hunt-execute

A command that carries out a vulnerability-research plan and turns the investigation results into a consolidated findings report.

In plain words
What is it for?
Use it after creating a hunt plan, or provide a specific hypothesis, to investigate a module for possible security vulnerabilities.
Why use it?
It removes the manual work of running each planned check, collecting evidence, and judging confidence across several security hypotheses.

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-execute
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 1,764 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 $0.01764
Opus 5 $0.00000 $0.00882
Sonnet 5 $0.00000 $0.00353
Haiku 4.5 $0.00000 $0.00176

Measured 2d ago against content hash a15828bedf44, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

hunt-execute 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/hunt-execute.md · 173 lines

How it starts

The opening of the file, as written. The whole thing — 173 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Hunt Execute

Overview

Automatically execute a vulnerability research plan produced by /hunt-plan. Runs the investigation commands for each hypothesis, collects evidence, scores confidence, and produces a consolidated findings report.

Usage:

  • /hunt-execute appinfo.dll -- execute the most recent hunt plan for this module
  • /hunt-execute -- execute the plan from the most recent /hunt-plan session
  • /hunt-execute --plan-file .claude/workspace/appinfo_hunt_plan_20260304.json -- execute a specific plan file
  • /hunt-execute appinfo.dll --hypothesis "TOCTOU in file path handler" -- execute an inline hypothesis without a prior /hunt-plan

This command is the "action" counterpart to /hunt-plan's "planning" phase. While /hunt-plan produces hypotheses and maps them to commands, /hunt-execute runs those commands and interprets results. The --hypothesis flag allows skipping the planning step for quick, targeted investigations.

IMPORTANT: Execution Model

This is an execute-immediately command. Run the full investigation pipeline and deliver the completed findings report. Use the grind loop for multi-hypothesis workflows.

Workspace Protocol

This command orchestrates multiple analysis steps per hypothesis:

  1. Create .claude/workspace/<module>_hunt_execute_<timestamp>/.
  2. Store per-hypothesis results in <run_dir>/hypothesis_<N>/results.json.
  3. Keep only summary output and confidence scores in context.
  4. Use <run_dir>/manifest.json to track which hypotheses have been investigated.

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

1. Locate the hunt plan

Check for an existing /hunt-plan plan using this priority order:

Read the full file on GitHub · 173 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 · 173 lines · 0 tokens per session scan A a15828bedf44

Subscribe to this mod's changes

hunt-execute 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 1,764 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.