. Per function, LLVM runs: IR legalization of types and operations the target lacks; SelectionDAGBuilder; LegalizeTypes and LegalizeOps; instruction selection by TableGen pattern match; pre-register-allocation scheduling; register allocation; prolog and epilog insertion; AsmPrinter to assembly or object. Name the stage the symptom belongs to. Done when: one stage is named as the owner of the symptom.

  2. Reproduce with llc in a scratch directory, with the same triple the build uses:

    clang -c -emit-llvm -O2 -o foo.bc foo.c
    llc -mtriple=aarch64-linux-gnu -O2 foo.bc -o foo.s
    llc -mtriple=riscv64-unknown-elf -O2 foo.bc -o foo-rv.s
    llc -mtriple=thumbv7em-none-eabi -mattr=+dsp foo.bc -o foo-m7.s
    

Read the full file on GitHub · 62 lines

Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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 · 62 lines · 42 tokens per session scan A caa974eeeb61

Subscribe to this mod's changes

code-generation-and-backends is a skill published in the GitHub repository OutlineDriven/outline-driven-development (52 stars, last pushed 4d ago), licensed Apache-2.0. It adds 42 tokens to every session and 1,586 once invoked, about $0.0002 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 2026-09-06.

Related

Other skills, from other repositories

bounded-model-checking-c

Use when C or C++ code needs memory-safety or undefined-behavior guarantees proved with CBMC, or ACSL contracts checked with Frama-C Eva or WP. Not for choosing the proof policy: use proof-driven.

OutlineDriven/odin-claude-plugin · 52 tokens

cpp-modules

C++20 modules skill for modern C++ projects. Use when working with named modules, module partitions, header units, CMake MODULESOURCES, Clang -fmodules-ts, BMI caching issues, or migrating from headers to modules. Activates on queries about C++20 modules, import statements, module interface units, header units, or BMI…

mohitmishra786/low-level-dev-skills · 76 tokens

openmp

OpenMP skill for shared-memory parallel programming. Use when writing parallel for loops, reductions, task parallelism, SIMD directives, GPU offloading, or profiling with Score-P/TAU. Activates on queries about OpenMP, pragma omp, schedule static dynamic, reduction, false sharing, or OMPNUMTHREADS.

mohitmishra786/low-level-dev-skills · 67 tokens

xmake-targets

Use when configuring targets in xmake.lua — setting kind (binary/static/shared), adding files/includes/links, defining dependencies between targets, and applying per-target compile/link flags.

xmake-io/xmake-skills · 40 tokens

cpp

Use when writing modern C++ (17/20/23). Covers RAII, smart-pointer ownership, move semantics, ranges, concepts, and eliminating undefined behavior with sanitizers.

nimadorostkar/Claude-Skills-collection · 38 tokens

arduino-code-generator

Generate Arduino and embedded C++ snippets for sensors, actuators, buses, state machines, timing, data logging, and hardware abstraction. Use when a user requests implementation code and provide the exact board, framework, toolchain, pins, voltage, memory, and library versions first. Bundled templates target UNO…

wedsamuel1230/arduino-skills · 86 tokens