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.
npx agentmods add skills/marcosd4h/deepextractruntime/decompiled-code-extractornpx skills add marcosd4h/DeepExtractRuntime --skill decompiled-code-extractorgit clone --depth 1 https://github.com/marcosd4h/DeepExtractRuntimeWhat 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 | $0.00089 | $0.01924 |
| Opus 5 | $0.00044 | $0.00962 |
| Sonnet 5 | $0.00018 | $0.00385 |
| Haiku 4.5 | $0.00009 | $0.00192 |
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 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.
How it starts
The opening of the file, as written. The whole thing — 204 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
python .claude/skills/decompiled-code-extractor/scripts/find_module_db.py appinfo.dll
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> resolves the function name to its .cpp file path across all modules. 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.
- 2d 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 (20 stars, last pushed 3mo ago), licensed MIT. It adds 89 tokens to every session and 1,924 once invoked, about $0.0004 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.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
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.
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.
chat-perf
Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.
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.
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…