scan

A command that combines several security checks for a compiled program into one vulnerability report, including attack-surface review, data-flow checks, and result cleanup.

In plain words
What is it for?
Use it to scan a module or function, limit the scan to selected issue types or entry points, bypass cached results, or automatically audit the most serious findings.
Why use it?
It gathers findings from different scanners and removes duplicates so security issues can be reviewed in one severity-ranked report.

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/scan
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 1,957 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 $0.01957
Opus 5 $0.00000 $0.00979
Sonnet 5 $0.00000 $0.00391
Haiku 4.5 $0.00000 $0.00196

Measured 2d ago against content hash 300ec0bed37c, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

scan 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/scan.md · 158 lines

How it starts

The opening of the file, as written. The whole thing — 158 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Vulnerability Scan

Overview

Unified vulnerability scan that orchestrates recon, AI scanner context preparation, taint analysis, assembly verification, and deduplication into a single pipeline. Produces a consolidated, severity-ranked findings report.

The pipeline prepares workspace context for the AI-driven memory-corruption, logic, and taint scanners, launches LLM scanner subagents, and merges everything into a deduplicated report.

Usage:

  • /scan appinfo.dll -- full scan (recon + AI context + taint + verify + report)
  • /scan appinfo.dll --top 15 -- analyze top 15 entry points
  • /scan appinfo.dll --taint-only -- delegate to /taint (AI-driven taint scanner)
  • /scan appinfo.dll --memory-only -- delegate to /memory-scan (AI-driven scanner)
  • /scan appinfo.dll --logic-only -- delegate to /ai-logical-bug-scan (AI-driven scanner)
  • /scan appinfo.dll <function> -- all detectors on a specific function
  • /scan appinfo.dll --auto-audit -- after scanning, automatically audit the top 3 CRITICAL/HIGH findings
  • /scan appinfo.dll --no-cache -- bypass cached results for all scanners

IMPORTANT: Execution Model

This is an execute-immediately command. Run the full pipeline and deliver the completed report. Use the grind loop for large modules where all phases cannot complete in one pass.

Workspace Protocol

This command orchestrates many analysis steps:

  1. Create .claude/workspace/<module>_scan_<timestamp>/.
  2. Store per-phase results in <run_dir>/<phase>/results.json.
  3. Use <run_dir>/manifest.json to track completed/failed phases.
  4. Keep only summaries in context; read full findings from results.json on demand.

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.

Read the full file on GitHub · 158 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 · 158 lines · 0 tokens per session scan A 300ec0bed37c

Subscribe to this mod's changes

scan 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 1,957 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.