agent-loop-ext
Crash-resilient external agent loop with state persistence and CI/CD integration
Scaffold a project-local extension, addon, framework, plugin, or provider bundle under the configured AIWG artifact root.
$ npx -y skills add jmagly/aiwg --skill new-bundle --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
/new-bundleContext preview
The summary Claude sees to decide when to auto-load this skill.
Scaffold a project-local extension, addon, framework, plugin, or provider bundle under the configured AIWG artifact root.
namespace: aiwg name: new-bundle platforms: [all] description: Scaffold a project-local extension, addon, framework, plugin, or provider bundle under the configured AIWG artifact root. triggers: - new-bundle - new bundle - scaffold project-local - create project-local bundle - project-local bundle - new extension - new addon - new provider
Create a version-controlled project-local bundle under `.aiwg/`.
1. Determine the bundle name and type. 2. Select an optional starter artifact. 3. Preview when requested, then run:
aiwg new-bundle <name> \
[--type extension|addon|framework|plugin|provider] \
[--starter skill|rule|agent|minimal] \
[--description "..."] \
[--dry-run]4. Deploy the completed bundle with `aiwg use <name>`. 5. Validate project-local health with `aiwg doctor`. 6. When the bundle is ready to graduate, use `aiwg promote <name> --dry-run`.
The default type is `extension`; the default starter is `skill`. The aliases `new-extension`, `new-addon`, `new-framework`, `new-plugin`, and `new-provider` select their corresponding type.
generated artifacts.
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