compare-modules

A command for comparing two or more modules analyzed by DeepExtractIDA, a tool or workflow that examines program modules. It compares dependencies, imports and exports, function categories, and calls between modules.

In plain words
What is it for?
Use it to compare named modules or request a high-level comparison of all analyzed modules, with a limit of 200 for the all-modules option.
Why use it?
It brings related module findings together so you can inspect how modules differ and interact.

Command

Install

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.

agentmods
npx agentmods add commands/marcosd4h/deepextractruntime/compare-modules
Clone the repo
git clone --depth 1 https://github.com/marcosd4h/DeepExtractRuntime
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,960 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00000 $0.01960
Opus 5 $0.00000 $0.00980
Sonnet 5 $0.00000 $0.00392
Haiku 4.5 $0.00000 $0.00196

Measured 2d ago against content hash 67e7c43c3680, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

compare-modules 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.

commands/compare-modules.md · 123 lines

How it starts

The opening of the file, as written. The whole thing — 123 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Compare Modules

Overview

Cross-module analysis of two or more DeepExtractIDA-analyzed modules -- comparing dependency relationships, import/export overlap, function classification distributions, and cross-module call chains.

The text after /compare-modules lists two or more module names:

  • /compare-modules appinfo.dll cmd.exe
  • /compare-modules explorer.exe shell32.dll ntdll.dll
  • /compare-modules --all -- compare all analyzed modules at a high level (capped at 200 modules; see Scale Limits)

If fewer than two modules are specified, list available modules and ask.

Scale Limits

The --all flag is capped at 200 modules (configurable via scale.max_modules_compare in .claude/config/defaults.json). If there are more than 200 modules, --all compares the first 200 and warns the user. For targeted comparison of specific modules, always list them explicitly.

With 100+ modules, pairwise analysis becomes O(N^2). Use --all only for high-level overviews; use explicit module lists for detailed comparison.

IMPORTANT: Execution Model

This is an execute-immediately command. Do NOT present anything for user confirmation. Run and write the final comparison report straight to the chat as your response. The user expects to see the completed report.

Execution Context

IMPORTANT: Any inline Python that imports helpers.* must run with cd <workspace>/.claude (so the .claude/ directory is on sys.path), not from the workspace root. Script invocations like python .claude/skills/.../script.py can be run from the workspace root because those scripts manage their own path setup.

Workspace Protocol

For multi-module comparison:

  1. Create a top-level run directory under .claude/workspace/ for the command.
  2. Create per-module sub-runs (for example, <run_dir>/<moduleA>/, <run_dir>/<moduleB>/) to avoid collisions.
  3. Pass --workspace-dir <module_run_dir> and --workspace-step <step_name> to every skill invocation.
  4. Keep only compact summaries in context; avoid inlining full JSON across modules.
  5. Read detailed data on demand from <module_run_dir>/<step_name>/results.json and use each run's manifest.json for traceability.

Read the full file on GitHub · 123 lines

Changes

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.

  1. 2d ago First seen · 123 lines · 0 tokens per session scan A 67e7c43c3680

Subscribe to this mod's changes

compare-modules 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 1,960 tokens. 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.