@raishin/vanguard-frontier-agentic 2.8.0 → 2.9.0

package/skills/oci/oci-limits-capacity-planner/references/mcp-and-evidence.md

@@ -0,0 +1,30 @@
+# MCP and evidence path
+
+Use this reference to choose the right evidence path without leaking environment details.
+
+## Evidence order
+
+1. Official OCI documentation for documented service behavior, limits, security guidance, and operational concepts.
+2. OCI API evidence through the user's configured read-only OCI MCP for API shape or sampled configured-environment observations.
+3. Sanitized user-provided evidence when live read-only evidence is unavailable.
+4. Explicit inference only when evidence is incomplete.
+
+## What each evidence type proves
+
+- Official documentation proves documented OCI behavior at the time checked.
+- Sampled OCI API evidence can prove API/CLI surface shape or observed configured-environment state at the time sampled.
+- User-provided evidence proves only what was provided and only if sanitized.
+- Inference is not proof; label it and keep recommendations conditional.
+
+## What evidence does not prove
+
+- Documentation does not prove the user's tenancy, compartments, IAM policies, limits, resources, billing state, security posture, or production readiness.
+- Sampled API evidence does not prove all regions, all compartments, all resources, future posture, or full operational readiness.
+- Command help proves command/API surface shape; it does not prove permission, resource existence, or safe execution.
+
+## Safe phrasing
+
+- “Official OCI documentation says...”
+- “OCI API evidence through the user's configured read-only OCI MCP shows...”
+- “The current state was not queried, so this remains an assumption.”
+- “This recommendation is documentation-based and needs environment validation before production change.”

package/skills/oci/oci-limits-capacity-planner/references/official-sources.md

@@ -0,0 +1,21 @@
+# Official sources
+
+Use these sources to ground service behavior before making production recommendations.
+
+## Oracle documentation checked on 2026-06-05
+
+- https://docs.oracle.com/en-us/iaas/Content/General/service-limits/default.htm
+- https://docs.oracle.com/en-us/iaas/Content/Quotas/Concepts/resourcequotas.htm
+- https://docs.oracle.com/en-us/iaas/Content/Quotas/Concepts/resourcequotas_topic-Available_Quotas_by_Service.htm
+
+## Sampled read-only OCI API evidence checked on 2026-06-05
+
+- OCI API evidence through the user's configured read-only OCI MCP was used for command/API surface shape only.
+- Command-help evidence confirms available list/filter surfaces; it does not prove permissions, resource existence, regional availability, capacity, quota, data correctness, or production readiness.
+
+## Grounding rules
+
+- Prefer the most specific Oracle documentation page for the service or feature being discussed.
+- If documentation and sampled API evidence appear to conflict, report the conflict and avoid stronger claims until resolved.
+- Do not cite internal tool names, local environment labels, connector identifiers, or environment-specific details in committed docs.
+- Do not paste sensitive identifiers or customer data into examples.

package/skills/oci/oci-limits-capacity-planner/references/safety-checklist.md

@@ -1,32 +1,35 @@
-# Safety Checklist
+# Safety checklist
 
-Use this checklist before recommending or executing changes for `oci-limits-capacity-planner`.
+Use this checklist before producing guidance, requesting evidence, or proposing changes.
 
-## Scope
+## Evidence labels
 
-- 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.
+- `documentation-based`: grounded in official OCI documentation only.
+- `sampled-api-shape`: grounded in read-only command/API help or metadata evidence.
+- `sampled-current-state`: grounded in read-only observations from the configured environment.
+- `user-supplied`: grounded in sanitized user evidence.
+- `inference`: reasoned from incomplete evidence; never present it as fact.
 
-## Access
+## Credential and identifier boundaries
 
-- 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.
+- Do not ask for credentials, tokens, private keys, API keys, config files, wallets, kubeconfigs, connection strings, customer data, or sensitive identifiers.
+- Do not commit environment-specific identifiers, internal tool names, local environment labels, connector IDs, or private endpoint details.
+- If the task requires live context, ask for a sanitized export or use approved read-only evidence paths.
 
-## Change safety
+## Mutation boundary
 
-- 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.
+Require explicit approval before creating, updating, deleting, moving, scaling, rotating, patching, enabling, disabling, refreshing, restoring, cutting over, opening network access, changing quotas, changing budgets, or changing access.
 
-## Platform portability
+## Approval gates
 
-- 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.
+- Confirm scope, owner, environment criticality, maintenance window, rollback plan, and validation target.
+- Separate read-only discovery from write actions.
+- Prefer least privilege and reversible changes.
+- Stop if evidence conflicts or if the blast radius is unknown.
+
+## Final-answer minimum
+
+- State evidence level and scope.
+- List blockers and unsafe assumptions.
+- Give safe next actions before risky actions.
+- Name what was not proved.

package/skills/oci/oci-limits-capacity-planner/references/workflow-and-output.md

@@ -0,0 +1,26 @@
+# Workflow and output contract
+
+Use this workflow for full reviews and live-guard decisions.
+
+## Execution flow
+
+1. Confirm the target service, scope, environment criticality, and desired decision.
+2. Load official source guidance and this skill's operations reference.
+3. Gather read-only OCI API evidence through the user's configured read-only OCI MCP only when current-state or API-shape evidence is needed.
+4. Classify findings as fact, sampled evidence, inference, blocker, or recommendation.
+5. Challenge broad permissions, destructive shortcuts, weak rollback, and unsupported production claims.
+6. Return concise findings with safe next actions and explicit unknowns.
+
+## Output contract
+
+Return these fields when the user asks for a review, guardrail, or production-readiness answer:
+
+- `verdict`: pass, pass-with-risk, blocked, or needs-evidence.
+- `evidence_level`: documentation-based, sampled-api-shape, sampled-current-state, user-supplied, or inference.
+- `blockers`: missing proof, unsafe assumptions, or approval gaps.
+- `safe_next_actions`: least-risk steps the user can take next.
+- `open_questions`: only questions that materially change the decision.
+
+## Tone
+
+Be blunt. Do not validate a weak plan. If the evidence is thin, say so and narrow the recommendation.

package/skills/oci/oci-live-autonomous-db-lifecycle-guard/SKILL.md

@@ -1,11 +1,11 @@
 ---
 name: oci-live-autonomous-db-lifecycle-guard
-description: Guard Autonomous Database lifecycle changes — scale, start, stop, clone, terminate — with protection-tag enforcement, backup verification, and connection-string impact analysis before any mutation.
-allowed-tools: Read Grep Glob WebFetch
+description: Guard Autonomous Database lifecycle changes such as scale, start, stop, clone, restore, wallet-impacting changes, and termination with backup, dependency, protection, approval, and rollback evidence.
+allowed-tools: Read Grep Glob
 metadata:
-  author: "github: Raishin"
-  version: "0.1.0"
-  updated: "2026-05-05"
+  author: github: Raishin
+  version: 0.1.1
+  updated: "2026-06-05"
   category: data
 ---
 
@@ -13,40 +13,39 @@ metadata:
 
 ## Purpose
 
-Act as the guarded live OCI operator for oci-live-autonomous-db-lifecycle-guard work. Insist on preview evidence before execution and treat ambiguous target or approval state as a stop condition.
+Act as a blunt OCI guard for this domain. Kill unverified readiness claims, broad access, destructive shortcuts, weak rollback, and source-free operational advice.
 
-## When to use
+Use this skill for:
 
-Use this skill when:
-
-- an Autonomous Database must be scaled, started, stopped, cloned, or terminated against a live OCI environment
-- a protection tag must be audited before a lifecycle operation that could cause data loss or outage
-- an Autonomous Database backup or wallet must be confirmed before a scale or clone operation
+- Autonomous Database scale, start, stop, clone, restore, or termination review
+- backup, protection, wallet, and connection-impact checks
+- lifecycle-state and Data Guard readiness triage
+- production change approval for Autonomous Database operations
+- rollback and post-change validation planning
 
 ## Lean operating rules
 
-- Prefer OCI CLI (`oci`) official documentation when available; fall back to Oracle Cloud docs and sanitized user evidence.
-- Do not execute a live OCI change until tenancy, compartment, active principal, and resource ownership are explicit.
-- Prefer plan, detect-drift, inspect, read, describe, and rollback evidence before execution.
-- If the request skips preview or rollback design, push back.
-- Never print secrets, API keys, tenancy OCIDs, private key contents, or raw config values. Summarize sanitized evidence only.
-- Load references only when needed.
+- Prefer official OCI documentation, then OCI API evidence through the user's configured read-only OCI MCP when current-state or API-shape evidence is needed, then sanitized user evidence.
+- Separate confirmed facts from inference. If state was not queried or shown, say so.
+- Challenge broad scope, broad permissions, destructive shortcuts, and production claims without evidence.
+- Keep the answer scoped, reversible where possible, least-privilege, and explicit about blockers or unknowns.
+- Never ask the user to paste credentials, tokens, private keys, API keys, config files, tenancy identifiers, compartment identifiers, resource identifiers, customer data, wallets, kubeconfigs, connection strings, or secrets.
 
 ## References
 
 Load these only when needed:
 
-- [Preflight commands](references/preflight-commands.md) — OCI CLI commands to run before any mutation.
-- [Rollback playbook](references/rollback-playbook.md) — concrete rollback steps for this service.
-- [Permission model](references/permission-model.md) — OCI IAM policy statements and dynamic group guidance.
-- [Official sources](references/official-sources.md) — authoritative OCI documentation links.
+- [OCI Live Autonomous DB Lifecycle Guard Operations](references/autonomous-db-lifecycle-operations.md) — use for current service behavior, common failure modes, hard design rules, verification targets, and push-back conditions.
+- [Safety checklist](references/safety-checklist.md) — use for evidence labels, risk gates, mutation boundaries, approval rules, credential boundaries, and current-state caveats.
+- [MCP and evidence path](references/mcp-and-evidence.md) — use when choosing documentation-based evidence, sampled read-only OCI API evidence, or sanitized user evidence.
+- [Workflow and output contract](references/workflow-and-output.md) — use when executing the full review, applying stress checks, or formatting the final answer.
+- [Official sources](references/official-sources.md) — use when you need the detailed Oracle documentation list or source notes.
 
 ## Response minimum
 
 Return, at minimum:
 
-- confirmed tenancy, compartment, and active principal
-- preflight evidence (plan output, drift result, inspect/read, health check)
-- approval status for the proposed mutation
-- rollback posture or explicit statement of what cannot be rolled back
-- post-action verification steps or refusal reason
+- the scoped target and evidence level,
+- the main risks or control gaps,
+- the safest next actions,
+- the assumptions or blockers that prevent stronger conclusions.

package/skills/oci/oci-live-autonomous-db-lifecycle-guard/metadata.json

@@ -11,17 +11,17 @@
     "kiro",
     "other"
   ],
-  "summary": "Guard Autonomous Database lifecycle changes \u2014 scale, start, stop, clone, terminate \u2014 with protection-tag enforcement, backup verification, and connection-string impact analysis before any mutation.",
+  "summary": "Guard Autonomous Database lifecycle changes such as scale, start, stop, clone, restore, wallet-impacting changes, and termination with backup, dependency, protection, approval, and rollback evidence.",
   "source_type": "original",
   "official_docs": [
-    "https://docs.oracle.com/en-us/iaas/Content/Database/Tasks/adbscaling.htm",
-    "https://docs.oracle.com/en-us/iaas/Content/Database/Tasks/adbstopstart.htm",
-    "https://docs.oracle.com/en-us/iaas/Content/Database/Tasks/adbcloning.htm",
-    "https://docs.oracle.com/en-us/iaas/Content/Database/Tasks/adbbackingup.htm"
+    "https://docs.oracle.com/en-us/iaas/autonomous-database-serverless/doc/scale-autonomous-database.html",
+    "https://docs.oracle.com/en-us/iaas/autonomous-database-serverless/doc/start-stop-autonomous-database.html",
+    "https://docs.oracle.com/en-us/iaas/autonomous-database-serverless/doc/autonomous-clone.html",
+    "https://docs.oracle.com/en-us/iaas/autonomous-database-serverless/doc/backup-recovery-autonomous.html"
   ],
-  "security_notes": "ADB termination is permanent \u2014 the database and all backups are deleted. Always verify protection tags before any terminate operation. ADB storage scale-up cannot be reversed. Termination blocked by defined-tag protection requires explicit tag removal approval.",
-  "last_verified": "2026-04-30",
+  "security_notes": "OCI skills must use official documentation and read-only discovery first, keep identifiers and secrets out of prompts and committed docs, and require explicit approval before mutations.",
+  "last_verified": "2026-06-05",
   "path": "skills/oci/oci-live-autonomous-db-lifecycle-guard",
   "author": "github: Raishin",
-  "version": "0.1.0"
+  "version": "0.1.1"
 }

package/skills/oci/oci-live-autonomous-db-lifecycle-guard/references/autonomous-db-lifecycle-operations.md

@@ -0,0 +1,63 @@
+# OCI Live Autonomous DB Lifecycle Guard Operations
+
+> Version note: OCI service behavior and tooling change over time. Verify exact command syntax, permissions, regional availability, and feature maturity against official OCI documentation before production use. Do not paste secrets or sensitive identifiers into commands, files, or chat.
+
+Use this reference for current, source-grounded service behavior and the hard review gates that the lean `SKILL.md` intentionally does not carry.
+
+## What people get wrong
+
+- Stopping or scaling production without connection, batch, backup, and dependency evidence.
+- Treating AVAILABLE as proof the application can tolerate a lifecycle action.
+- Assuming storage scale, clone, restore, or termination has a clean rollback.
+- Ignoring wallet, connection-string, Data Guard, and backup-recency impact.
+
+## Officially grounded service shape
+
+- Official OCI documentation describes Autonomous Database lifecycle operations including scaling, start/stop, cloning, backup, and recovery, but documentation does not prove a target database is safe to mutate.
+- OCI API evidence through the user’s configured read-only OCI MCP shows Autonomous Database listing is compartment-scoped and can filter by infrastructure type, lifecycle state, workload, version, free tier, display name, refreshable clone, Data Guard, and resource-pool fields. Treat this as API-shape evidence, not mutation approval.
+
+Documentation evidence proves documented OCI service behavior. OCI API evidence through the user's configured read-only OCI MCP can prove sampled API shape or observed configured-environment state. Neither proves broad tenancy posture, all-region availability, quota, or operational readiness.
+
+## Non-negotiable design rules
+
+- Separate lifecycle state, backup state, application dependency, wallet/connectivity, Data Guard, and protection evidence.
+- Require explicit approval before scale, start, stop, clone, restore, refresh, or termination.
+- Treat termination, restore, and irreversible capacity changes as blocked until owner, backup, rollback, and validation are proven.
+- Do not expose database names, endpoints, wallets, credentials, customer data, or sensitive identifiers.
+
+## Minimal safe implementation flow
+
+- Confirm target database, operation, criticality, owner, maintenance window, and rollback expectation using sanitized references.
+- Use official docs for lifecycle semantics and sampled read-only evidence for current lifecycle/API shape.
+- Check dependencies, backup/restore, connection impact, and protection controls before approval.
+- Return verdict, blockers, approval state, rollback posture, and post-change checks.
+
+## High-risk assumptions to kill
+
+- “AVAILABLE means safe to change.”
+- “A backup exists and is restorable.”
+- “Clone or restore has no downstream impact.”
+- “Stopping a database only affects the database team.”
+
+Those are lazy assumptions.
+
+## Safe command/code verification targets
+
+- List target database lifecycle and configuration without exposing identifiers.
+- Check backup recency, restore path, Data Guard state, wallet/connection impact, and dependent workload windows.
+- Capture pre-change state and owner approval before mutation.
+- Validate application connectivity, performance, backups, and alerts after change.
+
+## Safe verification targets
+
+- Scope is confirmed without exposing sensitive identifiers in chat or committed docs.
+- Required permissions are least-privilege and separated by read, use, manage, and destructive actions.
+- Current-state findings are labeled as sampled evidence, not broad proof.
+- Risky mutations have explicit approval, blast-radius review, rollback, and validation.
+- Official-source claims are linked to service docs and not overstated as live posture.
+
+## When to push back
+
+- The user asks to terminate, restore, stop, or scale without owner approval and rollback evidence.
+- The backup or dependency evidence is missing.
+- The request includes wallet, endpoint, credential, or customer data.

package/skills/oci/oci-live-autonomous-db-lifecycle-guard/references/mcp-and-evidence.md

@@ -0,0 +1,30 @@
+# MCP and evidence path
+
+Use this reference to choose the right evidence path without leaking environment details.
+
+## Evidence order
+
+1. Official OCI documentation for documented service behavior, limits, security guidance, and operational concepts.
+2. OCI API evidence through the user's configured read-only OCI MCP for API shape or sampled configured-environment observations.
+3. Sanitized user-provided evidence when live read-only evidence is unavailable.
+4. Explicit inference only when evidence is incomplete.
+
+## What each evidence type proves
+
+- Official documentation proves documented OCI behavior at the time checked.
+- Sampled OCI API evidence can prove API/CLI surface shape or observed configured-environment state at the time sampled.
+- User-provided evidence proves only what was provided and only if sanitized.
+- Inference is not proof; label it and keep recommendations conditional.
+
+## What evidence does not prove
+
+- Documentation does not prove the user's tenancy, compartments, IAM policies, limits, resources, billing state, security posture, or production readiness.
+- Sampled API evidence does not prove all regions, all compartments, all resources, future posture, or full operational readiness.
+- Command help proves command/API surface shape; it does not prove permission, resource existence, or safe execution.
+
+## Safe phrasing
+
+- “Official OCI documentation says...”
+- “OCI API evidence through the user's configured read-only OCI MCP shows...”
+- “The current state was not queried, so this remains an assumption.”
+- “This recommendation is documentation-based and needs environment validation before production change.”

package/skills/oci/oci-live-autonomous-db-lifecycle-guard/references/official-sources.md

@@ -1,13 +1,22 @@
-# Official Sources: OCI Live Autonomous DB Lifecycle Guard
+# Official sources
 
-## OCI Autonomous Database
+Use these sources to ground service behavior before making production recommendations.
 
-- https://docs.oracle.com/en-us/iaas/Content/Database/Concepts/adboverview.htm
-- https://docs.oracle.com/en-us/iaas/Content/Database/Tasks/adbmanaging.htm
-- https://docs.oracle.com/en-us/iaas/Content/Database/Tasks/adbbackingup.htm
-- https://docs.oracle.com/en-us/iaas/Content/Database/Tasks/adbcloning.htm
+## Oracle documentation checked on 2026-06-05
 
-## Source-grounding rule
+- https://docs.oracle.com/en-us/iaas/autonomous-database-serverless/doc/scale-autonomous-database.html
+- https://docs.oracle.com/en-us/iaas/autonomous-database-serverless/doc/start-stop-autonomous-database.html
+- https://docs.oracle.com/en-us/iaas/autonomous-database-serverless/doc/autonomous-clone.html
+- https://docs.oracle.com/en-us/iaas/autonomous-database-serverless/doc/backup-recovery-autonomous.html
 
-Use official Oracle Cloud Infrastructure documentation as the source of truth for ADB behavior.
-Lifecycle state transitions and backup retention windows must be verified from current OCI docs.
+## Sampled read-only OCI API evidence checked on 2026-06-05
+
+- OCI API evidence through the user's configured read-only OCI MCP was used for command/API surface shape only.
+- Command-help evidence confirms available list/filter surfaces; it does not prove permissions, resource existence, regional availability, capacity, quota, data correctness, or production readiness.
+
+## Grounding rules
+
+- Prefer the most specific Oracle documentation page for the service or feature being discussed.
+- If documentation and sampled API evidence appear to conflict, report the conflict and avoid stronger claims until resolved.
+- Do not cite internal tool names, local environment labels, connector identifiers, or environment-specific details in committed docs.
+- Do not paste sensitive identifiers or customer data into examples.

package/skills/oci/oci-live-autonomous-db-lifecycle-guard/references/safety-checklist.md

@@ -0,0 +1,35 @@
+# Safety checklist
+
+Use this checklist before producing guidance, requesting evidence, or proposing changes.
+
+## Evidence labels
+
+- `documentation-based`: grounded in official OCI documentation only.
+- `sampled-api-shape`: grounded in read-only command/API help or metadata evidence.
+- `sampled-current-state`: grounded in read-only observations from the configured environment.
+- `user-supplied`: grounded in sanitized user evidence.
+- `inference`: reasoned from incomplete evidence; never present it as fact.
+
+## Credential and identifier boundaries
+
+- Do not ask for credentials, tokens, private keys, API keys, config files, wallets, kubeconfigs, connection strings, customer data, or sensitive identifiers.
+- Do not commit environment-specific identifiers, internal tool names, local environment labels, connector IDs, or private endpoint details.
+- If the task requires live context, ask for a sanitized export or use approved read-only evidence paths.
+
+## Mutation boundary
+
+Require explicit approval before creating, updating, deleting, moving, scaling, rotating, patching, enabling, disabling, refreshing, restoring, cutting over, opening network access, changing quotas, changing budgets, or changing access.
+
+## Approval gates
+
+- Confirm scope, owner, environment criticality, maintenance window, rollback plan, and validation target.
+- Separate read-only discovery from write actions.
+- Prefer least privilege and reversible changes.
+- Stop if evidence conflicts or if the blast radius is unknown.
+
+## Final-answer minimum
+
+- State evidence level and scope.
+- List blockers and unsafe assumptions.
+- Give safe next actions before risky actions.
+- Name what was not proved.

package/skills/oci/oci-live-autonomous-db-lifecycle-guard/references/workflow-and-output.md

@@ -0,0 +1,26 @@
+# Workflow and output contract
+
+Use this workflow for full reviews and live-guard decisions.
+
+## Execution flow
+
+1. Confirm the target service, scope, environment criticality, and desired decision.
+2. Load official source guidance and this skill's operations reference.
+3. Gather read-only OCI API evidence through the user's configured read-only OCI MCP only when current-state or API-shape evidence is needed.
+4. Classify findings as fact, sampled evidence, inference, blocker, or recommendation.
+5. Challenge broad permissions, destructive shortcuts, weak rollback, and unsupported production claims.
+6. Return concise findings with safe next actions and explicit unknowns.
+
+## Output contract
+
+Return these fields when the user asks for a review, guardrail, or production-readiness answer:
+
+- `verdict`: pass, pass-with-risk, blocked, or needs-evidence.
+- `evidence_level`: documentation-based, sampled-api-shape, sampled-current-state, user-supplied, or inference.
+- `blockers`: missing proof, unsafe assumptions, or approval gaps.
+- `safe_next_actions`: least-risk steps the user can take next.
+- `open_questions`: only questions that materially change the decision.
+
+## Tone
+
+Be blunt. Do not validate a weak plan. If the evidence is thin, say so and narrow the recommendation.

package/skills/oci/oci-live-cost-budget-runaway-guard/SKILL.md

@@ -1,11 +1,11 @@
 ---
 name: oci-live-cost-budget-runaway-guard
-description: Gate OCI budget mutations and GPU/HPC shape provisioning against compartment spend limits, with inventory searches, quota audits, and emergency spend-stop playbooks.
-allowed-tools: Read Grep Glob WebFetch
+description: Gate OCI budget, alert, quota, and high-cost compute actions with spend evidence, owner approval, financial authority, rollback, and emergency stop boundaries.
+allowed-tools: Read Grep Glob
 metadata:
-  author: "github: Raishin"
-  version: "0.1.0"
-  updated: "2026-05-05"
+  author: github: Raishin
+  version: 0.1.1
+  updated: "2026-06-05"
   category: finops
 ---
 
@@ -13,40 +13,39 @@ metadata:
 
 ## Purpose
 
-Act as the guarded live OCI operator for oci-live-cost-budget-runaway-guard work. Insist on preview evidence before execution and treat ambiguous target or approval state as a stop condition.
+Act as a blunt OCI guard for this domain. Kill unverified readiness claims, broad access, destructive shortcuts, weak rollback, and source-free operational advice.
 
-## When to use
+Use this skill for:
 
-Use this skill when:
-
-- an OCI budget rule threshold or alert must be modified for a tenancy or compartment
-- a GPU or HPC shape provisioning request requires spend-limit approval before creating
-- a runaway GPU cost event is detected and emergency quota reduction or instance stop is needed
+- budget and alert threshold mutation review
+- runaway spend triage and emergency containment
+- GPU, HPC, or expensive shape provisioning review
+- quota or limit change review for costly resources
+- budget, usage, tag, and owner evidence checks
 
 ## Lean operating rules
 
-- Prefer OCI CLI (`oci`) official documentation when available; fall back to Oracle Cloud docs and sanitized user evidence.
-- Do not execute a live OCI change until tenancy, compartment, active principal, and resource ownership are explicit.
-- Prefer plan, detect-drift, inspect, read, describe, and rollback evidence before execution.
-- If the request skips preview or rollback design, push back.
-- Never print secrets, API keys, tenancy OCIDs, private key contents, or raw config values. Summarize sanitized evidence only.
-- Load references only when needed.
+- Prefer official OCI documentation, then OCI API evidence through the user's configured read-only OCI MCP when current-state or API-shape evidence is needed, then sanitized user evidence.
+- Separate confirmed facts from inference. If state was not queried or shown, say so.
+- Challenge broad scope, broad permissions, destructive shortcuts, and production claims without evidence.
+- Keep the answer scoped, reversible where possible, least-privilege, and explicit about blockers or unknowns.
+- Never ask the user to paste credentials, tokens, private keys, API keys, config files, tenancy identifiers, compartment identifiers, resource identifiers, customer data, wallets, kubeconfigs, connection strings, or secrets.
 
 ## References
 
 Load these only when needed:
 
-- [Preflight commands](references/preflight-commands.md) — OCI CLI commands to run before any mutation.
-- [Rollback playbook](references/rollback-playbook.md) — concrete rollback steps for this service.
-- [Permission model](references/permission-model.md) — OCI IAM policy statements and dynamic group guidance.
-- [Official sources](references/official-sources.md) — authoritative OCI documentation links.
+- [OCI Live Cost Budget Runaway Guard Operations](references/cost-budget-runaway-operations.md) — use for current service behavior, common failure modes, hard design rules, verification targets, and push-back conditions.
+- [Safety checklist](references/safety-checklist.md) — use for evidence labels, risk gates, mutation boundaries, approval rules, credential boundaries, and current-state caveats.
+- [MCP and evidence path](references/mcp-and-evidence.md) — use when choosing documentation-based evidence, sampled read-only OCI API evidence, or sanitized user evidence.
+- [Workflow and output contract](references/workflow-and-output.md) — use when executing the full review, applying stress checks, or formatting the final answer.
+- [Official sources](references/official-sources.md) — use when you need the detailed Oracle documentation list or source notes.
 
 ## Response minimum
 
 Return, at minimum:
 
-- confirmed tenancy, compartment, and active principal
-- preflight evidence (plan output, drift result, inspect/read, health check)
-- approval status for the proposed mutation
-- rollback posture or explicit statement of what cannot be rolled back
-- post-action verification steps or refusal reason
+- the scoped target and evidence level,
+- the main risks or control gaps,
+- the safest next actions,
+- the assumptions or blockers that prevent stronger conclusions.

package/skills/oci/oci-live-cost-budget-runaway-guard/metadata.json

@@ -11,17 +11,17 @@
     "kiro",
     "other"
   ],
-  "summary": "Gate OCI budget mutations and GPU/HPC shape provisioning against compartment spend limits, with inventory searches, quota audits, and emergency spend-stop playbooks.",
+  "summary": "Gate OCI budget, alert, quota, and high-cost compute actions with spend evidence, owner approval, financial authority, rollback, and emergency stop boundaries.",
   "source_type": "original",
   "official_docs": [
+    "https://docs.oracle.com/iaas/Content/Billing/Concepts/budgetsoverview.htm",
     "https://docs.oracle.com/en-us/iaas/Content/Billing/Tasks/managingbudgets.htm",
-    "https://docs.oracle.com/en-us/iaas/Content/Compute/Tasks/managinginstances.htm",
-    "https://docs.oracle.com/en-us/iaas/Content/Tagging/Tasks/managingtagsandtagnamespaces.htm",
+    "https://docs.oracle.com/iaas/Content/Billing/Tasks/managingalertrules.htm",
     "https://docs.oracle.com/en-us/iaas/Content/General/Concepts/resourcequotas.htm"
   ],
-  "security_notes": "GPU/HPC shapes (BM.GPU4.8, A100, BM.HPC2.36) can generate six-figure monthly costs when left running. Never approve quota increases or budget threshold raises without explicit financial-authority approval. Emergency stop requires Compute operator rights \u2014 escalate if not held.",
-  "last_verified": "2026-04-30",
+  "security_notes": "OCI skills must use official documentation and read-only discovery first, keep identifiers and secrets out of prompts and committed docs, and require explicit approval before mutations.",
+  "last_verified": "2026-06-05",
   "path": "skills/oci/oci-live-cost-budget-runaway-guard",
   "author": "github: Raishin",
-  "version": "0.1.0"
+  "version": "0.1.1"
 }