A reverse-engineering workflow for reconstructing related groups of decompiled functions—such as C++ class methods, call chains, or exported function trees—into coordinated C++ code.

Use it to reconstruct multiple related functions, discover their dependency order, share recovered structure definitions, and produce one cohesive source file.

It preserves shared context, including structures, constants, and dependencies, that can be lost when functions are reconstructed one at a time.

batch-lift — Skill for Claude Code and Codex by marcosd4h

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/marcosd4h/DeepExtractRuntime

agentmods

npx agentmods add skills/marcosd4h/deepextractruntime/batch-lift

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/marcosd4h/deepextractruntime/batch-lift/github.svg)](https://agentmods.dev/skills/marcosd4h/deepextractruntime/batch-lift)

Your own site

<a href="https://agentmods.dev/skills/marcosd4h/deepextractruntime/batch-lift"><img src="https://agentmods.dev/badge/skills/marcosd4h/deepextractruntime/batch-lift/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/marcosd4h/deepextractruntime/batch-lift"><img src="https://agentmods.dev/badge/skills/marcosd4h/deepextractruntime/batch-lift.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 84 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 3,876 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.

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.

Model	Per session	Once invoked
Fable 5.1	$0.00084	$0.03876
Opus 5.5	$0.00034	$0.01550
Sonnet 5.5	$0.00017	$0.00775
Haiku 4.5	$0.00008	$0.00388

Measured 2mo ago against content hash 2bf04005dd40, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

batch-lift 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 2mo ago.

The scan reads SKILL.md. This mod also ships 3 executable files (scripts/_common.py, scripts/collect_functions.py, scripts/prepare_batch_lift.py), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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/batch-lift/SKILL.md · 394 lines

How it starts

The opening of the file, as written. The whole thing — 394 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Batch / Contextual Code Lifting

Purpose

Lift related function groups together instead of one-at-a-time. Individual function lifting loses context -- struct definitions are incomplete, constants are defined in isolation, and cross-references between related functions are missed.

This skill orchestrates batch lifting by:

Collecting the right set of functions (class methods, call chains, export subtrees)
Building shared struct definitions accumulated across ALL functions in the set
Determining dependency order (lift callees before callers)
Generating a single cohesive .cpp output with constants, structs, and functions

Builds on: decompiled-code-extractor (function data extraction), code-lifting (per-function lifting workflow), callgraph-tracer (call chain discovery), reconstruct-types (struct scanning).

This is NOT security analysis. The goal is faithful, readable code reconstruction.

When NOT to Use

Lifting a single function in isolation -- use code-lifting or the code-lifter agent
Vulnerability scanning or security analysis of functions -- use ai-memory-corruption-scanner or ai-logic-scanner
Understanding what a function does without rewriting it -- use re-analyst or /explain
Reconstructing types without lifting code -- use reconstruct-types
Tracing call chains without lifting the functions -- use callgraph-tracer

Batch Lifting Modes

Mode	Trigger	What Gets Collected
Class methods	"Lift all methods of ClassName"	All methods by mangled name + signature references
Call chain	"Lift FuncX and everything it calls"	BFS from FuncX, N levels of internal calls
Export-down	"Lift from export X down 3 levels"	From named export, N levels of internal calls

Read the full file on GitHub · 394 lines

Files

What ships with it

5 files 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.

2mo ago First seen · 394 lines · 84 tokens per session scan A 2bf04005dd40

Subscribe to this mod's changes

batch-lift is a skill published in the GitHub repository marcosd4h/DeepExtractRuntime (21 stars, last pushed 2mo ago), licensed MIT. It adds 84 tokens to every session and 3,876 once invoked, about $0.0003 per session on Opus 5.5. 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.

Debugging

batch-lift next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
batch-liftmarcosd4h/DeepExtractRuntime	Skill	21	2mo ago	MIT	A	84	Claude Code, Codex
systematic-debuggingopen-metadata/OpenMetadata	Skill	16k	today	Apache-2.0	A	37	Claude Code
log-error-digestzebbern/claude-code-guide	Skill	4.7k	today	MIT	A	71	Claude Code, Codex
cwv-optimizeradobe/skills	Skill	326	today	Apache-2.0	A	112	Claude Code
ci-fixersipyourdrink-ltd/bernstein	Skill	1.2k	today	Apache-2.0	A	15	Claude Code, Codex
self-healhristo2612/jinn	Skill	329	yesterday	MIT	A	19	Claude Code, Codex
diagnosing-missing-recordingsPostHog/posthog	Skill	41k	today	none	A	76	Claude Code, Codex