@raishin/vanguard-frontier-agentic 1.0.0

package/skills/oci/oci-support-incident-coordinator/references/safety-checklist.md

@@ -0,0 +1,32 @@
+# Safety Checklist
+
+Use this checklist before recommending or executing changes for `oci-support-incident-coordinator`.
+
+## Scope
+
+- Region confirmed.
+- Compartment or compartment tree confirmed.
+- Resource identity confirmed by name and, when available, live evidence.
+- Owner and business impact confirmed.
+- Environment confirmed: dev/test/stage/prod.
+
+## Access
+
+- Default profile unless user explicitly chooses another profile/config in the active runtime.
+- Least-privilege action only.
+- No tenancy-wide grants unless risk-accepted.
+- No secrets requested or displayed.
+
+## Change safety
+
+- Read-only discovery first.
+- Explicit approval for write, delete, start, stop, update, policy, traffic, SQL, command execution, or remediation actions.
+- Rollback path documented.
+- Validation plan includes positive and negative checks.
+
+## Platform portability
+
+- Prefer MCP tool calls.
+- Use neutral `<placeholders>` in examples.
+- Do not assume Bash, PowerShell, cmd.exe, macOS, Windows, or Linux until execution context is known.
+- Do not embed machine-local paths.

package/skills/oci/oracle-oci-mcp-grounded-advisor/SKILL.md

@@ -0,0 +1,35 @@
+---
+name: oracle-oci-mcp-grounded-advisor
+description: Use this skill when the user asks about Oracle MCP servers, SQLcl MCP, OCI MCP, Oracle Database agent access, OCI automation, or cloud/database advice that must be grounded in official Oracle sources.
+metadata:
+  author: github: Raishin
+  version: 0.1.0
+---
+
+# Oracle and OCI MCP Grounded Advisor
+
+## Purpose
+
+Prevent hallucinated Oracle and OCI guidance by forcing official-source verification before recommendations.
+
+## Workflow
+
+1. Identify whether the question is about Oracle Database, SQLcl MCP, OCI, MySQL, documentation MCP, or general MCP architecture.
+2. Verify current behavior against official Oracle pages or repositories when the answer affects installation, authentication, supported versions, or permissions.
+3. Distinguish Oracle-official MCP servers from community projects.
+4. State authentication and data-access risks clearly.
+5. Prefer read-only exploration and documentation lookup before tool execution.
+
+## Output
+
+Return:
+
+- recommendation,
+- source-backed facts,
+- uncertainty or version caveats,
+- setup/security notes,
+- next validation command or official document to read.
+
+## Security notes
+
+Database MCP access can expose production data. Do not recommend connecting an agent to a database unless the user has scoped credentials, audit expectations, and read/write boundaries.

package/skills/oci/oracle-oci-mcp-grounded-advisor/metadata.json

@@ -0,0 +1,26 @@
+{
+  "id": "oracle-oci-mcp-grounded-advisor",
+  "name": "Oracle and OCI MCP Grounded Advisor",
+  "type": "skill",
+  "provider": "oci",
+  "harnesses": [
+    "codex",
+    "claude-code",
+    "cursor",
+    "gemini",
+    "kiro",
+    "other"
+  ],
+  "summary": "Ground Oracle, OCI, SQLcl, database, and MCP recommendations in official Oracle sources before advising.",
+  "source_type": "original",
+  "official_docs": [
+    "https://www.oracle.com/mcp",
+    "https://github.com/oracle/mcp",
+    "https://docs.oracle.com/en-us/iaas/Content/home.htm"
+  ],
+  "security_notes": "Oracle database and OCI MCP tools can expose sensitive data or mutate cloud resources. Verify auth model and permissions before recommending use.",
+  "last_verified": "2026-04-27",
+  "path": "skills/oci/oracle-oci-mcp-grounded-advisor",
+  "author": "github: Raishin",
+  "version": "0.1.0"
+}

package/templates/AGENTS.md

@@ -0,0 +1,11 @@
+# AGENTS.md
+
+## Purpose
+- Store starter asset templates for contributors.
+
+## Rules
+- Keep templates minimal and schema-compatible.
+- Update templates when required metadata fields change.
+- Do not put provider-specific guidance in generic templates.
+- Run `npm run validate` after template changes if catalog examples are affected.
+

package/templates/agent-template/AGENT.md

@@ -0,0 +1,20 @@
+# Human Agent Name
+
+## Mission
+
+State what the agent owns and what it must refuse or escalate.
+
+## Operating rules
+
+- Verify before recommending.
+- Separate facts from inference.
+- Prefer least privilege and reversible changes.
+- Do not apply infrastructure changes unless explicitly authorized.
+
+## Output format
+
+- Summary
+- Findings
+- Evidence
+- Recommended changes
+- Validation plan

package/templates/agent-template/metadata.json

@@ -0,0 +1,13 @@
+{
+  "id": "domain-agent-name",
+  "name": "Human Agent Name",
+  "type": "agent",
+  "provider": "terraform",
+  "harnesses": ["codex", "claude-code", "cursor", "gemini", "kiro"],
+  "summary": "One-sentence description of the agent role.",
+  "source_type": "original",
+  "official_docs": ["https://example.com/official-doc"],
+  "security_notes": "State review boundaries and mutation policy.",
+  "last_verified": "2026-04-27",
+  "path": "agents/domain-agent-name"
+}

package/templates/mcp-reference-template.md

@@ -0,0 +1,19 @@
+# MCP Reference Template
+
+## Summary
+
+- Vendor:
+- Official/community status:
+- Source URL:
+- Official docs:
+- Supported auth model:
+- Can mutate resources:
+- Last verified:
+
+## Install/config example
+
+Link to official setup instructions. Keep local examples minimal and avoid secrets.
+
+## Security notes
+
+State permission model, local/remote execution assumptions, and blast-radius risks.

package/templates/skill-template/SKILL.md

@@ -0,0 +1,31 @@
+---
+name: provider-skill-name
+description: Use this skill for a specific cloud workflow. Mention provider, trigger phrases, expected inputs, and when not to use it.
+---
+
+# Human Skill Name
+
+## Purpose
+
+Describe the workflow and the user problem it solves.
+
+## Inputs
+
+- Required cloud/provider context.
+- Files or commands to inspect.
+- Safety constraints.
+
+## Workflow
+
+1. Verify scope and credentials without exposing secrets.
+2. Read official documentation for claims that may drift.
+3. Prefer read-only inspection before mutation.
+4. Produce findings with evidence and risk level.
+
+## Output
+
+Return concise findings, remediation steps, and validation commands.
+
+## Security notes
+
+Call out permissions, production risks, and approval gates.

package/templates/skill-template/metadata.json

@@ -0,0 +1,13 @@
+{
+  "id": "provider-skill-name",
+  "name": "Human Skill Name",
+  "type": "skill",
+  "provider": "aws",
+  "harnesses": ["codex", "claude-code"],
+  "summary": "One-sentence description of the repeatable cloud workflow.",
+  "source_type": "original",
+  "official_docs": ["https://example.com/official-doc"],
+  "security_notes": "State permissions, mutation risk, approval gates, and secret-handling assumptions.",
+  "last_verified": "2026-04-27",
+  "path": "skills/aws/provider-skill-name"
+}