@probo/skills 0.3.0 → 0.3.2

package/.claude-plugin/plugin.json

@@ -1,6 +1,6 @@
 {
   "name": "probo",
-  "version": "0.3.0",
+  "version": "0.3.2",
   "description": "Open-source compliance workflows powered by Probo MCP (Claude Code, Codex, OpenCode)",
   "author": {
     "name": "Probo Inc",

package/.codex-plugin/plugin.json

@@ -1,6 +1,6 @@
 {
   "name": "probo",
-  "version": "0.3.0",
+  "version": "0.3.2",
   "description": "Open-source compliance workflows powered by Probo MCP (Codex, OpenCode, Claude Code)",
   "author": {
     "name": "Probo Inc",

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@probo/skills",
-  "version": "0.3.0",
+  "version": "0.3.2",
   "description": "Multi-agent compliance skills for open-source GRC (Claude Code, Codex, OpenCode) powered by Probo MCP",
   "private": false,
   "scripts": {
@@ -38,7 +38,7 @@
   ],
   "license": "MIT",
   "devDependencies": {
-    "js-yaml": "^4.3.1"
+    "js-yaml": "^5.4.1"
   },
   "repository": {
     "type": "git",

package/plugin.json

@@ -1,7 +1,7 @@
 {
   "$schema": "https://agent-plugins.org/schemas/1.0.0/plugin.schema.json",
   "name": "probo",
-  "version": "0.3.0",
+  "version": "0.3.2",
   "description": "Open-source compliance workflows powered by the Probo MCP API",
   "author": {
     "name": "Probo Inc",

package/skills/access-review/references/decision-rubric.md

@@ -11,7 +11,7 @@ for non-`APPROVED` decisions.
 | --- | --- | --- |
 | `TERMINATED_USER` flag | `REVOKE` | Terminated user — access no longer required |
 | `CONTRACTOR_EXPIRED` flag | `REVOKE` | Contractor engagement ended |
-| `active === false` and no `NEW` tag | `REVOKE` | Account inactive at source |
+| `active === false` | `REVOKE` | Account inactive at the source |
 | `ORPHANED` flag and `active === false` | `REVOKE` | Orphaned inactive account |
 | `ORPHANED` flag only, `active !== false` | `ESCALATE` | Orphaned account still active — needs owner |
 | `SHARED_ACCOUNT` flag | `ESCALATE` | Shared account — assign individual owner |
@@ -19,7 +19,7 @@ for non-`APPROVED` decisions.
 | `PRIVILEGED_ACCESS` or `ROLE_CREEP` flag | `ESCALATE` | Privileged access requires explicit approval |
 | `is_admin === true` and (`DORMANT` flag or last_login very stale) | `ESCALATE` | Admin access dormant — confirm business need |
 | `account_type === SERVICE_ACCOUNT`, active, no danger flags | `APPROVED` | Service account with expected access |
-| Active user, no flags (or only `NONE`), not admin, `incremental_tag !== NEW` | `APPROVED` | Routine access reaffirmed |
+| Active user, no flags (or only `NONE`), not admin | `APPROVED` | Routine access reaffirmed |
 
 "Very stale" last_login: no login in 90+ days when `last_login` is present.
 
@@ -27,7 +27,6 @@ for non-`APPROVED` decisions.
 
 | Condition | Suggested default | Why ambiguous |
 | --- | --- | --- |
-| `incremental_tag === NEW` | `ESCALATE` | New access since last campaign |
 | `NO_BUSINESS_JUSTIFICATION` flag | `ESCALATE` or `REVOKE` | Needs human judgment |
 | `OUT_OF_DEPARTMENT` flag | `ESCALATE` | Role/department mismatch |
 | `EXCESSIVE` or `ROLE_MISMATCH` flag | `ESCALATE` | Role change needs context |

package/skills/access-review/references/mcp-tools.md

@@ -40,7 +40,6 @@ List entries for a campaign. Primary data source for this command.
 | `campaign_id` | Campaign GID |
 | `filter.decision` | Use `PENDING` for review batches |
 | `filter.flag` | Optional — focus on a flag (e.g. `TERMINATED_USER`) |
-| `filter.incremental_tag` | Optional — `NEW`, `REMOVED`, `UNCHANGED` |
 | `filter.is_admin` | Optional boolean |
 | `filter.active` | Optional boolean |
 | `size` | Page size; use `50` per batch |
@@ -54,8 +53,8 @@ infer the tool from account IDs, roles, email patterns, or other entry data.
 
 Required: `campaign_id`
 
-Returns `statistics` with `total_count`, `decision_counts`, `flag_counts`,
-`incremental_tag_counts`. Call at the start of each run and after large batches.
+Returns `statistics` with `total_count`, `decision_counts`, `flag_counts`.
+Call at the start of each run and after large batches.
 
 ## Write (semi-auto command)
 
@@ -99,10 +98,9 @@ Do not call unless the user explicitly asks for campaign setup:
 | `is_admin` | Heightened scrutiny |
 | `active` | `false` often supports revoke |
 | `mfa_status` | `DISABLED` on privileged access → escalate |
-| `auth_method` | `API_KEY`, `SERVICE_ACCOUNT` context |
+| `auth_method` | `SSO`, `PASSWORD`, `API_KEY`, `OAUTH2`, `SSH`, `SERVICE_ACCOUNT` context |
 | `account_type` | `SERVICE_ACCOUNT` vs `USER` |
 | `last_login` | Dormancy signal |
-| `incremental_tag` | `NEW` needs extra scrutiny |
 | `flags`, `flag_reasons` | Primary risk signals |
 | `decision` | Target `PENDING` entries only |