prioritize

prioritize is a command for coding agents from marcosd4h/DeepExtractRuntime. It costs 0 tokens per session (1,476 once invoked), scanned A, original, MIT.

A command that combines security findings from several software modules and puts them in one ranked list. It scores each finding by how easy it may be to exploit, how reachable it is, and its potential effect.

In plain words
What is it for?
Use it to rank findings from selected modules or all available modules, show only the top results, or filter out findings below a chosen score.
Why use it?
It removes the need to compare separate scan reports by hand. You can focus first on findings with the highest combined risk.

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/prioritize
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 prioritize

README.md
[![agentmods](https://agentmods.dev/badge/commands/marcosd4h/deepextractruntime/prioritize.svg)](https://agentmods.dev/commands/marcosd4h/deepextractruntime/prioritize)
Your own site
<a href="https://agentmods.dev/commands/marcosd4h/deepextractruntime/prioritize"><img src="https://agentmods.dev/badge/commands/marcosd4h/deepextractruntime/prioritize.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 1,476 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 $0.01476
Opus 5 $0.00000 $0.00738
Sonnet 5 $0.00000 $0.00295
Haiku 4.5 $0.00000 $0.00148

Measured 3d ago against content hash 31bf02165e69, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

prioritize 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 3d 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/prioritize.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.

Prioritize Findings

Overview

Cross-module finding prioritization. Loads cached scan and audit results from multiple modules, normalizes them via the unified finding schema, ranks by exploitability × reachability × impact, and produces a single priority-ordered list spanning all specified modules.

Usage:

  • /prioritize --modules appinfo.dll lsasrv.dll -- prioritize findings across two modules
  • /prioritize --all -- prioritize findings across all available modules
  • /prioritize --modules appinfo.dll --top 20 -- limit to top 20 findings
  • /prioritize --all --min-score 0.5 -- only show findings with composite score ≥ 0.5

IMPORTANT: Execution Model

This is an execute-immediately command. Discover modules, load cached results, merge and rank findings, then deliver the completed report.

Workspace Protocol

This command aggregates results from prior scan/audit runs:

  1. Create .claude/workspace/prioritize_<timestamp>/.
  2. Store per-module loaded findings in <run_dir>/<module>/results.json.
  3. Store merged and ranked output in <run_dir>/ranked/results.json.
  4. Use <run_dir>/manifest.json to track completed/failed phases.

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.

Steps

Step 0: Preflight Validation

Validate arguments using helpers.command_validation.validate_command_args("prioritize", {"modules": "<modules>"}). If validation fails, report the errors and stop.

Step 1: Discover Available Modules

If --all: List all modules via the decompiled-code-extractor:

python .claude/skills/decompiled-code-extractor/scripts/find_module_db.py --list --json

If --modules A B C: Resolve each named module to its DB path:

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. 3d ago First seen · 158 lines · 0 tokens per session scan A 31bf02165e69

Subscribe to this mod's changes

prioritize is a command published in the GitHub repository marcosd4h/DeepExtractRuntime (20 stars, last pushed 4mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,476 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.