scan-all
Installation
SKILL.md
Codex compatibility note:
- Invoke
$skill-name: load the registered.agents/skills/<name>/SKILL.mdand execute it with Codex tools; no separateSkilltool or Claude mode switch is needed. When a workflow step or another skill names a skill, read that file in full yourself (every line, with no line limit; in parts only when output is cut off): a skill whose implicit invocation is off is never loaded for you. Author.claude/**; mirrors are generated.- Track steps before execution and keep progress/evidence current. Explicit skill requests execute their protocol. Use the native question tool for required questions.
- Map foreign tool names to available host capabilities. A name mismatch needs no approval; an actually unavailable required capability stops with its step/evidence and a user question before adaptation.
- Subagent authorization: when a skill is user-invoked or AI-detected and its protocol requires subagents, that skill activation authorizes use of the required
spawn_agentsubagent(s) for that task.- Preserve protocol order unless the user approves a deviation. Workflows use
$start-workflow: gates stay fixed; other steps may flex with logged reasons and evidence.
Quick Summary
Goal: Refresh selected, evidence-applicable built-in and explicitly generic custom reference docs while preserving truthful freshness and project ownership.
Summary: Resolve config and exact selection → classify ownership and capability → run disjoint scans → reconcile results and freshness → report. Keep always-on inputs separate; unsupported capabilities and manual docs receive explicit dispositions. Graph refresh remains conditional.
Workflow:
- Validate — Support absent config; validate present config and use the runtime evidence-based resolver.
- Resolve — Read always-on inputs separately and resolve the effective task-specific
referenceDocsselection. - Filter — Resolve exact built-in targets, selected generic custom docs, and manually owned docs; verify capability evidence for each scan.
- Scan — Run eligible targets in parallel only when their output write sets are disjoint.
- Summarize — Report refreshed, unchanged, skipped, blocked, and manual docs with evidence.