agent-loop-ext
Crash-resilient external agent loop with state persistence and CI/CD integration
Evaluate source access, rights, robots, authorization, provenance, and freshness before automated acquisition or public reuse.
$ npx -y skills add jmagly/aiwg --skill source-compliance-gate --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
/source-compliance-gateContext preview
The summary Claude sees to decide when to auto-load this skill.
Evaluate source access, rights, robots, authorization, provenance, and freshness before automated acquisition or public reuse.
namespace: aiwg platforms: [all] name: source-compliance-gate description: Evaluate source access, rights, robots, authorization, provenance, and freshness before automated acquisition or public reuse. script: entrypoint: scripts/source_compliance_gate.mjs runtime: node cwd: project-root argsHint: "<source-registry.json>" triggers: - check whether a public source may be acquired - validate a civic source registry - review robots terms license and freshness
1. Create a versioned source registry from `templates/source-registry.yaml`. Record owner, URL, API/feed/HTML/browser/OCR/manual-export/records/skip method, cadence, decision state, citation format, fallback, and provenance. 2. Run `aiwg run skill source-compliance-gate -- registry.json`. 3. Stop automated collection on prohibited/unknown terms, robots error or disallow, authorization uncertainty, control bypass, or expired approval. 4. Route jurisdiction, terms, license, and publication rights to a named human. 5. Compare observed and minimum records. An empty or under-count result follows the declared block/warn/authoritative-empty policy and never silently erases the reviewed last-good copy.
The executable emits a `compliance-gate-result` JSON report and exit `1` when any blocking result exists. It validates observed fields; it does not decide law, contractual permission, or fair use.
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