diff

A command for comparing two versions of the same software module, such as two DLL files, to produce a security-focused change report.

In plain words
What is it for?
Reviewing patched or updated binaries and checking changed functions, new attack surface, and fixed security flaws.
Why use it?
It helps reveal what changed after an update, including newly exposed code areas and vulnerabilities that were fixed.

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/diff
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 1,460 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 $0.01460
Opus 5 $0.00000 $0.00730
Sonnet 5 $0.00000 $0.00292
Haiku 4.5 $0.00000 $0.00146

Measured 2d ago against content hash 6004995c4173, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

diff 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/diff.md · 148 lines

How it starts

The opening of the file, as written. The whole thing — 148 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Diff -- Compare Binary Versions

Overview

Compare two versions of the same module to identify changed functions, new attack surface, and fixed vulnerabilities. Use when a binary has been updated (patched, new version) and you want to understand what changed from a security perspective.

Usage:

  • /diff <module_old> <module_new>
  • /diff appinfo_v1.dll appinfo_v2.dll

IMPORTANT: Execution Model

This is an execute-immediately command. Do NOT present anything for user confirmation. Run all analysis steps and present the completed diff report straight to the chat as your response.

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.

Tip: All skill scripts support --json for machine-readable output. Use --json when parsing script output programmatically.

Steps

Step 0: Preflight Validation

Validate arguments using helpers.command_validation.validate_command_args("diff", {"module": "<module_old>"}) and again for <module_new>. If either validation fails, report the errors to the user and stop. On success, use result.resolved["db_path"] for both modules in all subsequent skill script calls.

Step 1: Resolve Both Module DBs

python .claude/skills/decompiled-code-extractor/scripts/find_module_db.py <module_old>
python .claude/skills/decompiled-code-extractor/scripts/find_module_db.py <module_new>

Entry: Two module names provided by the user Exit: Both DB paths resolve to existing files

Step 2: Extract Function Inventories

python .claude/skills/decompiled-code-extractor/scripts/list_functions.py <db_old> --has-decompiled --json
python .claude/skills/decompiled-code-extractor/scripts/list_functions.py <db_new> --has-decompiled --json

Read the full file on GitHub · 148 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 · 148 lines · 0 tokens per session scan A 6004995c4173

Subscribe to this mod's changes

diff is a command published in the GitHub repository marcosd4h/DeepExtractRuntime (18 stars, last pushed 3mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,460 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.