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/function-indexnpx skills add marcosd4h/DeepExtractRuntime --skill function-indexgit 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 | $0.00117 | $0.03170 |
| Opus 5 | $0.00059 | $0.01585 |
| Sonnet 5 | $0.00023 | $0.00634 |
| Haiku 4.5 | $0.00012 | $0.00317 |
Grade A, and why
function-index 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 — 296 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Function Index
Purpose
Provide fast function-to-file resolution for DeepExtractIDA extraction outputs. Every extracted module folder contains a function_index.json that maps each function name to the .cpp file containing its decompiled output, plus a library tag for boilerplate detection. This skill provides scripts to query, filter, and resolve these indexes without scanning hundreds of .cpp files.
This skill is designed to be reused by other skills -- it does not depend on any other skills.
When NOT to Use
- Extracting full function data (decompiled code, assembly, xrefs) -- use decompiled-code-extractor
- Classifying functions by purpose or computing interest scores -- use classify-functions
- Searching across strings, APIs, and classes (not just function names) -- use
unified_search.pyor decompiled-code-extractor - Understanding what a function does -- use re-analyst or
/explain - Tracing call chains between functions -- use callgraph-tracer
Data Sources
Each module folder under extracted_code/{module}/ contains:
function_index.json-- lightweight index mapping function names to files and library tagsfile_info.json-- full module metadata (signatures, imports, exports, etc.){module}_*.cpp-- grouped decompiled source files
function_index.json Format
{
"<function_name>": {
"file": "module_standalone_group_5.cpp",
"library": null
},
"<wil_function>": {
"file": "module_standalone_group_1.cpp",
"library": "WIL"
}
}
| Field | Description |
|---|---|
file |
The .cpp filename in the same directory as the index |
library |
Library tag: WIL, STL, WRL, CRT, ETW/TraceLogging, or null |
library = null means application code. Non-null tags identify known library/runtime boilerplate.
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.
- 2d ago First seen · 296 lines · 117 tokens per session scan A ea9af28de830
function-index is a skill published in the GitHub repository marcosd4h/DeepExtractRuntime (20 stars, last pushed 3mo ago), licensed MIT. It adds 117 tokens to every session and 3,170 once invoked, about $0.0006 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.
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…
agent-host-chat-contributions
Build and review cross-cutting agent-host chat behavior through lifecycle contributions. Use when adding turn lifecycle side effects, prompt or context injection, restored-history transformation, protocol-action observation, or when reviewing changes that add code to AgentSideEffects or AgentService.
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.