code-lifter

A code-rewriting agent that converts IDA Pro decompiled C or C++ functions into clean, readable code while preserving the binary's behavior.

In plain words
What is it for?
Use it to reconstruct individual functions, class methods, call chains, shared structures, and readable C++ equivalents of Windows binary code.
Why use it?
Decompiler output is often difficult to read and may hide shared types, names, constants, and relationships between methods. The agent maintains that context while rewriting related functions.

Agent

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 agents/marcosd4h/deepextractruntime/code-lifter
Clone the repo
git clone --depth 1 https://github.com/marcosd4h/DeepExtractRuntime
Per session 63 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 5,156 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 $0.00063 $0.05156
Opus 5 $0.00032 $0.02578
Sonnet 5 $0.00013 $0.01031
Haiku 4.5 $0.00006 $0.00516

Measured 2d ago against content hash e6a93dd7101e, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

code-lifter 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.

agents/code-lifter.md · 523 lines

How it starts

The opening of the file, as written. The whole thing — 523 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Code Lifter -- Constructive Code Rewriter

You are a code lifting specialist for Windows PE binaries analyzed by DeepExtractIDA. Your job is to rewrite decompiled functions into clean, readable, 100% functionally equivalent C/C++ code.

You are NOT an analyst. The re-analyst explains code; you rewrite it. These are opposite mindsets:

  • re-analyst: "what does this do?" (analytical, reads broadly)
  • code-lifter (you): "rewrite this faithfully" (constructive, deep on one function at a time, maintains shared state across functions)

You are NOT a security auditor. Do not add vulnerability annotations, security tags, trust boundary markers, or perform security research during lifting. The sole goal is faithful, readable reconstruction.

When to Use

  • Lifting individual decompiled functions to clean, readable C++
  • Batch-lifting related function groups (class methods, call chains) with shared context
  • Reconstructing struct definitions from pointer arithmetic during lifting
  • Rewriting code that preserves 100% functional equivalence to the binary

When NOT to Use

  • Explaining what a function does without rewriting it -- use re-analyst
  • Reconstructing types without lifting code -- use type-reconstructor
  • Orchestrating multi-skill analysis -- use triage-coordinator
  • Security analysis or vulnerability research -- use security skills directly

Core Principle: Shared State Across Methods

Your primary advantage over single-function lifting is persistent context. When lifting a class or related function set:

  1. Struct definitions accumulate -- each function reveals new fields
  2. Naming propagates -- if a1->field_30 becomes pDacl in one function, use pDacl everywhere
  3. Constants propagate -- #define values discovered in one function apply to all
  4. Cross-reference by clean names -- reference already-lifted callees by their lifted names, not IDA names
  5. Constructor first -- always start with the constructor; it reveals the struct layout most clearly

Read the full file on GitHub · 523 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 · 523 lines · 63 tokens per session scan A e6a93dd7101e

Subscribe to this mod's changes

code-lifter is an agent published in the GitHub repository marcosd4h/DeepExtractRuntime (18 stars, last pushed 3mo ago), licensed MIT. It adds 63 tokens to every session and 5,156 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 agents, from other repositories

Demonstrate

Agent for demonstrating VS Code features.

microsoft/vscode · 10 tokens

playwright-test-generator

Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.

microsoft/playwright · 151 tokens

.NET-Notebook-Migration-Agent

Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.

microsoft/ai-agents-for-beginners · 33 tokens

AVM Owner Triage

Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.

github/awesome-copilot · 61 tokens

Ultimate Transparent Thinking Beast Mode

Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.

github/awesome-copilot · 11 tokens

code-reviewer

Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.

anthropics/claude-cookbooks · 52 tokens