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 skills add marcosd4h/DeepExtractRuntime --skill com-interface-analysisgit clone --depth 1 https://github.com/marcosd4h/DeepExtractRuntimeWrote 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/com-interface-analysis)<a href="https://agentmods.dev/skills/marcosd4h/deepextractruntime/com-interface-analysis"><img src="https://agentmods.dev/badge/skills/marcosd4h/deepextractruntime/com-interface-analysis/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/com-interface-analysis"><img src="https://agentmods.dev/badge/skills/marcosd4h/deepextractruntime/com-interface-analysis.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 | $0.00081 | $0.01983 |
| Opus 5.5 | $0.00032 | $0.00793 |
| Sonnet 5.5 | $0.00016 | $0.00397 |
| Haiku 4.5 | $0.00008 | $0.00198 |
Grade A, and why
com-interface-analysis 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 — 197 lines — stays where its author put it; the contents beside it link to each section on GitHub.
COM Interface Analysis
Purpose
Query and analyze COM (Component Object Model) server registrations extracted from Windows system binaries. Uses pre-built extraction data that maps every binary to its COM CLSIDs, interface methods, pseudo-IDL definitions, SDDL permissions, service identities, elevation flags, and activation types. The unique value is privilege-boundary risk scoring and elevation/UAC analysis across four access contexts defined by caller integrity level and server process privilege.
When to Use
- Enumerate COM servers and interfaces in a module
- Look up a CLSID to find its hosting binary and security properties
- Map the COM attack surface ranked by privilege-boundary risk
- Find privilege escalation targets (medium-IL caller to SYSTEM server)
- Identify UAC bypass candidates (CanElevate/AutoElevation servers)
- Classify COM entry points by semantic category
- Audit COM server security (permissions, elevation, marshalling, DCOM)
- Confirm decompiled functions are COM entry points
- View pseudo-IDL interface definitions
When NOT to Use
- General function explanation -- use re-analyst
- COM interface reconstruction from vtable patterns in decompiled code -- use com-interface-reconstruction
- WinRT server analysis -- use winrt-interface-analysis
- RPC interface analysis -- use rpc-interface-analysis
- Non-COM attack surface mapping -- use map-attack-surface
Data Sources
- COM index (
helpers/com_index.py): Singleton loaded fromconfig/assets/com_data/across four access contexts. - Access contexts (caller IL x server privilege):
extracted_high_il/all_servers-- high-IL caller, elevated + regular processesextracted_high_il/privileged_servers-- high-IL caller, privileged processes (SYSTEM/high)extracted_medium_il/medium_il/all_servers-- medium-IL caller, elevated + regular processesextracted_medium_il/medium_il/privileged_servers-- medium-IL caller, privileged processes (SYSTEM/high)
- Per-context file:
com_servers.json(binary-keyed; contains server metadata, interfaces, methods, pseudo-IDL, typelib interfaces, and procedure lists per binary).
What ships with it
8 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.
- reference.md 6.2 KB
- scripts/_common.py 1.9 KB runs code
- scripts/audit_com_security.py 6.9 KB runs code
- scripts/classify_com_entrypoints.py 4.3 KB runs code
- scripts/enumerate_com_methods.py 3.1 KB runs code
- scripts/find_com_privesc.py 4.1 KB runs code
- scripts/map_com_surface.py 3.8 KB runs code
- scripts/resolve_com_server.py 4.8 KB runs code
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 First seen · 197 lines · 81 tokens per session scan A bfaed1d00912
com-interface-analysis is a skill published in the GitHub repository marcosd4h/DeepExtractRuntime (21 stars, last pushed 1mo ago), licensed MIT. It adds 81 tokens to every session and 1,983 once invoked, about $0.0003 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
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
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…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…