agent-loop-ext
Crash-resilient external agent loop with state persistence and CI/CD integration
Tier-3 steward routing reference lookup for full CLI tables, deploy paths, issue/project-local routing, orchestration routes, diagnostics, and provider capability examples
$ npx -y skills add jmagly/aiwg --skill aiwg-steward-routing-reference --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
/aiwg-steward-routing-referenceContext preview
The summary Claude sees to decide when to auto-load this skill.
Tier-3 steward routing reference lookup for full CLI tables, deploy paths, issue/project-local routing, orchestration routes, diagnostics, and provider capability examples
name: aiwg-steward-routing-reference namespace: aiwg description: Tier-3 steward routing reference lookup for full CLI tables, deploy paths, issue/project-local routing, orchestration routes, diagnostics, and provider capability examples platforms: [all] triggers: - aiwg-steward routing reference - steward routing reference - steward tier 3 routing - steward full routing tables - aiwg steward lookup tables
Tier-3 reference for `aiwg-steward`. Use this only after the Tier-1 steward definition or `steward-quickref` points here.
Read the full reference at:
`agentic/code/addons/aiwg-utils/docs/agent-examples/aiwg-steward-routing-reference.md`
If this reference contradicts current CLI output, retry once with a broader discover phrase, run the steward repair ladder for stale discovery when appropriate, then file an AIWG correction issue with the stale target and observed command output.
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