launch-charter
CommunityLock in safe autonomy boundaries—forever.
System Documentation
What problem does it solve?
It prevents autonomous launch agents from drifting into unsafe or self-deregulating behavior by defining immutable governance rails that every run must follow.
Core Features & Use Cases
- Immutable governance charter: Establishes what agents may improve freely versus what they may never change (permissions, spend caps, safety controls, and the charter itself).
- Boundary enforcement across the launch crew: Binds autonomy behavior to the repo’s AGENTS.md boundary matrix and linked control skills (e.g., kill-switch, PII redaction, tier judgment).
- Operational safety gates for builders: Requires sandbox-by-default execution, separation of writing vs approving, oracle-based verification, reversibility, and hard spend ceilings.
Use case: Before any “ship-it” or cron/autonomy-loop run starts, an agent loads this charter to ensure changes are sandboxed, judged, oracle-validated, and escalated for any restricted path.
Quick Start
Ask the autonomous agent to start a ship-it or cron run by loading launch-charter as step 1, and require it to refuse any attempt to modify restricted files or this charter itself.
Dependency Matrix
Required Modules
None requiredComponents
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: launch-charter Download link: https://github.com/CleanExpo/Pi-Dev-Ops/archive/main.zip#launch-charter Please download this .zip file, extract it, and install it in the .claude/skills/ directory.
Agent Skills Search Helper
Install a tiny helper to your Agent, search and equip skill from 471,000+ vetted skills library on demand.