/autonomous
Run all remaining phases autonomously — discuss→plan→execute per phase
$ npx -y skills add backbay-labs/thrunt-god --agent claude-codeHow it fires
How this command gets triggered: by you, by Claude, or both.
- Fires itselfClaude auto-loads it when your prompt matches the work.
- You can call itInvoke it directly when you want it.
- Slash command
/autonomous
Context preview
What this command does when you run it.
Run all remaining phases autonomously — discuss→plan→execute per phase
Command definition
autonomous.mdname: thrunt:autonomous
description: Run all remaining phases autonomously — discuss→plan→execute per phase
argument-hint: "[--from N]"
allowed-tools:
- Read
- Write
- Bash
- Glob
- Grep
- AskUserQuestion
- Task
<objective> Execute all remaining milestone phases autonomously. For each phase: discuss → plan → execute. Pauses only for user decisions (grey area acceptance, blockers, validation requests).
Uses HUNTMAP.md phase discovery and Skill() flat invocations for each phase command. After all phases complete: milestone audit → complete → cleanup.
**Creates/Updates:**
- `.planning/STATE.md` — updated after each phase
- `.planning/HUNTMAP.md` — progress updated after each phase
- Phase artifacts — CONTEXT.md, PLANs, SUMMARYs per phase
**After:** Milestone is complete and cleaned up. </objective>
<execution_context> @~/.claude/thrunt-god/workflows/autonomous.md @~/.claude/thrunt-god/references/ui-brand.md </execution_context>
<context> Optional flag: `--from N` — start from phase N instead of the first incomplete phase.
Project context, phase list, and state are resolved inside the workflow using init commands (`thrunt-tools.cjs init milestone-op`, `thrunt-tools.cjs huntmap analyze`). No upfront context loading needed. </context>
<process> Execute the autonomous workflow from @~/.claude/thrunt-god/workflows/autonomous.md end-to-end. Preserve all workflow gates (phase discovery, per-phase execution, blocker handling, progress display). </process>
Read more
name: thrunt:autonomous description: Run all remaining phases autonomously — discuss→plan→execute per phase argument-hint: "[--from N]" allowed-tools: - Read - Write - Bash - Glob - Grep - AskUserQuestion - Task
<objective> Execute all remaining milestone phases autonomously. For each phase: discuss → plan → execute. Pauses only for user decisions (grey area acceptance, blockers, validation requests).
Uses HUNTMAP.md phase discovery and Skill() flat invocations for each phase command. After all phases complete: milestone audit → complete → cleanup.
**Creates/Updates:**
- `.planning/STATE.md` — updated after each phase
- `.planning/HUNTMAP.md` — progress updated after each phase
- Phase artifacts — CONTEXT.md, PLANs, SUMMARYs per phase
**After:** Milestone is complete and cleaned up. </objective>
<execution_context> @~/.claude/thrunt-god/workflows/autonomous.md @~/.claude/thrunt-god/references/ui-brand.md </execution_context>
<context> Optional flag: `--from N` — start from phase N instead of the first incomplete phase.
Project context, phase list, and state are resolved inside the workflow using init commands (`thrunt-tools.cjs init milestone-op`, `thrunt-tools.cjs huntmap analyze`). No upfront context loading needed. </context>
<process> Execute the autonomous workflow from @~/.claude/thrunt-god/workflows/autonomous.md end-to-end. Preserve all workflow gates (phase discovery, per-phase execution, blocker handling, progress display). </process>
Threat hunting command system for agentic IDEs
Repo: backbay-labs/thrunt-god
Other commands on thrunt-god.
- /help
Show available THRUNT threat hunting commands and artifact layout
Open command - /map-environment
Map available telemetry, query surfaces, tenants, retention windows, and investigation blind spots
Open command - /new-case
Initialize a threat hunting case from a signal, detection, intel lead, or analyst suspicion
Open command - /new-program
Initialize a threat hunting program with an environment map, tool inventory, huntmap, and empty execution directories
Open command - /plan
Create phase plans for a threat hunt with exact telemetry tasks, receipts, and query outputs
Open command - /publish
Publish a hunt as a case report, escalation, detection promotion, or leadership summary
Open command

