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/classify-functionsnpx skills add marcosd4h/DeepExtractRuntime --skill classify-functionsgit 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 | $0.00105 | $0.02854 |
| Opus 5 | $0.00053 | $0.01427 |
| Sonnet 5 | $0.00021 | $0.00571 |
| Haiku 4.5 | $0.00011 | $0.00285 |
Grade A, and why
classify-functions 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 3d 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 — 272 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Function Purpose Classification & Triage
Purpose
Automatically categorize every function in a DeepExtractIDA analysis database into purpose categories using multiple signal sources:
- API usage signature: outbound xrefs classified by category (file I/O, registry, network, crypto, etc.)
- String analysis: registry paths, error messages, format strings, URLs, ETW providers
- Naming patterns:
Wpp*/_tlg*/wil_*= telemetry;??0/??1= constructors/destructors;sub_*= unnamed - Assembly metrics: instruction count, call count, branch count, leaf detection (from raw assembly)
- Structural metrics: loop count, cyclomatic complexity from loop analysis
Output is a categorized function index for the entire module, enabling researchers to triage 1000+ function binaries and focus effort on the most interesting functions.
When NOT to Use
- Deep security analysis of a specific function -- use security-dossier or taint-analysis
- Understanding what a specific function does line-by-line -- use re-analyst or
/explain - Generating a full module report with imports, exports, and architecture -- use generate-re-report
- Mapping entry points and ranking by attack value -- use map-attack-surface
- Scanning for specific vulnerability patterns -- use ai-memory-corruption-scanner or ai-logic-scanner
Data Sources
SQLite Databases (primary)
Individual analysis DBs in extracted_dbs/ provide per-function data:
simple_outbound_xrefs-- API calls (classified into categories)string_literals-- string content analysisfunction_name/mangled_name-- naming pattern matchingassembly_code-- structural metrics (instruction/call/branch counts)loop_analysis-- loop count and cyclomatic complexitydangerous_api_calls-- security-relevant API usage
Finding a Module DB
Reuse the decompiled-code-extractor skill's find_module_db.py:
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
What ships with it
6 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.
- 3d ago First seen · 272 lines · 105 tokens per session scan A 8da9b8409cc0
classify-functions is a skill published in the GitHub repository marcosd4h/DeepExtractRuntime (20 stars, last pushed 4mo ago), licensed MIT. It adds 105 tokens to every session and 2,854 once invoked, about $0.0005 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…