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.
git clone --depth 1 https://github.com/marcosd4h/DeepExtractRuntimenpx agentmods add skills/marcosd4h/deepextractruntime/decompiled-code-extractorWrote 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.
[](https://agentmods.dev/skills/marcosd4h/deepextractruntime/decompiled-code-extractor)<a href="https://agentmods.dev/skills/marcosd4h/deepextractruntime/decompiled-code-extractor"><img src="https://agentmods.dev/badge/skills/marcosd4h/deepextractruntime/decompiled-code-extractor/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.
<a href="https://agentmods.dev/skills/marcosd4h/deepextractruntime/decompiled-code-extractor"><img src="https://agentmods.dev/badge/skills/marcosd4h/deepextractruntime/decompiled-code-extractor.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00089 | $0.02483 |
| Opus 5.5 | $0.00036 | $0.00993 |
| Sonnet 5.5 | $0.00018 | $0.00497 |
| Haiku 4.5 | $0.00009 | $0.00248 |
Grade A, and why
decompiled-code-extractor 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 1mo 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.
How it starts
The opening of the file, as written. The whole thing — 233 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Decompiled Code Extractor
Purpose
Extract structured function data from DeepExtractIDA analysis databases. This skill provides the core scripts for locating module databases, listing and searching functions, and extracting complete per-function records. It is the foundational data-access layer that nearly every other skill depends on.
The scripts do not perform any analysis, lifting, or rewriting. They are purely data retrieval tools.
When NOT to Use
- Classifying functions by purpose or triaging a module -- use classify-functions
- Understanding what a function does (explanation, not raw data) -- use re-analyst or
/explain - Tracing call chains or cross-module execution paths -- use callgraph-tracer
- Scanning for vulnerabilities in extracted code -- use ai-memory-corruption-scanner or ai-logic-scanner
- Lifting or rewriting decompiled code to readable C++ -- use the code-lifter agent
Data Sources
Finding a Module DB
python .claude/skills/decompiled-code-extractor/scripts/find_module_db.py --list --json
python .claude/skills/decompiled-code-extractor/scripts/find_module_db.py --module appinfo.dll --json
# detached extraction:
# find_module_db.py --module appinfo.dll --json --workspace-root <extraction>
Locating the Target Function
Functions come from two sources:
1. Generated .cpp files in extracted_code/{module}/:
- Class methods:
{module}_{ClassName}_group_{N}.cpp - Standalone:
{module}_standalone_group_{N}.cpp - Each function has a comment header:
// Function Name:,// Mangled Name:,// Function Signature (Extended):,// Function Signature:
2. SQLite databases in extracted_dbs/ (preferred -- contains assembly):
- Use the utility scripts in
scripts/to extract function data - Each function record has
decompiled_code,assembly_code, signatures, xrefs, strings, and more
3. Function index (fastest): python .claude/skills/function-index/scripts/lookup_function.py <name> --json resolves the function name to its .cpp path across all modules. Add --workspace-root <extraction> when the extraction is not this overlay. After lookup, extract with --id. Use --app-only to skip library boilerplate.
What ships with it
7 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.
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.
- 1mo ago Changed · +29 lines ef29b3601794
- 1mo ago First seen · 204 lines · 89 tokens per session scan A 91e6abbbffd0
decompiled-code-extractor is a skill published in the GitHub repository marcosd4h/DeepExtractRuntime (21 stars, last pushed 1mo ago), licensed MIT. It adds 89 tokens to every session and 2,483 once invoked, about $0.0004 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.
Other skills, from other repositories
debug-optimize-lcp
Guides debugging and optimizing Largest Contentful Paint (LCP) using Chrome DevTools MCP tools. Use this skill whenever the user asks about LCP performance, slow page loads, Core Web Vitals optimization, or wants to understand why their page's main content takes too long to appear. Also use when the user mentions…
systematic-debugging
Use when debugging a failing test, build error, or runtime issue that isn't immediately obvious. Guides a 4-phase root cause analysis instead of random fix attempts.
diagnose
Trace from a reproduced symptom to the source code that causes it. Pin the specific file and approximate line, rate confidence in the cause and clarity of the fix independently, and always propose a concrete fix.
repro-admin
Reproduce an EmDash admin UI bug. Attach a container, start the demo dev server, drive the admin with agent-browser using the dev-bypass session, and capture the reproduction as screenshots plus a replayable transcript.
log-error-digest
Analyze log files to troubleshoot errors, identify peak error periods, and produce error clustering, frequency statistics, and time distribution reports. Supports JSON, syslog, and Nginx formats with automatic detection. Use when a user uploads a .log file and asks to analyze errors, find patterns, debug issues, or…
deck-retro
Run a fully local agent-deck retrospective over the user's own transcripts, Recall index and logs. Use when a user wants to find recurring failures or take their own finding from investigation through synthetic reproduction, a user-filed issue, a test-first fix and contributor PR handoff. Also use for weekly usage…