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/map-attack-surfacenpx skills add marcosd4h/DeepExtractRuntime --skill map-attack-surfacegit 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 | $0.00131 | $0.02914 |
| Opus 5 | $0.00066 | $0.01457 |
| Sonnet 5 | $0.00026 | $0.00583 |
| Haiku 4.5 | $0.00013 | $0.00291 |
Grade A, and why
map-attack-surface 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 — 291 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Attack Surface Mapper
Purpose
Answer: "Where can an attacker enter this binary?"
Automatically discover, classify, and rank every possible entry point in an analyzed Windows PE binary, from obvious DLL exports to hidden COM vtable methods, RPC stubs, callback registrations, and socket dispatchers. Each entry point is ranked by attack value using callgraph reachability to dangerous operations.
When NOT to Use
- General module-level triage or function classification -- use classify-functions or generate-re-report
- Tracing attacker-controlled input to specific sinks -- use taint-analysis
- Understanding what a specific function does -- use re-analyst or
/explain - PE-level import/export dependency mapping -- use import-export-resolver
Data Sources
SQLite Databases (primary)
Individual analysis DBs in extracted_dbs/ provide:
file_info.entry_point-- PE-detected entry pointsfile_info.exports-- All exported functions with signaturesfile_info.tls_callbacks-- TLS callback metadata with threat scoringfile_info.imports-- Imported APIs (used for API pattern detection)functions.simple_outbound_xrefs-- Callgraph edges for reachability analysisfunctions.vtable_contexts-- COM/WRL vtable reconstructionsfunctions.dangerous_api_calls-- Dangerous API sinks per functionfunctions.string_literals-- String patterns (pipe names, RPC protocols)
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
Quick Cross-Dimensional Search
To search across function names, strings, APIs, classes, and exports in one call:
python .claude/helpers/unified_search.py <db_path> --query "SearchTerm"
python .claude/helpers/unified_search.py <db_path> --query "SearchTerm" --json
Utility Scripts
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 · 291 lines · 131 tokens per session scan A e527dd56c49d
map-attack-surface is a skill published in the GitHub repository marcosd4h/DeepExtractRuntime (20 stars, last pushed 3mo ago), licensed MIT. It adds 131 tokens to every session and 2,914 once invoked, about $0.0007 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…