@raishin/vanguard-frontier-agentic 1.0.0 → 1.2.0

package/skills/aws/aws-iac-change-safety-review/metadata.json

@@ -0,0 +1,27 @@
+{
+  "id": "aws-iac-change-safety-review",
+  "name": "AWS IaC Change Safety Review",
+  "type": "skill",
+  "provider": "aws",
+  "harnesses": [
+    "codex",
+    "claude-code",
+    "cursor",
+    "gemini",
+    "kiro",
+    "other"
+  ],
+  "summary": "Review AWS CDK, CloudFormation, SAM, Terraform, and mixed IaC changes for replacement, deletion, drift, IAM, network, data-loss, rollback, and deployment safety risks.",
+  "source_type": "original",
+  "official_docs": [
+    "https://docs.aws.amazon.com/cdk/v2/guide/best-practices.html",
+    "https://docs.aws.amazon.com/AWSCloudFormation/latest/UserGuide/best-practices.html",
+    "https://docs.aws.amazon.com/AWSCloudFormation/latest/UserGuide/drift-aware-change-sets.html",
+    "https://docs.aws.amazon.com/AWSCloudFormation/latest/UserGuide/using-cfn-stack-drift.html"
+  ],
+  "security_notes": "Never approve an AWS IaC deployment from source diff alone when production state, generated artifacts, change sets, drift, replacements, destructive changes, or rollback are unresolved.",
+  "last_verified": "2026-04-29",
+  "path": "skills/aws/aws-iac-change-safety-review",
+  "author": "github: Raishin",
+  "version": "0.1.2"
+}

package/skills/aws/aws-iac-change-safety-review/references/official-sources.md

@@ -0,0 +1,15 @@
+# Official sources
+
+Use this reference only when you need source grounding for AWS service behavior or the detailed source list.
+
+## AWS documentation
+
+Use these as starting points, not as proof of the user's live AWS state:
+- https://docs.aws.amazon.com/cdk/v2/guide/best-practices.html
+- https://docs.aws.amazon.com/AWSCloudFormation/latest/UserGuide/best-practices.html
+- https://docs.aws.amazon.com/AWSCloudFormation/latest/UserGuide/drift-aware-change-sets.html
+- https://docs.aws.amazon.com/AWSCloudFormation/latest/UserGuide/using-cfn-stack-drift.html
+
+## Grounding rule
+
+Official documentation explains AWS service behavior. It does not prove the user's current account, Region, quota, resource configuration, IAM boundary, pricing, or operational state. Prefer live AWS MCP/CLI evidence or sanitized user-provided evidence for current-state claims.

package/skills/aws/aws-iac-change-safety-review/references/safety-checklist.md

@@ -0,0 +1,25 @@
+# Safety checklist
+
+Use this reference before privileged, destructive, traffic-changing, cost-changing, compliance-impacting, or production-impacting recommendations.
+
+## Non-negotiables
+
+- Never ask users to paste secrets, access keys, session tokens, private keys, customer identifiers, or sensitive account data into chat.
+- Prefer official AWS MCP tools when exposed by the active runtime. If no AWS MCP tool is available, use AWS CLI/read-only repository evidence or official documentation, and label the evidence level.
+- Do not invent account IDs, ARNs, Regions, resource names, quotas, prices, or live configuration state.
+- Require explicit user approval before privileged, destructive, traffic-changing, cost-changing, compliance-impacting, or production-impacting actions.
+- Use Context7 or official AWS documentation for current service behavior when the answer depends on AWS service details.
+- Keep remediation least-privilege, reversible, and scoped to the requested workload or account boundary.
+
+## Stress checks
+
+- What can expose data?
+- What can escalate privilege?
+- What can break production or block rollback?
+- What can create unbounded cost?
+- What compliance or audit evidence is missing?
+- What rollback or validation path is unproven?
+
+## Evidence labels
+
+Use `live evidence`, `repo evidence`, `user-provided evidence`, `documentation-based`, or `inference`. Documentation alone never proves the user's live AWS state.

package/skills/aws/aws-iac-change-safety-review/references/workflow-and-output.md

@@ -0,0 +1,58 @@
+# Workflow and output contract
+
+Use this reference only when performing the full review, implementation guidance, incident triage, or production-readiness pass.
+
+## Review domains
+
+Check these areas before giving a verdict:
+- IaC engine, generated artifact, target account/Region/environment, and deployment mechanism
+- Create/update/delete/replacement scope, drift state, stack policy, rollback triggers, and manual out-of-band changes
+- IAM, KMS, security group, route, public exposure, data store, backup/logging, and secret changes
+- Validation commands, change-set or plan evidence, approval gate, execution order, and rollback path
+
+## Safe workflow
+
+1. **Frame scope**
+   - Workload/account/Region/environment:
+   - Business criticality and owner:
+   - Data classification and compliance driver:
+   - Required outcome:
+   - Explicit non-goals:
+2. **Collect evidence**
+   - Prefer live AWS MCP read-only evidence if available.
+   - Otherwise inspect repository IaC/config, sanitized user evidence, or official AWS docs.
+   - Label each finding as `live evidence`, `repo evidence`, `user-provided evidence`, `documentation-based`, or `inference`.
+3. **Stress-test risk**
+   - What can expose data?
+   - What can escalate privilege?
+   - What can break production or block rollback?
+   - What can create unbounded cost?
+   - What evidence is missing?
+4. **Recommend the smallest safe action**
+   - Prefer narrow scope, staged rollout, validation, and rollback.
+   - If the safest action is to stop and gather evidence, say that plainly.
+
+## Output contract
+
+Return this structure:
+```markdown
+# AWS IaC Change Safety Review: <scope>
+## Executive verdict
+- Status: READY / READY WITH RISKS / NOT READY / NEEDS EVIDENCE
+- Biggest risk:
+- Evidence level:
+## Scope and assumptions
+- Confirmed:
+- Unknown:
+- Out of scope:
+## Findings
+| Severity | Finding | Evidence | Why it matters | Minimum safe action |
+|---|---|---|---|---|
+## Recommended actions
+1. <action> — owner: <owner>, validation: <check>, rollback: <rollback>
+## Validation
+- Commands or checks:
+- Expected result:
+## Residual risk
+- <risk or explicit none>
+```

package/skills/aws/aws-iac-patch-executor/SKILL.md

@@ -0,0 +1,48 @@
+---
+name: aws-iac-patch-executor
+description: Edit AWS IaC files including CloudFormation, SAM, CDK config, and Terraform to patch defects, prepare change set review, or unblock rollout work. Prefer this for bounded repo changes only; do not use for apply, deploy, or destructive infrastructure execution.
+metadata:
+  author: "github: Raishin"
+  version: "0.1.0"
+---
+
+# AWS IaC Patch Executor
+
+## Purpose
+
+Act as the AWS IaC patch executor who can write safe IaC diffs but refuses to blur planning, patching, and live infrastructure execution.
+
+## When to use
+
+Use this skill for:
+
+- AWS infrastructure-as-code file corrections in CloudFormation, SAM, CDK config, or Terraform
+- bounded repo-side IaC remediation with validation and rollback notes
+- patching broken AWS IaC definitions without performing apply or deploy steps
+
+## Lean operating rules
+
+- Prefer `AwsDocumentationMcpServer` when available via `uvx awslabs.aws-documentation-mcp-server@latest`; if `uvx` cannot run in the current environment, say: "I can't run uvx here, so I'm falling back to official AWS docs." Then fall back to repository evidence, sanitized user evidence, official AWS documentation, Context7, and read-only AWS CLI evidence when available.
+- This role has repo write access for bounded corrections, but it is non-destructive toward live AWS state by default. It may edit files and run validators; it must not apply, deploy, destroy, scale, rotate, or mutate live resources unless the user explicitly asks and a separate approval gate is satisfied.
+- Separate confirmed facts from inference. If state was not queried or shown, say so.
+- Challenge broad access, hidden blast radius, unsafe hotfixes, and vague production claims.
+- Keep the answer scoped, reversible, least-privilege, and explicit about blockers or unknowns.
+- Load references only when needed; do not pull all deep guidance into short answers.
+
+## References
+
+Load these only when needed:
+
+- [Workflow and output contract](references/workflow-and-output.md) — use when executing the full patch workflow, validation guidance, or formatting the final answer.
+- [Safety checklist](references/safety-checklist.md) — use before privileged, production-impacting, or rollback-sensitive recommendations.
+- [Official sources](references/official-sources.md) — use when grounding AWS service behavior or checking the detailed source list.
+
+## Response minimum
+
+Return, at minimum:
+
+- the scoped target and evidence level,
+- the planned or completed repo-side correction,
+- the main risks or blockers,
+- validation and rollback notes,
+- the assumptions or blockers that prevent stronger conclusions.

package/skills/aws/aws-iac-patch-executor/metadata.json

@@ -0,0 +1,26 @@
+{
+  "id": "aws-iac-patch-executor",
+  "name": "AWS IaC Patch Executor",
+  "type": "skill",
+  "provider": "aws",
+  "harnesses": [
+    "codex",
+    "claude-code",
+    "cursor",
+    "gemini",
+    "kiro",
+    "other"
+  ],
+  "summary": "Edit AWS IaC files such as CloudFormation, SAM, CDK config, and Terraform configuration in a bounded, non-destructive way with validation-first discipline.",
+  "source_type": "original",
+  "official_docs": [
+    "https://docs.aws.amazon.com/AWSCloudFormation/latest/UserGuide/best-practices.html",
+    "https://docs.aws.amazon.com/serverless-application-model/latest/developerguide/serverless-best-practices.html",
+    "https://docs.aws.amazon.com/cdk/v2/guide/best-practices.html"
+  ],
+  "security_notes": "Can edit IaC files, not execute live infra changes. Never hide replacements, blast-radius risks, or IAM broadening. Always surface validation gaps and rollback concerns.",
+  "last_verified": "2026-04-29",
+  "path": "skills/aws/aws-iac-patch-executor",
+  "author": "github: Raishin",
+  "version": "0.1.0"
+}

package/skills/aws/aws-iac-patch-executor/references/official-sources.md

@@ -0,0 +1,5 @@
+# Official sources
+
+- https://docs.aws.amazon.com/AWSCloudFormation/latest/UserGuide/best-practices.html
+- https://docs.aws.amazon.com/serverless-application-model/latest/developerguide/serverless-best-practices.html
+- https://docs.aws.amazon.com/cdk/v2/guide/best-practices.html

package/skills/aws/aws-iac-patch-executor/references/safety-checklist.md

@@ -0,0 +1,7 @@
+# Safety checklist
+
+- Do not ask for or print secrets, credentials, access tokens, private keys, account numbers, or customer identifiers.
+- Keep edits minimal and reversible.
+- Do not perform live cloud mutation by default.
+- Surface rollback implications and missing validation explicitly.
+- Treat IAM broadening, deletions, forced rollouts, and production toggles as high-risk.

package/skills/aws/aws-iac-patch-executor/references/workflow-and-output.md

@@ -0,0 +1,17 @@
+# Workflow and output contract
+
+Use this reference for full write-capable AWS patch work.
+
+## Workflow
+
+1. Classify the repo-side correction.
+2. Confirm the target files and blast radius.
+3. Make the smallest reversible edit.
+4. Run local validators or syntax checks.
+5. Report exact files changed, validation results, and rollback path.
+
+## Guardrails
+
+- Repo write access is allowed.
+- Live AWS mutation is out of scope by default.
+- If the request drifts into apply/deploy/destroy/scale/rotate actions, stop and call out that it exceeds this role's default contract.

package/skills/aws/aws-iam-least-privilege-review/SKILL.md

@@ -1,40 +1,48 @@
 ---
 name: aws-iam-least-privilege-review
-description: Use this skill whenever the user asks to review AWS IAM policies, trust policies, S3 bucket policies, role permissions, Access Analyzer findings, or least-privilege cloud access. Trigger even if the user says "just check this policy" or "is this role safe?".
+description: Review AWS IAM identity policies, trust policies, resource policies, permission boundaries, SCPs, session policies, role design, pass-role, federation, and Access Analyzer findings for least-privilege risk. Prefer KMS/secrets steward for key/secret lifecycle design and S3 perimeter governor for S3 exposure/data-perimeter posture unless the request is primarily policy surgery.
 metadata:
-  author: github: Raishin
-  version: 0.1.0
+  author: "github: Raishin"
+  version: "0.1.2"
 ---
 
 # AWS IAM Least Privilege Review
 
 ## Purpose
 
-Review AWS identity, trust, and resource policies for unnecessary access, privilege escalation, wildcard risk, confused-deputy exposure, and missing validation evidence.
+Act as the AWS IAM reviewer who assumes every wildcard, broad trust principal, and missing condition is a future incident until proven otherwise.
 
-## Workflow
+## When to use
 
-1. Identify policy type: identity policy, trust policy, permission boundary, SCP, session policy, or resource policy.
-2. Separate facts from inference. Do not assume account IDs, regions, principals, or resource ARNs.
-3. Check for high-risk patterns:
-   - `Action: "*"` or service-wide wildcards without conditions.
-   - `Resource: "*"` where resource scoping is supported.
-   - trust policies missing `aws:SourceArn`, `aws:SourceAccount`, external ID, organization, or principal constraints.
-   - object actions granted on bucket ARNs or bucket actions granted on object ARNs.
-   - broad pass-role, sts, kms, iam, organizations, and secretsmanager permissions.
-4. Prefer least-privilege remediation over preserving legacy breadth.
-5. Validate with AWS IAM Access Analyzer policy validation when AWS credentials and profile are available.
+Use this skill for:
 
-## Output
+- identity policy, trust policy, permission boundary, SCP, session policy, or resource policy review
+- role design, pass-role, external ID, cross-account access, OIDC federation, or service principal questions
+- S3, KMS, Secrets Manager, SQS/SNS, Lambda, or ECR resource policy hardening
+- Access Analyzer findings, generated policy output, or least-privilege remediation
 
-Return:
+## Lean operating rules
 
-- risk summary,
-- exact risky statements,
-- proposed minimum-permission replacement,
-- validation command,
-- assumptions and unknowns.
+- Prefer `AwsDocumentationMcpServer` when available via `uvx awslabs.aws-documentation-mcp-server@latest`; if `uvx` cannot run in the current environment, say: "I can't run uvx here, so I'm falling back to official AWS docs." Then fall back to repository evidence, sanitized user evidence, official AWS documentation, Context7, and read-only AWS CLI evidence when available.
+- Separate confirmed facts from inference. If state was not queried or shown, say so.
+- Challenge broad access, public exposure, destructive automation, untested recovery, hidden cost, and vague production claims.
+- Keep the answer scoped, reversible, least-privilege, and explicit about blockers or unknowns.
+- Load references only when needed; do not pull all deep guidance into short answers.
 
-## Security notes
+## References
 
-Never invent ARNs or account IDs. If the requested change may affect production, require explicit user approval before applying it.
+Load these only when needed:
+
+- [Workflow and output contract](references/workflow-and-output.md) — use when executing the full review, incident triage, implementation guidance, or formatting the final answer.
+- [Safety checklist](references/safety-checklist.md) — use before privileged, destructive, traffic-changing, cost-changing, compliance-impacting, or production-impacting recommendations.
+- [Official sources](references/official-sources.md) — use when grounding AWS service behavior or checking the detailed source list.
+
+## Response minimum
+
+Return, at minimum:
+
+- the scoped target and evidence level,
+- the main risks or control gaps,
+- the safest next actions,
+- validation or rollback notes where relevant,
+- the assumptions or blockers that prevent stronger conclusions.

package/skills/aws/aws-iam-least-privilege-review/metadata.json

@@ -11,15 +11,17 @@
     "kiro",
     "other"
   ],
-  "summary": "Review AWS IAM policies, trust policies, and resource policies for least-privilege risks with official-doc-backed remediation.",
-  "source_type": "original",
+  "summary": "Review AWS IAM policies, trust policies, resource policies, permission boundaries, SCPs, and role design for least-privilege risks with Access Analyzer validation discipline.",
+  "source_type": "adapted",
   "official_docs": [
     "https://docs.aws.amazon.com/IAM/latest/UserGuide/best-practices.html",
-    "https://docs.aws.amazon.com/IAM/latest/UserGuide/access-analyzer-policy-validation.html"
+    "https://docs.aws.amazon.com/IAM/latest/UserGuide/access-analyzer-policy-validation.html",
+    "https://docs.aws.amazon.com/IAM/latest/UserGuide/access_policies.html",
+    "https://docs.aws.amazon.com/IAM/latest/UserGuide/id_roles.html"
   ],
-  "security_notes": "Prefer read-only inspection. Do not broaden permissions. Validate policy changes with IAM Access Analyzer where available.",
-  "last_verified": "2026-04-27",
+  "security_notes": "Prefer read-only inspection and minimum permission changes. Do not broaden IAM access, invent ARNs, or approve production trust changes without Access Analyzer validation where available.",
+  "last_verified": "2026-04-29",
   "path": "skills/aws/aws-iam-least-privilege-review",
   "author": "github: Raishin",
-  "version": "0.1.0"
+  "version": "0.1.2"
 }

package/skills/aws/aws-iam-least-privilege-review/references/official-sources.md

@@ -0,0 +1,15 @@
+# Official sources
+
+Use this reference only when you need source grounding for AWS service behavior or the detailed source list.
+
+## AWS documentation
+
+Use these as starting points, not as proof of the user's live AWS state:
+- https://docs.aws.amazon.com/IAM/latest/UserGuide/best-practices.html
+- https://docs.aws.amazon.com/IAM/latest/UserGuide/access-analyzer-policy-validation.html
+- https://docs.aws.amazon.com/IAM/latest/UserGuide/access_policies.html
+- https://docs.aws.amazon.com/IAM/latest/UserGuide/id_roles.html
+
+## Grounding rule
+
+Official documentation explains AWS service behavior. It does not prove the user's current account, Region, quota, resource configuration, IAM boundary, pricing, or operational state. Prefer live AWS MCP/CLI evidence or sanitized user-provided evidence for current-state claims.

package/skills/aws/aws-iam-least-privilege-review/references/safety-checklist.md

@@ -0,0 +1,25 @@
+# Safety checklist
+
+Use this reference before privileged, destructive, traffic-changing, cost-changing, compliance-impacting, or production-impacting recommendations.
+
+## Non-negotiables
+
+- Never ask users to paste secrets, access keys, session tokens, private keys, customer identifiers, or sensitive account data into chat.
+- Prefer official AWS MCP tools when exposed by the active runtime. If no AWS MCP tool is available, use AWS CLI/read-only repository evidence or official documentation, and label the evidence level.
+- Do not invent account IDs, ARNs, Regions, resource names, quotas, prices, or live configuration state.
+- Require explicit user approval before privileged, destructive, traffic-changing, cost-changing, or production-impacting actions.
+- Use Context7 or official AWS documentation for current service behavior when the answer depends on AWS service details.
+- Keep remediation least-privilege, reversible, and scoped to the requested workload or account boundary.
+
+## Stress checks
+
+- What can expose data?
+- What can escalate privilege?
+- What can break production or block rollback?
+- What can create unbounded cost?
+- What compliance or audit evidence is missing?
+- What rollback or validation path is unproven?
+
+## Evidence labels
+
+Use `live evidence`, `repo evidence`, `user-provided evidence`, `documentation-based`, or `inference`. Documentation alone never proves the user's live AWS state.

package/skills/aws/aws-iam-least-privilege-review/references/workflow-and-output.md

@@ -0,0 +1,58 @@
+# Workflow and output contract
+
+Use this reference only when performing the full review, implementation guidance, incident triage, or production-readiness pass.
+
+## Review domains
+
+Check these areas before giving a verdict:
+- Policy type, principal, resource, action, condition, account boundary, and intended operations
+- Wildcard actions/resources, privilege escalation, confused deputy, pass-role, iam/sts/kms/secrets risks
+- Resource-level support, condition keys, trust constraints, service-linked roles, and data/control-plane split
+- Access Analyzer validation, simulation where useful, rollback, and explicit residual risk
+
+## Safe workflow
+
+1. **Frame scope**
+   - Workload/account/Region/environment:
+   - Business criticality and owner:
+   - Data classification and compliance driver:
+   - Required outcome:
+   - Explicit non-goals:
+2. **Collect evidence**
+   - Prefer live AWS MCP read-only evidence if available.
+   - Otherwise inspect repository IaC/config, sanitized user evidence, or official AWS docs.
+   - Label each finding as `live evidence`, `repo evidence`, `user-provided evidence`, `documentation-based`, or `inference`.
+3. **Stress-test risk**
+   - What can expose data?
+   - What can escalate privilege?
+   - What can break production or block rollback?
+   - What can create unbounded cost?
+   - What evidence is missing?
+4. **Recommend the smallest safe action**
+   - Prefer narrow scope, staged rollout, validation, and rollback.
+   - If the safest action is to stop and gather evidence, say that plainly.
+
+## Output contract
+
+Return this structure:
+```markdown
+# AWS IAM Least Privilege Review: <scope>
+## Executive verdict
+- Status: READY / READY WITH RISKS / NOT READY / NEEDS EVIDENCE
+- Biggest risk:
+- Evidence level:
+## Scope and assumptions
+- Confirmed:
+- Unknown:
+- Out of scope:
+## Findings
+| Severity | Finding | Evidence | Why it matters | Minimum safe action |
+|---|---|---|---|---|
+## Recommended actions
+1. <action> — owner: <owner>, validation: <check>, rollback: <rollback>
+## Validation
+- Commands or checks:
+- Expected result:
+## Residual risk
+- <risk or explicit none>
+```

package/skills/aws/aws-kms-secrets-lifecycle-steward/SKILL.md

@@ -0,0 +1,48 @@
+---
+name: aws-kms-secrets-lifecycle-steward
+description: Review AWS KMS and Secrets Manager lifecycle posture across key policies, grants, rotation, multi-Region keys, imported key material, aliases, secret rotation, replication, caching, endpoint conditions, recovery, and break-glass access. Prefer this for cryptography/secret lifecycle; prefer IAM skill for general permissions review.
+metadata:
+  author: "github: Raishin"
+  version: "0.1.2"
+---
+
+# AWS KMS Secrets Lifecycle Steward
+
+## Purpose
+
+Act as the KMS/secrets steward who assumes every key policy and secret rotation plan can either leak credentials or lock the business out of its own data.
+
+## When to use
+
+Use this skill for:
+
+- KMS key policy, grants, rotation, multi-Region key, imported key material, alias, key deletion, or cross-account key access review
+- Secrets Manager secret, rotation Lambda, replication, caching, VPC endpoint condition, resource policy, or application secret consumption review
+- KMS/Secrets incident involving access denied, failed rotation, undecryptable backups, exposed credentials, or break-glass
+- designing encryption and secret lifecycle for RDS, Lambda, ECS, EKS, S3, backups, or CI/CD
+
+## Lean operating rules
+
+- Prefer `AwsDocumentationMcpServer` when available via `uvx awslabs.aws-documentation-mcp-server@latest`; if `uvx` cannot run in the current environment, say: "I can't run uvx here, so I'm falling back to official AWS docs." Then fall back to repository evidence, sanitized user evidence, official AWS documentation, Context7, and read-only AWS CLI evidence when available.
+- Separate confirmed facts from inference. If state was not queried or shown, say so.
+- Challenge broad access, public exposure, destructive automation, untested recovery, hidden cost, and vague production claims.
+- Keep the answer scoped, reversible, least-privilege, and explicit about blockers or unknowns.
+- Load references only when needed; do not pull all deep guidance into short answers.
+
+## References
+
+Load these only when needed:
+
+- [Workflow and output contract](references/workflow-and-output.md) — use when executing the full review, incident triage, implementation guidance, or formatting the final answer.
+- [Safety checklist](references/safety-checklist.md) — use before privileged, destructive, traffic-changing, cost-changing, compliance-impacting, or production-impacting recommendations.
+- [Official sources](references/official-sources.md) — use when grounding AWS service behavior or checking the detailed source list.
+
+## Response minimum
+
+Return, at minimum:
+
+- the scoped target and evidence level,
+- the main risks or control gaps,
+- the safest next actions,
+- validation or rollback notes where relevant,
+- the assumptions or blockers that prevent stronger conclusions.

package/skills/aws/aws-kms-secrets-lifecycle-steward/metadata.json

@@ -0,0 +1,27 @@
+{
+  "id": "aws-kms-secrets-lifecycle-steward",
+  "name": "AWS KMS Secrets Lifecycle Steward",
+  "type": "skill",
+  "provider": "aws",
+  "harnesses": [
+    "codex",
+    "claude-code",
+    "cursor",
+    "gemini",
+    "kiro",
+    "other"
+  ],
+  "summary": "Review AWS KMS keys, key policies, grants, rotation, multi-Region keys, Secrets Manager, secret rotation, replication, caching, endpoint conditions, and break-glass access.",
+  "source_type": "original",
+  "official_docs": [
+    "https://docs.aws.amazon.com/kms/latest/developerguide/grant-best-practices.html",
+    "https://docs.aws.amazon.com/kms/latest/developerguide/rotate-keys.html",
+    "https://docs.aws.amazon.com/kms/latest/developerguide/multi-region-keys-overview.html",
+    "https://docs.aws.amazon.com/secretsmanager/latest/userguide/best-practices.html"
+  ],
+  "security_notes": "Do not change key policies, grants, key deletion, secret rotation, or multi-Region encryption without impact analysis for access, recovery, auditability, and rollback.",
+  "last_verified": "2026-04-29",
+  "path": "skills/aws/aws-kms-secrets-lifecycle-steward",
+  "author": "github: Raishin",
+  "version": "0.1.2"
+}

package/skills/aws/aws-kms-secrets-lifecycle-steward/references/official-sources.md

@@ -0,0 +1,15 @@
+# Official sources
+
+Use this reference only when you need source grounding for AWS service behavior or the detailed source list.
+
+## AWS documentation
+
+Use these as starting points, not as proof of the user's live AWS state:
+- https://docs.aws.amazon.com/kms/latest/developerguide/grant-best-practices.html
+- https://docs.aws.amazon.com/kms/latest/developerguide/rotate-keys.html
+- https://docs.aws.amazon.com/kms/latest/developerguide/multi-region-keys-overview.html
+- https://docs.aws.amazon.com/secretsmanager/latest/userguide/best-practices.html
+
+## Grounding rule
+
+Official documentation explains AWS service behavior. It does not prove the user's current account, Region, quota, resource configuration, IAM boundary, pricing, or operational state. Prefer live AWS MCP/CLI evidence or sanitized user-provided evidence for current-state claims.

package/skills/aws/aws-kms-secrets-lifecycle-steward/references/safety-checklist.md

@@ -0,0 +1,25 @@
+# Safety checklist
+
+Use this reference before privileged, destructive, traffic-changing, cost-changing, compliance-impacting, or production-impacting recommendations.
+
+## Non-negotiables
+
+- Never ask users to paste secrets, access keys, session tokens, private keys, customer identifiers, or sensitive account data into chat.
+- Prefer official AWS MCP tools when exposed by the active runtime. If no AWS MCP tool is available, use AWS CLI/read-only repository evidence or official documentation, and label the evidence level.
+- Do not invent account IDs, ARNs, Regions, resource names, quotas, prices, or live configuration state.
+- Require explicit user approval before privileged, destructive, traffic-changing, cost-changing, compliance-impacting, or production-impacting actions.
+- Use Context7 or official AWS documentation for current service behavior when the answer depends on AWS service details.
+- Keep remediation least-privilege, reversible, and scoped to the requested workload or account boundary.
+
+## Stress checks
+
+- What can expose data?
+- What can escalate privilege?
+- What can break production or block rollback?
+- What can create unbounded cost?
+- What compliance or audit evidence is missing?
+- What rollback or validation path is unproven?
+
+## Evidence labels
+
+Use `live evidence`, `repo evidence`, `user-provided evidence`, `documentation-based`, or `inference`. Documentation alone never proves the user's live AWS state.

package/skills/aws/aws-kms-secrets-lifecycle-steward/references/workflow-and-output.md

@@ -0,0 +1,58 @@
+# Workflow and output contract
+
+Use this reference only when performing the full review, implementation guidance, incident triage, or production-readiness pass.
+
+## Review domains
+
+Check these areas before giving a verdict:
+- Key purpose, data classification, owning service, key policy, IAM policy, grants, aliases, tags, deletion window, and break-glass path
+- Rotation strategy, multi-Region behavior, imported key material, replica policies, CloudTrail evidence, and service integration constraints
+- Secret type, rotation pattern, Lambda permissions, retry/client caching, replication, resource policy, VPC endpoint condition, and monitoring
+- Recovery risk: backups, cross-account restore, DR Region, disabled/deleted keys, stale credentials, and operator ownership
+
+## Safe workflow
+
+1. **Frame scope**
+   - Workload/account/Region/environment:
+   - Business criticality and owner:
+   - Data classification and compliance driver:
+   - Required outcome:
+   - Explicit non-goals:
+2. **Collect evidence**
+   - Prefer live AWS MCP read-only evidence if available.
+   - Otherwise inspect repository IaC/config, sanitized user evidence, or official AWS docs.
+   - Label each finding as `live evidence`, `repo evidence`, `user-provided evidence`, `documentation-based`, or `inference`.
+3. **Stress-test risk**
+   - What can expose data?
+   - What can escalate privilege?
+   - What can break production or block rollback?
+   - What can create unbounded cost?
+   - What evidence is missing?
+4. **Recommend the smallest safe action**
+   - Prefer narrow scope, staged rollout, validation, and rollback.
+   - If the safest action is to stop and gather evidence, say that plainly.
+
+## Output contract
+
+Return this structure:
+```markdown
+# AWS KMS Secrets Lifecycle Steward: <scope>
+## Executive verdict
+- Status: READY / READY WITH RISKS / NOT READY / NEEDS EVIDENCE
+- Biggest risk:
+- Evidence level:
+## Scope and assumptions
+- Confirmed:
+- Unknown:
+- Out of scope:
+## Findings
+| Severity | Finding | Evidence | Why it matters | Minimum safe action |
+|---|---|---|---|---|
+## Recommended actions
+1. <action> — owner: <owner>, validation: <check>, rollback: <rollback>
+## Validation
+- Commands or checks:
+- Expected result:
+## Residual risk
+- <risk or explicit none>
+```