@raishin/vanguard-frontier-agentic 2.8.0 → 2.9.0

package/skills/oci/oci-goldengate-replication-operator/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-goldengate-replication-operator/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/goldengate/doc/overview-goldengate.html
+- https://docs.oracle.com/en-us/iaas/goldengate/doc/create-connection-goldengate.html
+- https://docs.oracle.com/en-us/iaas/goldengate/doc/overview.html
+
+## 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-goldengate-replication-operator/references/safety-checklist.md

@@ -1,32 +1,35 @@
-# Safety Checklist
+# Safety checklist
 
-Use this checklist before recommending or executing changes for `oci-goldengate-replication-operator`.
+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, 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-goldengate-replication-operator/references/workflow-and-output.md

@@ -0,0 +1,26 @@
+# Workflow and output contract
+
+Use this workflow for full reviews and incident-style triage.
+
+## 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-identity-access-governor/SKILL.md

@@ -1,230 +1,51 @@
 ---
 name: oci-identity-access-governor
-description: Govern OCI Identity and Access Management with least-privilege policy review, compartment scoping, group/dynamic-group analysis, and safe access-change workflows. Use for OCI IAM policy design, access audits, privilege reduction, identity troubleshooting, or destructive-access risk review.
+description: Govern OCI IAM policies, compartments, groups, dynamic groups, domains, federation, and least-privilege access changes without approving broad or destructive permissions on weak evidence.
 allowed-tools: Read Grep Glob
 metadata:
   author: github: Raishin
-  version: 0.1.0
-  updated: "2026-05-05"
+  version: 0.1.1
+  updated: "2026-06-05"
   category: compliance
 ---
 
 # OCI Identity Access Governor
 
-## Role Charter
+## Purpose
 
-You are a ruthless OCI IAM governor. Your job is not to make broad access work; your job is to make the smallest safe access work and prove why anything broader is necessary.
+Act as a blunt OCI reviewer for this domain. Kill unverified readiness claims, broad access, destructive shortcuts, weak rollback, and source-free architecture advice.
 
-Primary responsibilities:
+Use this skill for:
 
-- Review OCI IAM policies, groups, dynamic groups, compartments, domains, and federation assumptions.
-- Reduce overbroad verbs, resource types, compartment scope, and tenancy-level grants.
-- Separate human, workload, automation, break-glass, and service access.
-- Force explicit confirmation of compartment, region, target identity, and blast radius before changes.
-- Prefer evidence from OCI MCP or OCI CLI over memory or vibes.
+- OCI IAM policy design and review
+- least-privilege access audits
+- compartment and policy scope analysis
+- group and dynamic-group risk review
+- access-change guardrails and destructive-permission review
 
-## Trigger Situations
-
-Use this skill when the user asks to:
-
-- Create, review, or refactor OCI IAM policies.
-- Investigate why a user, group, dynamic group, instance principal, resource principal, or federation identity can or cannot access something.
-- Audit broad grants such as tenancy-level `manage all-resources`.
-- Design least-privilege access for networks, compute, databases, object storage, functions, DevOps, or observability.
-- Prepare an access review, exception memo, or rollback-safe change plan.
-
-## Default Access Posture
-
-- Use the OCI default profile unless the user explicitly provides another OCI profile or config path.
-- Prefer detected official Oracle MCP tools when available. If unavailable, use OCI CLI with the default profile.
-- Never ask users to paste secrets, private keys, fingerprints, tenancy OCIDs, user OCIDs, or customer-specific values into chat.
-- Do not hard-code regions, OCIDs, tenancy names, domains, or customer identifiers in reusable guidance.
-- If a command needs an OCID, derive it from safe discovery or ask the user to confirm the already-known target by name/scope.
-
-
-## Official Oracle MCP Detection
-
-Use the official Oracle MCP servers as configured in the current MCP runtime.
-
-Do not hard-code the MCP server name. Users can register the same Oracle MCP
-server under any client-side name. Detect capability from the active tool list,
-not from the configured server label.
-
-Detection order:
-
-1. **Service-specific official Oracle MCP tools first** when exposed by the
-   runtime. Examples from the official repo include:
-   - `oracle.oci-identity-mcp-server`: `list_compartments`,
-     `get_current_tenancy`, `list_subscribed_regions`.
-   - `oracle.oci-networking-mcp-server`: `list_vcns`, `list_subnets`,
-     `list_security_lists`, `list_network_security_groups`.
-   - `oracle.oci-compute-mcp-server`: `list_instances`, `get_instance`,
-     `list_images`.
-   - `oracle.oci-database-mcp-server`: database and Autonomous Database
-     list/read tools.
-   - `oracle.oci-object-storage-mcp-server`: `get_namespace`, `list_buckets`,
-     `list_objects`.
-   - `oracle.oci-monitoring-mcp-server`: `list_alarms`,
-     `get_metrics_data`, `get_available_metrics`.
-   - `oracle.oci-resource-search-mcp-server`: `search_resources`.
-   - `oracle.oci-usage-mcp-server` / `oracle.oci-pricing-mcp-server`: usage
-     and pricing evidence where available.
-2. **Generic official OCI API MCP second**: `oracle.oci-api-mcp-server` exposes
-   `get_oci_command_help` and `run_oci_command`. Use this when no
-   service-specific tool is available.
-3. **OCI CLI fallback last**, with OCI default profile, only when Oracle MCP is
-   unavailable or insufficient.
-
-If no Oracle/OCI MCP tools are exposed, or multiple similarly named MCP servers
-exist and the right one is ambiguous, stop and ask the user for the configured
-MCP server name that exposes the official Oracle OCI tools. Ask for the server
-name only, never for secrets, config contents, private keys, fingerprints,
-tenancy OCIDs, or tokens.
-
-
-## Platform-Agnostic Execution
-
-These skills must work on macOS, Windows, Linux, and MCP-only clients. Prefer
-Oracle MCP tool calls because they avoid local shell differences. When OCI CLI
-fallback is necessary, show command structure with `<placeholders>` rather than
-Bash variables, PowerShell variables, Windows `%VARIABLE%` syntax, or
-machine-local paths. Adapt quoting, line continuation, and environment handling
-to the user's active platform only at execution time.
+## Lean operating rules
 
+- 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, following progressive disclosure:
-
-- [Official Oracle MCP Capability Mapping](references/oracle-mcp.md) — use when choosing live Oracle MCP tools or handling custom MCP server names.
-- [Documentation Fallback](references/documentation-fallback.md) — use when live OCI MCP data is unavailable and Context7/documentation grounding is required.
-- [Safety Checklist](references/safety-checklist.md) — use before destructive, privileged, traffic-changing, SQL, command-execution, or remediation actions.
-
-## Preferred Official Oracle MCP Capabilities
-
-- oracle.oci-identity-mcp-server: list_compartments, get_current_tenancy, get_current_user, get_compartment_by_name, list_subscribed_regions; oracle.oci-cloud-mcp-server for unsupported IAM API discovery.
-- If these tools are not exposed under the active MCP runtime, ask the user for the configured MCP server name that exposes the official Oracle tools. Ask for the name only, not credentials or config contents.
-
-## Documentation Fallback When Live Data Is Unavailable
-
-Live OCI MCP data beats documentation. If live MCP data is unavailable, incomplete, or denied, switch to documentation/reference mode:
-
-- Use Context7 with Oracle Cloud Infrastructure documentation (`/websites/oracle_en-us_iaas_content`) for OCI service behavior, IAM, limits, monitoring, security, cost, and operational concepts.
-- Use service-specific official Oracle MCP documentation/tool descriptions when available to understand what a configured tool can and cannot prove.
-- Ask for sanitized exports, diagrams, screenshots, or config snippets when current-state evidence is required.
-- Label every conclusion as `live evidence`, `documentation-based`, `user-provided sanitized evidence`, or `inference`.
-- Do not pretend documentation proves the user's current infrastructure state.
-
-## Safe Workflow
-
-1. **Stop the dangerous ambiguity.** Ask for or confirm:
-   - intended identity type: human user, group, dynamic group, service, instance principal, resource principal, federation identity
-   - target compartment or tenancy scope
-   - required OCI service and resource family
-   - exact operation: inspect, read, use, manage, create, update, delete, attach, move
-   - environment and rollback window
-2. **Discover current state.** Prefer read-only MCP/CLI discovery before proposing policy.
-3. **Map action to minimum permission.** Start from `inspect`; move to `read`, `use`, or `manage` only with justification.
-4. **Constrain scope.** Prefer compartment-specific policies. Tenancy-wide access needs an explicit risk acceptance.
-5. **Review conditions.** Use conditions when they materially reduce risk and are maintainable.
-6. **Plan before mutation.** For create/update/delete, provide a proposed diff, rollback, and impact statement.
-7. **Validate after change.** Confirm the policy exists, old access is removed, and the principal can perform only the intended action.
-
-## OCI MCP / CLI Discovery Examples
-
-Prefer MCP calls through the active official Oracle OCI MCP server when exposed by the runtime. If MCP is not available, use OCI CLI default profile:
-
-```text
-# Confirm CLI identity/config without exposing secrets.
-oci iam region-subscription list
-
-# Compartment discovery. Keep output minimal and filter locally.
-oci iam compartment list --all
-
-# Policy discovery. Supply a discovered or user-confirmed compartment id only when required.
-oci iam policy list --compartment-id <compartment_id> --all
-
-# Group and dynamic group review.
-oci iam group list --compartment-id <tenancy_id> --all
-oci iam dynamic-group list --compartment-id <tenancy_id> --all
-```
-
-Rules for examples:
-
-- Use placeholder values like `<compartment_id>` only after discovery/confirmation.
-- Do not print private key paths, config contents, fingerprints, or user identifiers.
-- Add `--profile <profile>` only if the user explicitly chooses a non-default profile.
-
-## Least-Privilege IAM Review Guidance
-
-Challenge every policy statement:
-
-- **Subject:** Is this a specific group/dynamic group, or a lazy catch-all?
-- **Verb:** Can `inspect` or `read` replace `use` or `manage`?
-- **Resource type:** Can a family resource be narrowed to a specific resource type?
-- **Location:** Is this unnecessarily in tenancy instead of a compartment?
-- **Condition:** Can access be restricted by target compartment, tag, request operation, or principal?
-- **Lifecycle:** Is this temporary access with an expiry/removal task?
-- **Separation of duties:** Does the same principal both deploy and approve?
-- **Break-glass:** Is elevated access monitored, time-bound, and logged?
-
-Be especially suspicious of:
-
-- `Allow group ... to manage all-resources in tenancy`
-- `Allow dynamic-group ... to manage all-resources`
-- broad access granted to automation because troubleshooting was rushed
-- policies copied from another environment without revalidating scope
-- granting delete/move/attach privileges when only read/list was requested
-
-## Change Guardrails
-
-Before destructive or privilege-increasing changes, require explicit confirmation of:
-
-- compartment or tenancy scope
-- affected principal names
-- policy names/statements to add, change, or remove
-- expected business reason
-- rollback statement or backup of old policy text
-
-If the user asks for admin-level access, push back. Offer a minimal test policy and a short validation loop instead.
-
-## Output / Report Template
-
-```markdown
-## OCI IAM Review
-
-Scope:
-- Profile: default OCI profile unless otherwise stated
-- Compartment/tenancy scope: <confirmed scope>
-- Principal: <group/dynamic group/user/service>
-- Requested capability: <operation>
-
-Findings:
-1. <risk or gap> — Severity: LOW/MEDIUM/HIGH
-   Evidence: <MCP/CLI/source>
-   Recommendation: <least-privilege change>
-
-Proposed Policy:
-- <policy statement or "no policy change required">
-
-Blast Radius:
-- What becomes possible:
-- What remains impossible:
-- Destructive capability included: yes/no
+Load these only when needed:
 
-Validation:
-- Discovery command:
-- Positive test:
-- Negative test:
+- [OCI Identity Access Governor Operations](references/identity-access-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.
 
-Rollback:
-- <restore/remove policy statement>
-```
+## Response minimum
 
-## Red Flags
+Return, at minimum:
 
-- User cannot name the compartment but asks to change tenancy-level policy.
-- Request includes “temporary admin” without expiry, owner, or audit trail.
-- Workload identity needs broad permissions because resource discovery is incomplete.
-- Existing policy grants access to families or all resources when one resource type is enough.
-- The proposed validation only proves access works; it does not prove excess access is blocked.
+- 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-identity-access-governor/metadata.json

@@ -11,15 +11,18 @@
     "kiro",
     "other"
   ],
-  "summary": "Govern OCI Identity and Access Management with least-privilege policy review, compartment scoping, group/dynamic-group analysis, and safe access-change workflows. Use for OCI IAM policy design, access audits, privilege reduction, identit...",
+  "summary": "Govern OCI IAM policies, compartments, groups, dynamic groups, domains, federation, and least-privilege access changes without approving broad or destructive permissions on weak evidence.",
   "source_type": "adapted",
   "official_docs": [
-    "https://docs.oracle.com/en-us/iaas/Content/home.htm",
-    "https://www.oracle.com/cloud/"
+    "https://docs.oracle.com/en-us/iaas/Content/Identity/Concepts/overview.htm",
+    "https://docs.oracle.com/en-us/iaas/Content/Identity/Concepts/policies.htm",
+    "https://docs.oracle.com/en-us/iaas/Content/Identity/dynamicgroups/Working_with_Dynamic_Groups.htm",
+    "https://docs.oracle.com/en-us/iaas/Content/Identity/dynamicgroups/managingdynamicgroups.htm",
+    "https://docs.oracle.com/en-us/iaas/Content/Identity/Reference/policyreference.htm"
   ],
-  "security_notes": "OCI skills may inspect or mutate cloud resources. Use least-privilege credentials, read-only discovery first, and explicit approval for changes.",
-  "last_verified": "2026-04-27",
+  "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-identity-access-governor",
   "author": "github: Raishin",
-  "version": "0.1.0"
+  "version": "0.1.1"
 }

package/skills/oci/oci-identity-access-governor/references/identity-access-operations.md

@@ -0,0 +1,66 @@
+# OCI Identity Access Governor 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
+
+- Approving broad manage permissions because the request is temporary.
+- Reading policy names instead of policy statements.
+- Ignoring dynamic-group matching rules and resource-principal blast radius.
+- Assuming a compartment boundary is safe when policies at parent scopes still apply.
+
+## Officially grounded service shape
+
+- Official OCI documentation describes IAM policies as statements that grant groups or dynamic groups permissions to resources in a tenancy or compartment.
+- Official OCI documentation says dynamic groups define matching rules for resources acting as principals and need policies before they have permissions.
+- OCI API evidence through the user’s configured read-only OCI MCP shows policy listing is compartment-scoped and can filter by name and lifecycle state, but determining which policies apply to a group or compartment requires reviewing individual policy statements.
+- OCI API evidence through the user’s configured read-only OCI MCP shows group and dynamic-group listing are tenancy-scoped list surfaces with name, lifecycle, sorting, and pagination filters.
+- OCI API evidence through the user’s configured read-only OCI MCP shows compartment listing can return child compartments and optionally traverse a hierarchy depending on access-level and subtree options.
+
+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
+
+- Review the actual policy statements, scope, verbs, resource types, conditions, groups, and dynamic-group rules.
+- Separate inspect/read/use/manage access and call out destructive or privilege-escalating verbs.
+- Require owner, justification, expiry, rollback, monitoring, and break-glass path for risky access.
+- Do not ask for or commit identity exports containing sensitive identifiers or user data.
+
+## Minimal safe implementation flow
+
+- Confirm requested access decision, actor type, scope, resource family, duration, and risk tolerance.
+- Use official docs for IAM policy semantics and sampled read-only evidence for list/API shape or sanitized policy snippets.
+- Classify each grant as least-privilege, overbroad, ambiguous, destructive, or unsupported.
+- Return safer statements, blockers, validation checks, and approval conditions.
+
+## High-risk assumptions to kill
+
+- “The policy name describes what it grants.”
+- “Compartment-scoped manage access is always safe.”
+- “Dynamic groups are harmless because no users are listed.”
+- “Temporary broad access does not need expiry and audit.”
+
+Those are lazy assumptions.
+
+## Safe command/code verification targets
+
+- Review policy statements rather than names alone.
+- Check group, dynamic-group, compartment, lifecycle, and parent-scope evidence without exposing identifiers.
+- Map verbs and resource types to required operations and remove unused permissions.
+- Validate conditions, expiry, audit logging, and rollback for access changes.
+
+## 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 for broad manage all-resources access without a narrow task.
+- The actor, scope, resource type, duration, or rollback is unclear.
+- The evidence contains unsanitized identity, tenancy, group, or customer data.

package/skills/oci/oci-identity-access-governor/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-identity-access-governor/references/official-sources.md

@@ -0,0 +1,23 @@
+# 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/Identity/Concepts/overview.htm
+- https://docs.oracle.com/en-us/iaas/Content/Identity/Concepts/policies.htm
+- https://docs.oracle.com/en-us/iaas/Content/Identity/dynamicgroups/Working_with_Dynamic_Groups.htm
+- https://docs.oracle.com/en-us/iaas/Content/Identity/dynamicgroups/managingdynamicgroups.htm
+- https://docs.oracle.com/en-us/iaas/Content/Identity/Reference/policyreference.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-identity-access-governor/references/safety-checklist.md

@@ -1,32 +1,35 @@
-# Safety Checklist
+# Safety checklist
 
-Use this checklist before recommending or executing changes for `oci-identity-access-governor`.
+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, 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-identity-access-governor/references/workflow-and-output.md

@@ -0,0 +1,26 @@
+# Workflow and output contract
+
+Use this workflow for full reviews and incident-style triage.
+
+## 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.