agent-loop-ext
Crash-resilient external agent loop with state persistence and CI/CD integration
Regenerate the canonical WORKSPACE.md-first context graph and provider adapters
$ npx -y skills add jmagly/aiwg --skill aiwg-regenerate-workspace --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
/aiwg-regenerate-workspaceContext preview
The summary Claude sees to decide when to auto-load this skill.
Regenerate the canonical WORKSPACE.md-first context graph and provider adapters
namespace: aiwg name: aiwg-regenerate-workspace platforms: [all] kernel: true description: Regenerate the canonical WORKSPACE.md-first context graph and provider adapters commandHint: argumentHint: "[--provider <name>] [--dry-run] [--force]" allowedTools: Bash, Read model: haiku category: maintenance modelRole: efficiency modelTier: economy
Use this default branch for new and migrated projects. It maintains the precedence chain:
1. `WORKSPACE.md` — provider-neutral project and operator context. 2. `AIWG.md` — generated framework discovery and routing context. 3. Provider startup adapters — minimal pointers that load or direct readers to those files in order.
For an established project, audit before adopting the graph:
aiwg workspace-context audit --json aiwg workspace-context migrate --dry-run --json aiwg workspace-context migrate --apply aiwg regenerate --workspace aiwg workspace-context doctor
Migration is transactional and records recoverable preimages under `.aiwg/context-migrations/`. It refuses possible credential values and unresolved directive conflicts. Use [aiwg-regenerate-legacy](../aiwg-regenerate-legacy/SKILL.md) only when compatibility requires inline context.
Reusable project context and specialist workflows for the AI tools you already use. Plan software, coordinate specialist reviews, prepare campaigns, investigate incidents, organize research, curate media, and maintain operational knowledge.
Repo: jmagly/aiwg
Crash-resilient external agent loop with state persistence and CI/CD integration
Detect requests for iterative autonomous agent loops and route to the appropriate loop executor
Automatically execute tests when code-generating agents modify source files, enforcing the execute-before-return pattern
Enable agent loops to learn from similar past tasks and share patterns across loops
Query and manage the executable feedback debug memory
Execute tests on generated code and iterate until passing