compare-scans

compare-scans is a command for coding agents from marcosd4h/DeepExtractRuntime. It costs 0 tokens per session (941 once invoked), scanned A, original, MIT.

A comparison tool for AI security scan reports covering the same software module. It lines up findings from different scans and highlights changes, omissions, regressions, and conflicting severity judgments.

In plain words
What is it for?
Use it to compare recent or selected logic, memory, or taint scans and identify recurring findings, new issues, missed regressions, severity changes, and verdict conflicts.
Why use it?
It helps reveal security issues that repeat across scans or disappear unexpectedly, which is difficult to see by reading reports separately.

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-scans
Clone the repo
git clone --depth 1 https://github.com/marcosd4h/DeepExtractRuntime

Wrote 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.

agentmods badge for compare-scans

README.md
[![agentmods](https://agentmods.dev/badge/commands/marcosd4h/deepextractruntime/compare-scans.svg)](https://agentmods.dev/commands/marcosd4h/deepextractruntime/compare-scans)
Your own site
<a href="https://agentmods.dev/commands/marcosd4h/deepextractruntime/compare-scans"><img src="https://agentmods.dev/badge/commands/marcosd4h/deepextractruntime/compare-scans.svg" alt="Measured on agentmods" height="20"></a>
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 941 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 $0.00941
Opus 5 $0.00000 $0.00470
Sonnet 5 $0.00000 $0.00188
Haiku 4.5 $0.00000 $0.00094

Measured 4d ago against content hash 84b15268dec6, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

compare-scans 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 4d 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-scans.md · 111 lines

How it starts

The opening of the file, as written. The whole thing — 111 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Compare Scans

Overview

Compare findings across AI vulnerability scan reports for the same module. Identifies recurring findings, new findings, missed regressions, severity changes, and verdict conflicts between scans.

Usage:

  • /compare-scans <module> -- compare two most recent scan reports (any type)
  • /compare-scans <module> --type logic|memory|taint -- filter by scan type
  • /compare-scans <module> --reports <path1> <path2> -- compare specific reports

IMPORTANT: Execution Model

This command executes immediately. Run the full comparison and deliver results without pausing for confirmation.

Status Messaging (MANDATORY)

Output a plain-text status message before each step starts and after it completes. Messages are 1-2 lines summarizing what is happening.

Step 0: Preflight Validation

from helpers.command_validation import validate_command_args
result = validate_command_args("compare-scans", {
    "module": "<user_module>",
})
if not result.ok:
    # report errors and stop

Resolve the module reports directory at extracted_code/<module>/reports/.

Step 1: Report Discovery

Status (before): Tell the user: Discovering scan reports for <module>...

Use helpers.report_comparison.discover_reports(reports_dir, scan_type) to find .findings.json companion files. If --type is specified, filter by scan type. If --reports is given, use those paths directly.

Require at least 2 reports. If only 1 exists, show its summary and stop. If 0 exist, report "no structured scan reports found" and suggest running /ai-logical-bug-scan, /memory-scan, or /taint first.

Status (after): Tell the user how many reports were found and which two will be compared.

Step 2: Load Reports

Status (before): Tell the user: Loading report data...

Use helpers.report_comparison.load_findings_json() for both reports. Present brief identity: timestamp, entry point, scan type, finding counts (TP count, FP count).

Status (after): Tell the user the identity of both reports.

Read the full file on GitHub · 111 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. 4d ago First seen · 111 lines · 0 tokens per session scan A 84b15268dec6

Subscribe to this mod's changes

compare-scans is a command published in the GitHub repository marcosd4h/DeepExtractRuntime (19 stars, last pushed 4mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 941 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.