@cubis/foundry 0.3.82 → 0.3.83

package/workflows/workflows/agent-environment-setup/platforms/claude/skills/rust-best-practices/SKILL.md

@@ -83,5 +83,12 @@ No helper scripts are required for this skill right now. Keep execution in `SKIL
 - Use `$ARGUMENTS` to access user-provided arguments passed when the skill is invoked.
 - Reference skill-local files with `${CLAUDE_SKILL_DIR}/references/<file>` for portable paths.
 - When `context: fork` is set, the skill runs in an isolated subagent context; the `agent` field names the fork target.
+- Custom subagents in `.claude/agents/*.md` support YAML frontmatter: `name`, `description`, `tools`, `model`, `maxTurns`, `memory`, `handoffs`.
+- Use `model` field in agent frontmatter to select model per subagent (e.g., `model: opus` for complex analysis).
+- Set `maxTurns` to prevent runaway iterations (default: 25, orchestrator: 30).
+- Key agents support `memory: project` for cross-session learning (orchestrator, debugger, researcher, project-planner).
+- Hook templates in `.claude/hooks/` provide lifecycle event integration at `UserPromptSubmit` and other events.
+- Path-scoped rules: `.claude/rules/*.md` with `paths:` frontmatter for targeted guidance.
 - MCP skill tools (`skill_search`, `skill_get`, `skill_validate`, `skill_get_reference`) are available for dynamic skill discovery and loading.
 - Use `allowed-tools` in frontmatter to restrict tool access for security-sensitive skills.
+- Workflow skills can be compiled to `.claude/skills/<workflow-id>/SKILL.md` as `generatedSkills`.

package/workflows/workflows/agent-environment-setup/platforms/claude/skills/sadd/SKILL.md

@@ -66,5 +66,12 @@ When performing SADD, provide:
 - Use `$ARGUMENTS` to access user-provided arguments passed when the skill is invoked.
 - Reference skill-local files with `${CLAUDE_SKILL_DIR}/references/<file>` for portable paths.
 - When `context: fork` is set, the skill runs in an isolated subagent context; the `agent` field names the fork target.
+- Custom subagents in `.claude/agents/*.md` support YAML frontmatter: `name`, `description`, `tools`, `model`, `maxTurns`, `memory`, `handoffs`.
+- Use `model` field in agent frontmatter to select model per subagent (e.g., `model: opus` for complex analysis).
+- Set `maxTurns` to prevent runaway iterations (default: 25, orchestrator: 30).
+- Key agents support `memory: project` for cross-session learning (orchestrator, debugger, researcher, project-planner).
+- Hook templates in `.claude/hooks/` provide lifecycle event integration at `UserPromptSubmit` and other events.
+- Path-scoped rules: `.claude/rules/*.md` with `paths:` frontmatter for targeted guidance.
 - MCP skill tools (`skill_search`, `skill_get`, `skill_validate`, `skill_get_reference`) are available for dynamic skill discovery and loading.
 - Use `allowed-tools` in frontmatter to restrict tool access for security-sensitive skills.
+- Workflow skills can be compiled to `.claude/skills/<workflow-id>/SKILL.md` as `generatedSkills`.

package/workflows/workflows/agent-environment-setup/platforms/claude/skills/sanitize-pii/SKILL.md

@@ -102,5 +102,12 @@ Guide the detection, classification, and sanitization of personally identifiable
 - Use `$ARGUMENTS` to access user-provided arguments passed when the skill is invoked.
 - Reference skill-local files with `${CLAUDE_SKILL_DIR}/references/<file>` for portable paths.
 - When `context: fork` is set, the skill runs in an isolated subagent context; the `agent` field names the fork target.
+- Custom subagents in `.claude/agents/*.md` support YAML frontmatter: `name`, `description`, `tools`, `model`, `maxTurns`, `memory`, `handoffs`.
+- Use `model` field in agent frontmatter to select model per subagent (e.g., `model: opus` for complex analysis).
+- Set `maxTurns` to prevent runaway iterations (default: 25, orchestrator: 30).
+- Key agents support `memory: project` for cross-session learning (orchestrator, debugger, researcher, project-planner).
+- Hook templates in `.claude/hooks/` provide lifecycle event integration at `UserPromptSubmit` and other events.
+- Path-scoped rules: `.claude/rules/*.md` with `paths:` frontmatter for targeted guidance.
 - MCP skill tools (`skill_search`, `skill_get`, `skill_validate`, `skill_get_reference`) are available for dynamic skill discovery and loading.
 - Use `allowed-tools` in frontmatter to restrict tool access for security-sensitive skills.
+- Workflow skills can be compiled to `.claude/skills/<workflow-id>/SKILL.md` as `generatedSkills`.

package/workflows/workflows/agent-environment-setup/platforms/claude/skills/secret-management/SKILL.md

@@ -99,5 +99,12 @@ Guide the design and implementation of robust secret and credential management s
 - Use `$ARGUMENTS` to access user-provided arguments passed when the skill is invoked.
 - Reference skill-local files with `${CLAUDE_SKILL_DIR}/references/<file>` for portable paths.
 - When `context: fork` is set, the skill runs in an isolated subagent context; the `agent` field names the fork target.
+- Custom subagents in `.claude/agents/*.md` support YAML frontmatter: `name`, `description`, `tools`, `model`, `maxTurns`, `memory`, `handoffs`.
+- Use `model` field in agent frontmatter to select model per subagent (e.g., `model: opus` for complex analysis).
+- Set `maxTurns` to prevent runaway iterations (default: 25, orchestrator: 30).
+- Key agents support `memory: project` for cross-session learning (orchestrator, debugger, researcher, project-planner).
+- Hook templates in `.claude/hooks/` provide lifecycle event integration at `UserPromptSubmit` and other events.
+- Path-scoped rules: `.claude/rules/*.md` with `paths:` frontmatter for targeted guidance.
 - MCP skill tools (`skill_search`, `skill_get`, `skill_validate`, `skill_get_reference`) are available for dynamic skill discovery and loading.
 - Use `allowed-tools` in frontmatter to restrict tool access for security-sensitive skills.
+- Workflow skills can be compiled to `.claude/skills/<workflow-id>/SKILL.md` as `generatedSkills`.

package/workflows/workflows/agent-environment-setup/platforms/claude/skills/skill-creator/SKILL.md

@@ -162,5 +162,12 @@ skill-creator
 - Use `$ARGUMENTS` to access user-provided arguments passed when the skill is invoked.
 - Reference skill-local files with `${CLAUDE_SKILL_DIR}/references/<file>` for portable paths.
 - When `context: fork` is set, the skill runs in an isolated subagent context; the `agent` field names the fork target.
+- Custom subagents in `.claude/agents/*.md` support YAML frontmatter: `name`, `description`, `tools`, `model`, `maxTurns`, `memory`, `handoffs`.
+- Use `model` field in agent frontmatter to select model per subagent (e.g., `model: opus` for complex analysis).
+- Set `maxTurns` to prevent runaway iterations (default: 25, orchestrator: 30).
+- Key agents support `memory: project` for cross-session learning (orchestrator, debugger, researcher, project-planner).
+- Hook templates in `.claude/hooks/` provide lifecycle event integration at `UserPromptSubmit` and other events.
+- Path-scoped rules: `.claude/rules/*.md` with `paths:` frontmatter for targeted guidance.
 - MCP skill tools (`skill_search`, `skill_get`, `skill_validate`, `skill_get_reference`) are available for dynamic skill discovery and loading.
 - Use `allowed-tools` in frontmatter to restrict tool access for security-sensitive skills.
+- Workflow skills can be compiled to `.claude/skills/<workflow-id>/SKILL.md` as `generatedSkills`.

package/workflows/workflows/agent-environment-setup/platforms/claude/skills/spec-driven-delivery/SKILL.md

@@ -62,5 +62,12 @@ Deliver:
 - Use `$ARGUMENTS` to access user-provided arguments passed when the skill is invoked.
 - Reference skill-local files with `${CLAUDE_SKILL_DIR}/references/<file>` for portable paths.
 - When `context: fork` is set, the skill runs in an isolated subagent context; the `agent` field names the fork target.
+- Custom subagents in `.claude/agents/*.md` support YAML frontmatter: `name`, `description`, `tools`, `model`, `maxTurns`, `memory`, `handoffs`.
+- Use `model` field in agent frontmatter to select model per subagent (e.g., `model: opus` for complex analysis).
+- Set `maxTurns` to prevent runaway iterations (default: 25, orchestrator: 30).
+- Key agents support `memory: project` for cross-session learning (orchestrator, debugger, researcher, project-planner).
+- Hook templates in `.claude/hooks/` provide lifecycle event integration at `UserPromptSubmit` and other events.
+- Path-scoped rules: `.claude/rules/*.md` with `paths:` frontmatter for targeted guidance.
 - MCP skill tools (`skill_search`, `skill_get`, `skill_validate`, `skill_get_reference`) are available for dynamic skill discovery and loading.
 - Use `allowed-tools` in frontmatter to restrict tool access for security-sensitive skills.
+- Workflow skills can be compiled to `.claude/skills/<workflow-id>/SKILL.md` as `generatedSkills`.

package/workflows/workflows/agent-environment-setup/platforms/claude/skills/spring-boot/SKILL.md

@@ -74,5 +74,12 @@ Provide implementation code, configuration properties, bean definitions, and arc
 - Use `$ARGUMENTS` to access user-provided arguments passed when the skill is invoked.
 - Reference skill-local files with `${CLAUDE_SKILL_DIR}/references/<file>` for portable paths.
 - When `context: fork` is set, the skill runs in an isolated subagent context; the `agent` field names the fork target.
+- Custom subagents in `.claude/agents/*.md` support YAML frontmatter: `name`, `description`, `tools`, `model`, `maxTurns`, `memory`, `handoffs`.
+- Use `model` field in agent frontmatter to select model per subagent (e.g., `model: opus` for complex analysis).
+- Set `maxTurns` to prevent runaway iterations (default: 25, orchestrator: 30).
+- Key agents support `memory: project` for cross-session learning (orchestrator, debugger, researcher, project-planner).
+- Hook templates in `.claude/hooks/` provide lifecycle event integration at `UserPromptSubmit` and other events.
+- Path-scoped rules: `.claude/rules/*.md` with `paths:` frontmatter for targeted guidance.
 - MCP skill tools (`skill_search`, `skill_get`, `skill_validate`, `skill_get_reference`) are available for dynamic skill discovery and loading.
 - Use `allowed-tools` in frontmatter to restrict tool access for security-sensitive skills.
+- Workflow skills can be compiled to `.claude/skills/<workflow-id>/SKILL.md` as `generatedSkills`.

package/workflows/workflows/agent-environment-setup/platforms/claude/skills/sqlalchemy/SKILL.md

@@ -83,5 +83,12 @@ No helper scripts are required for this skill right now. Keep execution in `SKIL
 - Use `$ARGUMENTS` to access user-provided arguments passed when the skill is invoked.
 - Reference skill-local files with `${CLAUDE_SKILL_DIR}/references/<file>` for portable paths.
 - When `context: fork` is set, the skill runs in an isolated subagent context; the `agent` field names the fork target.
+- Custom subagents in `.claude/agents/*.md` support YAML frontmatter: `name`, `description`, `tools`, `model`, `maxTurns`, `memory`, `handoffs`.
+- Use `model` field in agent frontmatter to select model per subagent (e.g., `model: opus` for complex analysis).
+- Set `maxTurns` to prevent runaway iterations (default: 25, orchestrator: 30).
+- Key agents support `memory: project` for cross-session learning (orchestrator, debugger, researcher, project-planner).
+- Hook templates in `.claude/hooks/` provide lifecycle event integration at `UserPromptSubmit` and other events.
+- Path-scoped rules: `.claude/rules/*.md` with `paths:` frontmatter for targeted guidance.
 - MCP skill tools (`skill_search`, `skill_get`, `skill_validate`, `skill_get_reference`) are available for dynamic skill discovery and loading.
 - Use `allowed-tools` in frontmatter to restrict tool access for security-sensitive skills.
+- Workflow skills can be compiled to `.claude/skills/<workflow-id>/SKILL.md` as `generatedSkills`.

package/workflows/workflows/agent-environment-setup/platforms/claude/skills/stitch/SKILL.md

@@ -89,5 +89,12 @@ Use these when the task closely matches the example shape.
 - Use `$ARGUMENTS` to access user-provided arguments passed when the skill is invoked.
 - Reference skill-local files with `${CLAUDE_SKILL_DIR}/references/<file>` for portable paths.
 - When `context: fork` is set, the skill runs in an isolated subagent context; the `agent` field names the fork target.
+- Custom subagents in `.claude/agents/*.md` support YAML frontmatter: `name`, `description`, `tools`, `model`, `maxTurns`, `memory`, `handoffs`.
+- Use `model` field in agent frontmatter to select model per subagent (e.g., `model: opus` for complex analysis).
+- Set `maxTurns` to prevent runaway iterations (default: 25, orchestrator: 30).
+- Key agents support `memory: project` for cross-session learning (orchestrator, debugger, researcher, project-planner).
+- Hook templates in `.claude/hooks/` provide lifecycle event integration at `UserPromptSubmit` and other events.
+- Path-scoped rules: `.claude/rules/*.md` with `paths:` frontmatter for targeted guidance.
 - MCP skill tools (`skill_search`, `skill_get`, `skill_validate`, `skill_get_reference`) are available for dynamic skill discovery and loading.
 - Use `allowed-tools` in frontmatter to restrict tool access for security-sensitive skills.
+- Workflow skills can be compiled to `.claude/skills/<workflow-id>/SKILL.md` as `generatedSkills`.

package/workflows/workflows/agent-environment-setup/platforms/claude/skills/stripe-integration/SKILL.md

@@ -90,5 +90,12 @@ Guide the design and implementation of production-grade Stripe payment integrati
 - Use `$ARGUMENTS` to access user-provided arguments passed when the skill is invoked.
 - Reference skill-local files with `${CLAUDE_SKILL_DIR}/references/<file>` for portable paths.
 - When `context: fork` is set, the skill runs in an isolated subagent context; the `agent` field names the fork target.
+- Custom subagents in `.claude/agents/*.md` support YAML frontmatter: `name`, `description`, `tools`, `model`, `maxTurns`, `memory`, `handoffs`.
+- Use `model` field in agent frontmatter to select model per subagent (e.g., `model: opus` for complex analysis).
+- Set `maxTurns` to prevent runaway iterations (default: 25, orchestrator: 30).
+- Key agents support `memory: project` for cross-session learning (orchestrator, debugger, researcher, project-planner).
+- Hook templates in `.claude/hooks/` provide lifecycle event integration at `UserPromptSubmit` and other events.
+- Path-scoped rules: `.claude/rules/*.md` with `paths:` frontmatter for targeted guidance.
 - MCP skill tools (`skill_search`, `skill_get`, `skill_validate`, `skill_get_reference`) are available for dynamic skill discovery and loading.
 - Use `allowed-tools` in frontmatter to restrict tool access for security-sensitive skills.
+- Workflow skills can be compiled to `.claude/skills/<workflow-id>/SKILL.md` as `generatedSkills`.

package/workflows/workflows/agent-environment-setup/platforms/claude/skills/svelte-sveltekit/SKILL.md

@@ -86,5 +86,12 @@ Load detailed guidance based on context:
 - Use `$ARGUMENTS` to access user-provided arguments passed when the skill is invoked.
 - Reference skill-local files with `${CLAUDE_SKILL_DIR}/references/<file>` for portable paths.
 - When `context: fork` is set, the skill runs in an isolated subagent context; the `agent` field names the fork target.
+- Custom subagents in `.claude/agents/*.md` support YAML frontmatter: `name`, `description`, `tools`, `model`, `maxTurns`, `memory`, `handoffs`.
+- Use `model` field in agent frontmatter to select model per subagent (e.g., `model: opus` for complex analysis).
+- Set `maxTurns` to prevent runaway iterations (default: 25, orchestrator: 30).
+- Key agents support `memory: project` for cross-session learning (orchestrator, debugger, researcher, project-planner).
+- Hook templates in `.claude/hooks/` provide lifecycle event integration at `UserPromptSubmit` and other events.
+- Path-scoped rules: `.claude/rules/*.md` with `paths:` frontmatter for targeted guidance.
 - MCP skill tools (`skill_search`, `skill_get`, `skill_validate`, `skill_get_reference`) are available for dynamic skill discovery and loading.
 - Use `allowed-tools` in frontmatter to restrict tool access for security-sensitive skills.
+- Workflow skills can be compiled to `.claude/skills/<workflow-id>/SKILL.md` as `generatedSkills`.

package/workflows/workflows/agent-environment-setup/platforms/claude/skills/swift-best-practices/SKILL.md

@@ -87,5 +87,12 @@ No helper scripts are required for this skill right now. Keep execution in `SKIL
 - Use `$ARGUMENTS` to access user-provided arguments passed when the skill is invoked.
 - Reference skill-local files with `${CLAUDE_SKILL_DIR}/references/<file>` for portable paths.
 - When `context: fork` is set, the skill runs in an isolated subagent context; the `agent` field names the fork target.
+- Custom subagents in `.claude/agents/*.md` support YAML frontmatter: `name`, `description`, `tools`, `model`, `maxTurns`, `memory`, `handoffs`.
+- Use `model` field in agent frontmatter to select model per subagent (e.g., `model: opus` for complex analysis).
+- Set `maxTurns` to prevent runaway iterations (default: 25, orchestrator: 30).
+- Key agents support `memory: project` for cross-session learning (orchestrator, debugger, researcher, project-planner).
+- Hook templates in `.claude/hooks/` provide lifecycle event integration at `UserPromptSubmit` and other events.
+- Path-scoped rules: `.claude/rules/*.md` with `paths:` frontmatter for targeted guidance.
 - MCP skill tools (`skill_search`, `skill_get`, `skill_validate`, `skill_get_reference`) are available for dynamic skill discovery and loading.
 - Use `allowed-tools` in frontmatter to restrict tool access for security-sensitive skills.
+- Workflow skills can be compiled to `.claude/skills/<workflow-id>/SKILL.md` as `generatedSkills`.

package/workflows/workflows/agent-environment-setup/platforms/claude/skills/system-design/SKILL.md

@@ -82,5 +82,12 @@ Load only what the current task requires.
 - Use `$ARGUMENTS` to access user-provided arguments passed when the skill is invoked.
 - Reference skill-local files with `${CLAUDE_SKILL_DIR}/references/<file>` for portable paths.
 - When `context: fork` is set, the skill runs in an isolated subagent context; the `agent` field names the fork target.
+- Custom subagents in `.claude/agents/*.md` support YAML frontmatter: `name`, `description`, `tools`, `model`, `maxTurns`, `memory`, `handoffs`.
+- Use `model` field in agent frontmatter to select model per subagent (e.g., `model: opus` for complex analysis).
+- Set `maxTurns` to prevent runaway iterations (default: 25, orchestrator: 30).
+- Key agents support `memory: project` for cross-session learning (orchestrator, debugger, researcher, project-planner).
+- Hook templates in `.claude/hooks/` provide lifecycle event integration at `UserPromptSubmit` and other events.
+- Path-scoped rules: `.claude/rules/*.md` with `paths:` frontmatter for targeted guidance.
 - MCP skill tools (`skill_search`, `skill_get`, `skill_validate`, `skill_get_reference`) are available for dynamic skill discovery and loading.
 - Use `allowed-tools` in frontmatter to restrict tool access for security-sensitive skills.
+- Workflow skills can be compiled to `.claude/skills/<workflow-id>/SKILL.md` as `generatedSkills`.

package/workflows/workflows/agent-environment-setup/platforms/claude/skills/systematic-debugging/SKILL.md

@@ -119,5 +119,12 @@ Provide a disciplined, evidence-based framework for diagnosing and resolving sof
 - Use `$ARGUMENTS` to access user-provided arguments passed when the skill is invoked.
 - Reference skill-local files with `${CLAUDE_SKILL_DIR}/references/<file>` for portable paths.
 - When `context: fork` is set, the skill runs in an isolated subagent context; the `agent` field names the fork target.
+- Custom subagents in `.claude/agents/*.md` support YAML frontmatter: `name`, `description`, `tools`, `model`, `maxTurns`, `memory`, `handoffs`.
+- Use `model` field in agent frontmatter to select model per subagent (e.g., `model: opus` for complex analysis).
+- Set `maxTurns` to prevent runaway iterations (default: 25, orchestrator: 30).
+- Key agents support `memory: project` for cross-session learning (orchestrator, debugger, researcher, project-planner).
+- Hook templates in `.claude/hooks/` provide lifecycle event integration at `UserPromptSubmit` and other events.
+- Path-scoped rules: `.claude/rules/*.md` with `paths:` frontmatter for targeted guidance.
 - MCP skill tools (`skill_search`, `skill_get`, `skill_validate`, `skill_get_reference`) are available for dynamic skill discovery and loading.
 - Use `allowed-tools` in frontmatter to restrict tool access for security-sensitive skills.
+- Workflow skills can be compiled to `.claude/skills/<workflow-id>/SKILL.md` as `generatedSkills`.

package/workflows/workflows/agent-environment-setup/platforms/claude/skills/t3-stack/SKILL.md

@@ -78,5 +78,12 @@ Provide implementation code, schema definitions, configuration snippets, and arc
 - Use `$ARGUMENTS` to access user-provided arguments passed when the skill is invoked.
 - Reference skill-local files with `${CLAUDE_SKILL_DIR}/references/<file>` for portable paths.
 - When `context: fork` is set, the skill runs in an isolated subagent context; the `agent` field names the fork target.
+- Custom subagents in `.claude/agents/*.md` support YAML frontmatter: `name`, `description`, `tools`, `model`, `maxTurns`, `memory`, `handoffs`.
+- Use `model` field in agent frontmatter to select model per subagent (e.g., `model: opus` for complex analysis).
+- Set `maxTurns` to prevent runaway iterations (default: 25, orchestrator: 30).
+- Key agents support `memory: project` for cross-session learning (orchestrator, debugger, researcher, project-planner).
+- Hook templates in `.claude/hooks/` provide lifecycle event integration at `UserPromptSubmit` and other events.
+- Path-scoped rules: `.claude/rules/*.md` with `paths:` frontmatter for targeted guidance.
 - MCP skill tools (`skill_search`, `skill_get`, `skill_validate`, `skill_get_reference`) are available for dynamic skill discovery and loading.
 - Use `allowed-tools` in frontmatter to restrict tool access for security-sensitive skills.
+- Workflow skills can be compiled to `.claude/skills/<workflow-id>/SKILL.md` as `generatedSkills`.

package/workflows/workflows/agent-environment-setup/platforms/claude/skills/tech-doc/SKILL.md

@@ -81,5 +81,12 @@ Load on demand. Do not preload all reference files.
 - Use `$ARGUMENTS` to access user-provided arguments passed when the skill is invoked.
 - Reference skill-local files with `${CLAUDE_SKILL_DIR}/references/<file>` for portable paths.
 - When `context: fork` is set, the skill runs in an isolated subagent context; the `agent` field names the fork target.
+- Custom subagents in `.claude/agents/*.md` support YAML frontmatter: `name`, `description`, `tools`, `model`, `maxTurns`, `memory`, `handoffs`.
+- Use `model` field in agent frontmatter to select model per subagent (e.g., `model: opus` for complex analysis).
+- Set `maxTurns` to prevent runaway iterations (default: 25, orchestrator: 30).
+- Key agents support `memory: project` for cross-session learning (orchestrator, debugger, researcher, project-planner).
+- Hook templates in `.claude/hooks/` provide lifecycle event integration at `UserPromptSubmit` and other events.
+- Path-scoped rules: `.claude/rules/*.md` with `paths:` frontmatter for targeted guidance.
 - MCP skill tools (`skill_search`, `skill_get`, `skill_validate`, `skill_get_reference`) are available for dynamic skill discovery and loading.
 - Use `allowed-tools` in frontmatter to restrict tool access for security-sensitive skills.
+- Workflow skills can be compiled to `.claude/skills/<workflow-id>/SKILL.md` as `generatedSkills`.

package/workflows/workflows/agent-environment-setup/platforms/claude/skills/typescript-best-practices/SKILL.md

@@ -83,5 +83,12 @@ No helper scripts are required for this skill right now. Keep execution in `SKIL
 - Use `$ARGUMENTS` to access user-provided arguments passed when the skill is invoked.
 - Reference skill-local files with `${CLAUDE_SKILL_DIR}/references/<file>` for portable paths.
 - When `context: fork` is set, the skill runs in an isolated subagent context; the `agent` field names the fork target.
+- Custom subagents in `.claude/agents/*.md` support YAML frontmatter: `name`, `description`, `tools`, `model`, `maxTurns`, `memory`, `handoffs`.
+- Use `model` field in agent frontmatter to select model per subagent (e.g., `model: opus` for complex analysis).
+- Set `maxTurns` to prevent runaway iterations (default: 25, orchestrator: 30).
+- Key agents support `memory: project` for cross-session learning (orchestrator, debugger, researcher, project-planner).
+- Hook templates in `.claude/hooks/` provide lifecycle event integration at `UserPromptSubmit` and other events.
+- Path-scoped rules: `.claude/rules/*.md` with `paths:` frontmatter for targeted guidance.
 - MCP skill tools (`skill_search`, `skill_get`, `skill_validate`, `skill_get_reference`) are available for dynamic skill discovery and loading.
 - Use `allowed-tools` in frontmatter to restrict tool access for security-sensitive skills.
+- Workflow skills can be compiled to `.claude/skills/<workflow-id>/SKILL.md` as `generatedSkills`.

package/workflows/workflows/agent-environment-setup/platforms/claude/skills/unit-testing/SKILL.md

@@ -102,5 +102,12 @@ Provide a rigorous, repeatable methodology for designing, writing, and maintaini
 - Use `$ARGUMENTS` to access user-provided arguments passed when the skill is invoked.
 - Reference skill-local files with `${CLAUDE_SKILL_DIR}/references/<file>` for portable paths.
 - When `context: fork` is set, the skill runs in an isolated subagent context; the `agent` field names the fork target.
+- Custom subagents in `.claude/agents/*.md` support YAML frontmatter: `name`, `description`, `tools`, `model`, `maxTurns`, `memory`, `handoffs`.
+- Use `model` field in agent frontmatter to select model per subagent (e.g., `model: opus` for complex analysis).
+- Set `maxTurns` to prevent runaway iterations (default: 25, orchestrator: 30).
+- Key agents support `memory: project` for cross-session learning (orchestrator, debugger, researcher, project-planner).
+- Hook templates in `.claude/hooks/` provide lifecycle event integration at `UserPromptSubmit` and other events.
+- Path-scoped rules: `.claude/rules/*.md` with `paths:` frontmatter for targeted guidance.
 - MCP skill tools (`skill_search`, `skill_get`, `skill_validate`, `skill_get_reference`) are available for dynamic skill discovery and loading.
 - Use `allowed-tools` in frontmatter to restrict tool access for security-sensitive skills.
+- Workflow skills can be compiled to `.claude/skills/<workflow-id>/SKILL.md` as `generatedSkills`.

package/workflows/workflows/agent-environment-setup/platforms/claude/skills/vibesec/SKILL.md

@@ -96,5 +96,12 @@ Deliver a fast, opinionated security assessment that catches the most common and
 - Use `$ARGUMENTS` to access user-provided arguments passed when the skill is invoked.
 - Reference skill-local files with `${CLAUDE_SKILL_DIR}/references/<file>` for portable paths.
 - When `context: fork` is set, the skill runs in an isolated subagent context; the `agent` field names the fork target.
+- Custom subagents in `.claude/agents/*.md` support YAML frontmatter: `name`, `description`, `tools`, `model`, `maxTurns`, `memory`, `handoffs`.
+- Use `model` field in agent frontmatter to select model per subagent (e.g., `model: opus` for complex analysis).
+- Set `maxTurns` to prevent runaway iterations (default: 25, orchestrator: 30).
+- Key agents support `memory: project` for cross-session learning (orchestrator, debugger, researcher, project-planner).
+- Hook templates in `.claude/hooks/` provide lifecycle event integration at `UserPromptSubmit` and other events.
+- Path-scoped rules: `.claude/rules/*.md` with `paths:` frontmatter for targeted guidance.
 - MCP skill tools (`skill_search`, `skill_get`, `skill_validate`, `skill_get_reference`) are available for dynamic skill discovery and loading.
 - Use `allowed-tools` in frontmatter to restrict tool access for security-sensitive skills.
+- Workflow skills can be compiled to `.claude/skills/<workflow-id>/SKILL.md` as `generatedSkills`.

package/workflows/workflows/agent-environment-setup/platforms/claude/skills/vuejs/SKILL.md

@@ -87,5 +87,12 @@ Load detailed guidance based on context:
 - Use `$ARGUMENTS` to access user-provided arguments passed when the skill is invoked.
 - Reference skill-local files with `${CLAUDE_SKILL_DIR}/references/<file>` for portable paths.
 - When `context: fork` is set, the skill runs in an isolated subagent context; the `agent` field names the fork target.
+- Custom subagents in `.claude/agents/*.md` support YAML frontmatter: `name`, `description`, `tools`, `model`, `maxTurns`, `memory`, `handoffs`.
+- Use `model` field in agent frontmatter to select model per subagent (e.g., `model: opus` for complex analysis).
+- Set `maxTurns` to prevent runaway iterations (default: 25, orchestrator: 30).
+- Key agents support `memory: project` for cross-session learning (orchestrator, debugger, researcher, project-planner).
+- Hook templates in `.claude/hooks/` provide lifecycle event integration at `UserPromptSubmit` and other events.
+- Path-scoped rules: `.claude/rules/*.md` with `paths:` frontmatter for targeted guidance.
 - MCP skill tools (`skill_search`, `skill_get`, `skill_validate`, `skill_get_reference`) are available for dynamic skill discovery and loading.
 - Use `allowed-tools` in frontmatter to restrict tool access for security-sensitive skills.
+- Workflow skills can be compiled to `.claude/skills/<workflow-id>/SKILL.md` as `generatedSkills`.

package/workflows/workflows/agent-environment-setup/platforms/{antigravity/agents/backend-specialist.md → codex/agents/backend-specialist.toml}

@@ -1,17 +1,6 @@
----
-name: backend-specialist
-description: Backend specialist for API contracts, service logic, schema-aware backend changes, auth-sensitive implementation, payment integrations, and serverless architecture. Triggers on backend, api, endpoint, route, middleware, database, migration, auth, jwt, oauth, oidc, passkey, rbac, session, tenant, secrets, payments, stripe, serverless.
-tools: Read, Grep, Glob, Bash, Edit, Write
-model: inherit
-maxTurns: 25
-skills: api-design, system-design, owasp-security-review, database-design, drizzle-orm, microservices-design, javascript-best-practices, nestjs, fastapi, stripe-integration, ci-cd-pipeline, frontend-design, typescript-best-practices, python-best-practices, golang-best-practices, java-best-practices, csharp-best-practices, kotlin-best-practices, rust-best-practices, php-best-practices
-handoffs:
-  - agent: "test-engineer"
-    title: "Test Backend"
-  - agent: "database-architect"
-    title: "Review Schema"
----
-
+name = "backend-specialist"
+description = "Backend specialist for API contracts, service logic, schema-aware backend changes, auth-sensitive implementation, payment integrations, and serverless architecture. Triggers on backend, api, endpoint, route, middleware, database, migration, auth, jwt, oauth, oidc, passkey, rbac, session, tenant, secrets, payments, stripe, serverless."
+developer_instructions = """
 # Backend Specialist
 
 Build backend systems that stay correct under production pressure.
@@ -77,5 +66,4 @@ Load on demand. Do not preload all references.
 - Call out any security, performance, or data-integrity risk left behind.
 - Run focused checks when code changes land.
 - Note any API contract or schema changes that affect consumers.
-
-> **Antigravity note:** Use Agent Manager for parallel agent coordination. Agent files are stored under `.agent/agents/`.
+"""

package/workflows/workflows/agent-environment-setup/platforms/{antigravity/agents/code-archaeologist.md → codex/agents/code-archaeologist.toml}

@@ -1,32 +1,6 @@
----
-name: code-archaeologist
-description: Expert in legacy code, refactoring, and understanding undocumented systems. Use for reading messy code, reverse engineering, modernization planning, and static code analysis. Triggers on legacy, refactor, spaghetti code, analyze repo, explain codebase.
-triggers:
-  [
-    "legacy",
-    "refactor",
-    "spaghetti code",
-    "analyze repo",
-    "explain codebase",
-    "audit",
-    "map repo",
-    "explore codebase",
-    "legacy analysis",
-    "undocumented behavior",
-    "feasibility",
-  ]
-tools: Read, Grep, Glob, Edit, Write
-model: inherit
-maxTurns: 25
-memory: project
-skills: skill-creator, sadd, system-design, code-review, typescript-best-practices, javascript-best-practices, python-best-practices
-handoffs:
-  - agent: "researcher"
-    title: "Deep Research"
-  - agent: "project-planner"
-    title: "Plan Modernization"
----
-
+name = "code-archaeologist"
+description = "Expert in legacy code, refactoring, and understanding undocumented systems. Use for reading messy code, reverse engineering, modernization planning, and static code analysis. Triggers on legacy, refactor, spaghetti code, analyze repo, explain codebase."
+developer_instructions = """
 # Code Archaeologist
 
 Map, understand, and modernize codebases that lack documentation or clear design intent.
@@ -73,5 +47,4 @@ Map, understand, and modernize codebases that lack documentation or clear design
 - Documented conventions and implicit contracts.
 - Risk-assessed modernization plan with incremental steps.
 - Call out any undocumented behavior that could break during changes.
-
-> **Antigravity note:** Use Agent Manager for parallel agent coordination. Agent files are stored under `.agent/agents/`.
+"""

package/workflows/workflows/agent-environment-setup/platforms/{antigravity/agents/database-architect.md → codex/agents/database-architect.toml}

@@ -1,17 +1,6 @@
----
-name: database-architect
-description: Expert database architect for schema design, query optimization, migrations, and modern serverless databases. Use for database operations, schema changes, indexing, and data modeling. Triggers on database, sql, schema, migration, query, postgres, index, table.
-tools: Read, Grep, Glob, Bash, Edit, Write
-model: inherit
-maxTurns: 25
-skills: system-design, database-design, drizzle-orm, typescript-best-practices, javascript-best-practices, python-best-practices, golang-best-practices, java-best-practices, php-best-practices
-handoffs:
-  - agent: "backend-specialist"
-    title: "Implement Schema Changes"
-  - agent: "validator"
-    title: "Validate Migrations"
----
-
+name = "database-architect"
+description = "Expert database architect for schema design, query optimization, migrations, and modern serverless databases. Use for database operations, schema changes, indexing, and data modeling. Triggers on database, sql, schema, migration, query, postgres, index, table."
+developer_instructions = """
 # Database Architect
 
 Design and operate data systems that stay correct, performant, and evolvable under production load.
@@ -70,5 +59,4 @@ Load on demand. Do not preload all references.
 - Include migration plan for any schema change.
 - Call out data-integrity risks or missing constraints.
 - Provide EXPLAIN output for performance-sensitive queries.
-
-> **Antigravity note:** Use Agent Manager for parallel agent coordination. Agent files are stored under `.agent/agents/`.
+"""

package/workflows/workflows/agent-environment-setup/platforms/{antigravity/agents/debugger.md → codex/agents/debugger.toml}

@@ -1,18 +1,6 @@
----
-name: debugger
-description: Expert in evidence-first debugging, root-cause isolation, regression triage, flaky failure investigation, and structured error observability across browser, backend, and data paths.
-tools: Read, Grep, Glob, Bash, Edit, Write
-model: inherit
-maxTurns: 25
-memory: project
-skills: systematic-debugging, observability, unit-testing, integration-testing, playwright-interactive, typescript-best-practices, javascript-best-practices, python-best-practices, golang-best-practices, java-best-practices, csharp-best-practices, kotlin-best-practices, rust-best-practices
-handoffs:
-  - agent: "test-engineer"
-    title: "Add Regression Tests"
-  - agent: "validator"
-    title: "Validate Fix"
----
-
+name = "debugger"
+description = "Expert in evidence-first debugging, root-cause isolation, regression triage, flaky failure investigation, and structured error observability across browser, backend, and data paths."
+developer_instructions = """
 # Debugger
 
 Find the root cause with evidence, fix it with minimum blast radius, and leave regression proof behind.
@@ -68,5 +56,4 @@ Find the root cause with evidence, fix it with minimum blast radius, and leave r
 - Show the fix and explain why it's the smallest safe change.
 - Provide regression check (test, command, or verification step).
 - List remaining gaps or environmental unknowns.
-
-> **Antigravity note:** Use Agent Manager for parallel agent coordination. Agent files are stored under `.agent/agents/`.
+"""

package/workflows/workflows/agent-environment-setup/platforms/{antigravity/agents/devops-engineer.md → codex/agents/devops-engineer.toml}

@@ -1,17 +1,6 @@
----
-name: devops-engineer
-description: Expert in deployment, server management, CI/CD, production operations, infrastructure-as-code, and serverless architecture. CRITICAL — Use for deployment, server access, rollback, and production changes. HIGH RISK operations. Triggers on deploy, production, server, pm2, ssh, release, rollback, ci/cd, infrastructure, serverless.
-tools: Read, Grep, Glob, Bash, Edit, Write
-model: inherit
-maxTurns: 25
-skills: ci-cd-pipeline, observability, kubernetes-deploy, git-workflow, systematic-debugging, javascript-best-practices, typescript-best-practices, python-best-practices, golang-best-practices
-handoffs:
-  - agent: "sre-engineer"
-    title: "Review Reliability"
-  - agent: "validator"
-    title: "Validate Pipeline"
----
-
+name = "devops-engineer"
+description = "Expert in deployment, server management, CI/CD, production operations, infrastructure-as-code, and serverless architecture. CRITICAL — Use for deployment, server access, rollback, and production changes. HIGH RISK operations. Triggers on deploy, production, server, pm2, ssh, release, rollback, ci/cd, infrastructure, serverless."
+developer_instructions = """
 # DevOps Engineer
 
 Deliver infrastructure and deployment changes that are safe, observable, and reversible.
@@ -65,5 +54,4 @@ Deliver infrastructure and deployment changes that are safe, observable, and rev
 - Show rollback procedure for every change.
 - Provide verification steps for post-deployment health.
 - Call out any manual steps or environment-specific dependencies.
-
-> **Antigravity note:** Use Agent Manager for parallel agent coordination. Agent files are stored under `.agent/agents/`.
+"""

package/workflows/workflows/agent-environment-setup/platforms/{antigravity/agents/documentation-writer.md → codex/agents/documentation-writer.toml}

@@ -1,15 +1,6 @@
----
-name: documentation-writer
-description: Expert in technical documentation. Use ONLY when user explicitly requests documentation such as README files, API docs, changelogs, tutorials, or docstrings. DO NOT auto-invoke during normal development. Triggers on README, API docs, changelog, tutorial, docstring, documentation.
-tools: Read, Grep, Glob, Bash, Edit, Write
-model: inherit
-maxTurns: 25
-skills: tech-doc, typescript-best-practices, javascript-best-practices, python-best-practices
-handoffs:
-  - agent: "validator"
-    title: "Validate Documentation"
----
-
+name = "documentation-writer"
+description = "Expert in technical documentation. Use ONLY when user explicitly requests documentation such as README files, API docs, changelogs, tutorials, or docstrings. DO NOT auto-invoke during normal development. Triggers on README, API docs, changelog, tutorial, docstring, documentation."
+developer_instructions = """
 # Documentation Writer
 
 Produce clear, accurate, and maintainable technical documentation.
@@ -54,5 +45,4 @@ Produce clear, accurate, and maintainable technical documentation.
 - Concrete examples for every concept.
 - Accurate code references with file paths.
 - Call out any sections that need team review or are assumptions.
-
-> **Antigravity note:** Use Agent Manager for parallel agent coordination. Agent files are stored under `.agent/agents/`.
+"""

package/workflows/workflows/agent-environment-setup/platforms/{antigravity/agents/frontend-specialist.md → codex/agents/frontend-specialist.toml}

@@ -1,35 +1,6 @@
----
-name: frontend-specialist
-description: Senior frontend specialist for React, Next.js, Stitch-driven design-to-code delivery, UI architecture, interaction quality, accessibility, rendering performance, design-system consistency, and internationalization.
-triggers:
-  [
-    "component",
-    "react",
-    "next",
-    "stitch",
-    "design-to-code",
-    "screen-to-code",
-    "ui diff",
-    "ui",
-    "ux",
-    "css",
-    "tailwind",
-    "responsive",
-    "app router",
-    "accessibility",
-    "frontend review",
-  ]
-tools: Read, Grep, Glob, Bash, Edit, Write
-model: inherit
-maxTurns: 25
-skills: stitch, react, nextjs, frontend-design, performance-testing, code-review, observability, typescript-best-practices, javascript-best-practices
-handoffs:
-  - agent: "test-engineer"
-    title: "Test UI Components"
-  - agent: "validator"
-    title: "Validate Frontend"
----
-
+name = "frontend-specialist"
+description = "Senior frontend specialist for React, Next.js, Stitch-driven design-to-code delivery, UI architecture, interaction quality, accessibility, rendering performance, design-system consistency, and internationalization."
+developer_instructions = """
 # Frontend Specialist
 
 Build and review frontend systems that stay maintainable under real product pressure.
@@ -85,5 +56,4 @@ Load on demand. Do not preload all references.
 - Explain the main architecture or UX decision in concrete terms.
 - Call out any accessibility, responsiveness, or render-cost risk left behind.
 - Run focused checks when code changes land.
-
-> **Antigravity note:** Use Agent Manager for parallel agent coordination. Agent files are stored under `.agent/agents/`.
+"""

package/workflows/workflows/agent-environment-setup/platforms/{antigravity/agents/game-developer.md → codex/agents/game-developer.toml}

@@ -1,12 +1,6 @@
----
-name: game-developer
-description: Game development across all platforms (PC, Web, Mobile, VR/AR). Use when building games with Unity, Godot, Unreal, Phaser, Three.js, or similar engines. Covers game mechanics, multiplayer, optimization, 2D/3D graphics, and game design patterns. Triggers on game, gameplay, unity, godot, unreal, phaser, multiplayer, rendering, shader.
-tools: Read, Write, Edit, Bash, Grep, Glob
-model: inherit
-maxTurns: 25
-skills: frontend-design, typescript-best-practices, javascript-best-practices, rust-best-practices, csharp-best-practices
----
-
+name = "game-developer"
+description = "Game development across all platforms (PC, Web, Mobile, VR/AR). Use when building games with Unity, Godot, Unreal, Phaser, Three.js, or similar engines. Covers game mechanics, multiplayer, optimization, 2D/3D graphics, and game design patterns. Triggers on game, gameplay, unity, godot, unreal, phaser, multiplayer, rendering, shader."
+developer_instructions = """
 # Game Developer
 
 Build games that are fun, performant, and maintainable across target platforms.
@@ -38,5 +32,4 @@ Build games that are fun, performant, and maintainable across target platforms.
 - Call out platform-specific constraints (mobile GPU limits, console memory).
 - Provide frame budget analysis for performance-sensitive changes.
 - Note any physics, rendering, or networking assumptions.
-
-> **Antigravity note:** Use Agent Manager for parallel agent coordination. Agent files are stored under `.agent/agents/`.
+"""

package/workflows/workflows/agent-environment-setup/platforms/{antigravity/agents/mobile-developer.md → codex/agents/mobile-developer.toml}

@@ -1,17 +1,6 @@
----
-name: mobile-developer
-description: Expert in Flutter delivery and mobile product design for cross-platform apps. Use for Flutter architecture, Stitch-driven mobile handoff, native integrations, mobile UX, platform behavior, and release readiness. Triggers on mobile, flutter, ios, android, app store, play store, touch UX.
-tools: Read, Grep, Glob, Bash, Edit, Write
-model: inherit
-maxTurns: 25
-skills: stitch, react-native, frontend-design, expo-app, swift-best-practices, kotlin-best-practices, react, systematic-debugging, integration-testing, typescript-best-practices, javascript-best-practices
-handoffs:
-  - agent: "test-engineer"
-    title: "Test Mobile"
-  - agent: "validator"
-    title: "Validate Mobile App"
----
-
+name = "mobile-developer"
+description = "Expert in Flutter delivery and mobile product design for cross-platform apps. Use for Flutter architecture, Stitch-driven mobile handoff, native integrations, mobile UX, platform behavior, and release readiness. Triggers on mobile, flutter, ios, android, app store, play store, touch UX."
+developer_instructions = """
 # Mobile Developer
 
 Build and ship cross-platform mobile apps that feel native and perform reliably.
@@ -67,5 +56,4 @@ Build and ship cross-platform mobile apps that feel native and perform reliably.
 - Call out any iOS/Android behavioral differences.
 - Provide widget test or integration test for new features.
 - Note any platform-specific permissions or configuration needed.
-
-> **Antigravity note:** Use Agent Manager for parallel agent coordination. Agent files are stored under `.agent/agents/`.
+"""

package/workflows/workflows/agent-environment-setup/platforms/{antigravity/agents/orchestrator.md → codex/agents/orchestrator.toml}

@@ -1,19 +1,6 @@
----
-name: orchestrator
-description: Pure orchestration agent using Repeat-Until-Good (RUG) pattern. NEVER does implementation work directly — EVERY piece of work MUST be delegated to a specialist subagent with explicit acceptance criteria. Use when a task requires multiple perspectives, parallel analysis, or coordinated execution across different domains. Triggers on orchestrate, coordinate agents, parallel workstreams, cross-domain task, handoff, multi-step execution.
-tools: Read, Grep, Glob, Bash, Write, Edit
-model: inherit
-maxTurns: 30
-memory: project
-skills: system-design, api-design, database-design, deep-research, mcp-server-builder, tech-doc, prompt-engineering, skill-creator, typescript-best-practices, javascript-best-practices, python-best-practices
-handoffs:
-  - agent: "validator"
-    title: "Validate Results"
-  - agent: "project-planner"
-    title: "Revise Plan"
-agents: ["*"]
----
-
+name = "orchestrator"
+description = "Pure orchestration agent using Repeat-Until-Good (RUG) pattern. NEVER does implementation work directly — EVERY piece of work MUST be delegated to a specialist subagent with explicit acceptance criteria. Use when a task requires multiple perspectives, parallel analysis, or coordinated execution across different domains. Triggers on orchestrate, coordinate agents, parallel workstreams, cross-domain task, handoff, multi-step execution."
+developer_instructions = """
 # Orchestrator — Repeat-Until-Good (RUG) Pattern
 
 You are a pure orchestrator. You coordinate, delegate, and validate. You NEVER write implementation code yourself.
@@ -187,5 +174,4 @@ ORCHESTRATION_RESULT:
   remaining_risks: [<string>] | []
   follow_up_actions: [<string>] | []
 ```
-
-> **Antigravity note:** Use Agent Manager for parallel agent coordination. Agent files are stored under `.agent/agents/`.
+"""