hunt-plan

hunt-plan is a command for coding agents from marcosd4h/DeepExtractRuntime. It costs 0 tokens per session (3,577 once invoked), scanned A, original, MIT.

A planning command for vulnerability research—the process of finding and testing security weaknesses in software—especially in Windows modules.

In plain words
What is it for?
Use it to plan a campaign for one module, test a hypothesis, compare related modules, trace data across modules, or revise a plan using earlier results.
Why use it?
It turns a suspected attack pattern or research goal into testable hypotheses, trust-boundary checks, and concrete analysis steps without running the investigation itself.

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/hunt-plan
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 hunt-plan

README.md
[![agentmods](https://agentmods.dev/badge/commands/marcosd4h/deepextractruntime/hunt-plan.svg)](https://agentmods.dev/commands/marcosd4h/deepextractruntime/hunt-plan)
Your own site
<a href="https://agentmods.dev/commands/marcosd4h/deepextractruntime/hunt-plan"><img src="https://agentmods.dev/badge/commands/marcosd4h/deepextractruntime/hunt-plan.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 3,577 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 $0.03577
Opus 5 $0.00000 $0.01788
Sonnet 5 $0.00000 $0.00715
Haiku 4.5 $0.00000 $0.00358

Measured 4d ago against content hash 0337a3379312, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

hunt-plan 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/hunt-plan.md · 330 lines

How it starts

The opening of the file, as written. The whole thing — 330 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Hunt Plan

Overview

Hypothesis-driven vulnerability research planning and strategic campaign design. Generates testable attack hypotheses, matches observations to known Windows attack patterns, plans variant analysis, validates suspected findings, and maps trust boundaries -- all mapped to concrete workspace commands. Also covers strategic planning at the campaign, cross-module, and replan levels.

The command supports 4 modes selected by the first argument:

  • /hunt-plan appinfo.dll -- campaign mode (default): plan a full VR campaign (includes trust boundary mapping)
  • /hunt-plan hypothesis TOCTOU appinfo.dll -- test a specific vulnerability hypothesis, find variants of a pattern, or validate a suspected finding
  • /hunt-plan cross appinfo.dll consent.exe -- plan a cross-module taint and data flow campaign
  • /hunt-plan replan -- re-plan from prior analysis results

If no arguments are provided, ask the user what they want to investigate.

IMPORTANT: Execution Model

This is a collaborative dialogue command. Do NOT run analysis, write code, or execute scripts. The purpose is to produce an approved research design with testable hypotheses that transitions into an implementation plan via CreatePlan. All investigation happens after the user approves.

Steps

1. Detect mode

Parse the user's input to determine the research mode:

First argument Mode Description
(module name only) campaign Plan a full VR campaign against the module (includes trust boundary mapping)
hypothesis hypothesis Formulate and test a hypothesis, find pattern variants, or validate a suspected finding
cross cross-module Plan a cross-module taint and data flow investigation
replan replan Re-plan based on prior analysis results

Default to campaign when only a module name is provided.

2. Gather existing context

Check what data is already available before asking questions:

  • Review session context for available modules and module profiles
  • Check .claude/cache/ and .claude/workspace/ for prior triage, classification, or attack surface results
  • Note which modules have been analyzed and what data exists
  • If a specific module is mentioned, check whether /triage output exists

Read the full file on GitHub · 330 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 · 330 lines · 0 tokens per session scan A 0337a3379312

Subscribe to this mod's changes

hunt-plan 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 3,577 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.