Next Move Agent Skill

Ranked next offensive moves from engagement state. Reads state/loot/Killchain, runs the deterministic analyzer, elaborates the top move. Use when asked "what next", "where to focus", "prioritize", or at the start of an engagement session.

203 tokens

context cost

the whole folder, loaded on every use

files

instructions only

copies elsewhere

how many repositories repackaged it

320

stars on the repo

on the repository, not the skill itself

Install

one command, takes just this skill from the repository

npx skills add https://github.com/Encod3d-Sec/TORCH --skill next-move

The instruction itself

1 sections, as written by the author

Next Move (deprecated - now an input to /redteamlead)

next-move no longer runs standalone. Its ranked output is now one INPUT that

/redteamlead reads before giving a wiki-grounded direction.

For "where do I go next", call Skill(redteamlead) instead of this skill directly.

The deterministic ranker stays and is unchanged:

python3 scripts/next_move.py --json

RTL reads this --json output (plus state/loot/Killchain/log and the wiki) to produce

its ranked directions. Nothing else in this file is load-bearing anymore.

How to use it

Copy the folder

Take encod3d-sec/next-move from the repository into ~/.claude/skills for personal use, or into .claude/skills inside a project.

Check the name does not clash

The agent identifies a skill by the name field in its header. Two skills with the same name cannot sit side by side — one of them will be ignored.