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 commands/marcosd4h/deepextractruntime/winrtgit 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 | $0.00000 | $0.01193 |
| Opus 5 | $0.00000 | $0.00596 |
| Sonnet 5 | $0.00000 | $0.00239 |
| Haiku 4.5 | $0.00000 | $0.00119 |
Grade A, and why
winrt 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.
This is a copy
86% identical to com — 68 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 121 lines — stays where its author put it; the contents beside it link to each section on GitHub.
WinRT Analysis
Overview
Analyze WinRT server interfaces in Windows binaries using ground-truth extraction data. Enumerates server classes, maps the privilege-boundary attack surface, audits security properties, classifies entry points, and identifies privilege escalation targets.
The text after /winrt is the module name and optional subcommand (e.g., /winrt TaskFlowDataEngine.dll, /winrt surface, /winrt privesc).
Subcommands
| Subcommand | Usage | Purpose |
|---|---|---|
| (default) | /winrt <module> |
Enumerate WinRT server classes, interfaces, methods |
workspace |
/winrt workspace |
Discover which workspace modules implement WinRT servers |
surface |
/winrt surface [module] |
Risk-ranked WinRT attack surface (module or system-wide) |
methods |
/winrt methods <module_or_class> |
List methods with optional pseudo-IDL |
classify |
/winrt classify <module> |
Semantic classification of WinRT entry points |
audit |
/winrt audit <module> |
WinRT-specific security audit |
privesc |
/winrt privesc [--top N] |
Find privilege escalation targets |
IMPORTANT: Execution Model
Execute immediately. Do NOT ask for confirmation before running scripts. Read the winrt-interface-analysis SKILL.md to understand available scripts and their options, then run the appropriate script(s) for the subcommand.
Execution Context
- Working directory: Workspace root (scripts handle their own path setup)
- Output: Scripts support
--jsonfor machine-readable output - Data: Read-only access to WinRT extraction data via
helpers.winrt_index
Steps
Step 0: Preflight Validation
Parse the user's input to determine the subcommand and target. If a module name is given, verify it exists in the WinRT index by running:
python .claude/skills/winrt-interface-analysis/scripts/resolve_winrt_server.py <module> --json
If no servers are found, report this and suggest checking module name spelling or using surface --system-wide to see all available modules.
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 · 121 lines · 0 tokens per session scan A 3146f9e4746a
winrt is a command published in the GitHub repository marcosd4h/DeepExtractRuntime (20 stars, last pushed 3mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,193 tokens. A static security scan graded it A with 0 findings. It is 86% identical to com, differing in 68 lines, and is treated as a copy.
Other commands, from other repositories
git
Git operations with intelligent commit messages and workflow optimization.
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.