seed-test-data

Installation
SKILL.md

Codex compatibility note:

  • Invoke $skill-name: load the registered .agents/skills/<name>/SKILL.md and execute it with Codex tools; no separate Skill tool 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_agent subagent(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

Review modes: For review/audit work, standalone defaults to --review-only (--report-only alias); --fix-loop enables review → validate → authorized fix → fresh re-review, default cap 3. --fix-loop --loop-owner=caller returns a read-only pass to the caller that owns fixes/re-review. Create triage, review, validation and re-review todo tasks first; apply the carried review-policy contract for LOW deferral and user-approved bounded extensions. Non-review modes and terminal findings validation keep their own dispatch.

Goal: Build configurable local-development seeders that exercise happy paths through public application commands, produce realistic QC/performance data, and remain idempotent and restart-safe.

Summary: Follow the existing seeder convention; gate the environment first; use a small configurable count, public commands and a fresh DI scope per iteration. Generate: classify → discover conventions → verify dev config → analyze scenarios → locate seeder → implement → validate → self-audit → fresh review → final review handoff → lessons. Review: resolve target → read conventions → grade → report/hand off → lessons; no edits.

Workflow: Use Generate by default. A --mode=review flag or a request to review/audit/check a seeder selects the read-only audit below.

Key Rules:

Installs
2
GitHub Stars
3
First Seen
13 days ago