dharma-autonomous-build

Executes bounded overnight autonomous cleanup and build lanes with explicit stop conditions.

Updated Aug 5, 2026
One-click install
npx skills add https://github.com/AmitabhainArunachala/dharma_swarmv.01 --skill dharma-autonomous-build-amitabhainarunachala
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: dharma-autonomous-build
Source: https://github.com/AmitabhainArunachala/dharma_swarmv.01/tree/main/mode_pack/claude/autonomous-build
Command: npx skills add https://github.com/AmitabhainArunachala/dharma_swarmv.01 --skill dharma-autonomous-build-amitabhainarunachala

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? Long-running autonomous coding sessions tend to drift out of scope, touch protected hot paths, or silently widen into adjacent domains. This Skill keeps an agent executing bounded cleanup or build work overnight while preserving lane integrity and leaving a truthful control trail. ## Core Features & Use Cases - Bounded Lane Execution: Runs cleanup or build tranches only when the lane, hot-path exclusions, and stop conditions are already written down. - Structured Reporting: Requires every cycle to output the current lane, tranche completed, files changed, validation performed, residual risks, and the next bounded seam. - Explicit Stop Rules: Halts on unresolved ownership, path-coupling, or authority ambiguity instead of silently widening scope, and records the blocker in control docs. - Use Case: An operator decomposes a non-TUI cleanup into a safe lane, activates this mode overnight, and the agent iterates through tranches while updating the lane-owner control document and logging issues without touching TUI or dashboard hot paths. ## Quick Start Activate the dharma-autonomous-build mode and run the next bounded cleanup tranche defined in the overnight control document, reporting files changed and validation performed.

Frequently Asked Questions about dharma-autonomous-build

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I run an autonomous overnight coding session safely?▼

Define the lane, hot-path exclusions, and stop conditions in a control document first, then activate this mode. The agent executes bounded tranches, reports files changed and validation performed after each cycle, and stops on any ambiguity instead of widening scope.

What should an autonomous build agent report after each work cycle?▼

Each tranche must report six items: current lane, tranche completed, files changed, validation performed, residual risks, and the next bounded seam. This creates a truthful control trail for operator review.

When should I not use autonomous build mode?▼

Do not use it when the lane is not yet explicit, stop conditions are unwritten, or the work touches protected hot paths like TUI or dashboard code. The mode requires pre-decomposed, bounded work and halts on unresolved ownership or authority ambiguity.

How does the agent handle scope ambiguity during autonomous execution?▼

The agent stops immediately on unresolved ownership, path-coupling, or authority ambiguity and records the blocker explicitly in the control docs. It never silently widens into adjacent domains or confuses file existence with tracked, merge-safe state.

Which tools does the autonomous build mode allow?▼

The mode permits Read, Grep, Glob, Bash, Edit, and Write. These cover inspection, execution, and modification of repository files while the lane rules and frontmatter discipline govern how they are used.