loop-contract

Community

Scaffold a verifiable agent loop

AuthorSollanSystems
Version1.0.0
Installs0

System Documentation

What problem does it solve?

This Skill turns an architecture decision into a persistent, on-disk operating contract so an agent loop can keep its truth outside chat context. It prevents false completion by forcing the loop to store goals, workflow rules, task state, and evidence requirements in files that survive compaction, crashes, and runtime changes.

Core Features & Use Cases

  • Contract Scaffolding: Creates the core repo-OS artifacts needed to initialize a new agent loop, including SPEC, WORKFLOW, TASKS, RUNLOG, and .loop state files.
  • Verification-First Setup: Prepares verify-fast and verify-full skeletons plus the supporting manifest so success criteria can be checked deterministically.
  • Reflection and Safety Gates: Records an iteration-zero pre-execution review, captures approval gates, and enumerates terminal states to keep the loop auditable.
  • Use Case: Use it when you have an ADR and need to bootstrap a new loop workspace or extend an existing one with clearer criteria, evidence rules, and machine-readable state.

Quick Start

Ask the skill to scaffold the repo-OS operating contract for your project from the approved architecture decision and initialize the workspace files before any implementation changes.

Dependency Matrix

Required Modules

None required

Components

Standard package

💻 Claude Code Installation

Recommended: Let Claude install automatically. Simply copy and paste the text below to Claude Code.

Please help me install this Skill:
Name: loop-contract
Download link: https://github.com/SollanSystems/loop-engineer/archive/main.zip#loop-contract

Please download this .zip file, extract it, and install it in the .claude/skills/ directory.
View Source Repository

Agent Skills Search Helper

Install a tiny helper to your Agent, search and equip skill from 536,000+ vetted skills library on demand.