codegen-validation

A testing method for compiler backends and assemblers that runs generated machine code on a real CPU or fast emulator and checks the result.

In plain words
What is it for?
It helps validate new code-generation targets, instruction selection, calling conventions, stack frames, register spilling, relocations, and optimization passes.
Why use it?
Assembly can look correct while containing hidden calling-convention, register, or stack errors. Running code with known answers exposes these mistakes.

Skill for Claude CodeCodex

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.

agentmods
npx agentmods add skills/midstall/claude-for-hardware/codegen-validation
Any agent
npx skills add Midstall/claude-for-hardware --skill codegen-validation
Clone the repo
git clone --depth 1 https://github.com/Midstall/claude-for-hardware

Made for: Claude Code, Codex.

Per session 46 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 891 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00046 $0.00891
Opus 5 $0.00023 $0.00445
Sonnet 5 $0.00009 $0.00178
Haiku 4.5 $0.00005 $0.00089

Measured 2d ago against content hash 71656d328d04, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

codegen-validation 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 2d 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/codegen-validation/SKILL.md · 74 lines

How it starts

The opening of the file, as written. The whole thing — 74 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Codegen Validation

Overview

A codegen backend is correct when the code it emits computes the right answer on a real machine. Reading the assembly proves nothing; a plausible-looking instruction sequence with a wrong ABI detail or a clobbered callee-saved register passes every eyeball review and fails on hardware.

Core principle: Execution-validate. Compile a known program, run the output on a real CPU or a fast emulator, and assert the observed result. If you didn't run it, you don't know it works.

When to Use

  • Bringing up a new codegen target or instruction selection
  • Implementing calling conventions, stack frames, register spilling, relocations
  • Debugging "the assembly looks right but the answer is wrong"
  • Adding an optimization pass and needing to prove it preserves behavior

The Validation Loop

known program (expected result known)
   -> codegen -> machine code
   -> run on real CPU / fast emulator
   -> assert observed result == expected
  • Pick programs with known answers. Start tiny: return a constant, add two args, a call to a leaf function, a loop that sums. Each isolates one capability (literals, ABI, calls, control flow).
  • Run on something real and fast. A native emulator for your target CPU closes the loop in milliseconds, so it can run on every build. The point is real execution semantics, not a model of what you think the instruction does.
  • Assert the observed value, not "it didn't crash." Read the result register or memory and compare to the expected answer.

This Catches Bugs Review Misses

Execution validation reliably catches the codegen bugs that look fine on paper:

  • A select/conditional-move lowering that picks the wrong operand.
  • Critical-edge splitting that drops or duplicates a value.
  • A prologue/epilogue that fails to save/restore a callee-saved register (return-address corruption shows up only when something actually calls).
  • ABI mistakes: argument in the wrong register, stack misaligned, return value in the wrong place.
  • Relocations that resolve to the wrong address.

Read the full file on GitHub · 74 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. 2d ago First seen · 74 lines · 46 tokens per session scan A 71656d328d04

Subscribe to this mod's changes

codegen-validation is a skill published in the GitHub repository Midstall/claude-for-hardware (18 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 46 tokens to every session and 891 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 2026-08-30.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

brainstorming

You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.

obra/superpowers · 37 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens

agent-host-chat-contributions

Build and review cross-cutting agent-host chat behavior through lifecycle contributions. Use when adding turn lifecycle side effects, prompt or context injection, restored-history transformation, protocol-action observation, or when reviewing changes that add code to AgentSideEffects or AgentService.

microsoft/vscode · 56 tokens

auto-perf-optimize

Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.

microsoft/vscode · 62 tokens