vivshaw/loam-meta

Use near branch completion when contract, API, architecture, invariant, dependency, or domain changes may require AGENTS.md updates.

Use when creating, adapting, validating, auditing, or releasing a portable Agent Skills package for one or more agent hosts.

Use when writing skills, AGENTS.md files, agent prompts, or any directives that involve shell commands, environment variables, API credentials, file creation, or git operations - prevents secrets leakage into LLM context, unsafe shell patterns, and credential exposure

Use when creating or editing skills, before deployment, to verify they work under pressure and resist rationalization - applies RED-GREEN-REFACTOR cycle to process documentation by running baseline without skill, writing to address failures, iterating to close loopholes

Use when writing instructions that guide agent behavior - skills, AGENTS.md files, agent prompts, system prompts.

Use when creating or updating AGENTS.md context files for projects or subdirectories - covers top-level vs domain-level organization, capturing architectural intent and contracts, and mandatory freshness dates

Use when creating new skills, editing existing skills, or verifying skills work before deployment - applies TDD to process documentation by testing with subagents before writing, iterating until bulletproof against rationalization