chore(grok): CONTRIBUTING compliance — AGENTS.md, golden snapshots, VERSION/CHANGELOG

The original PR was hand-opened before reading CONTRIBUTING.md and missed
three CI-gating requirements:

- Register /grok in AGENTS.md (skill-validation doc-inventory cross-check).
- Refresh the three ship golden snapshots (claude/codex/factory) that the
  grok-review dashboard line in ship/SKILL.md regenerated — host-config
  golden-file regression tests.
- Bump VERSION to the next free queue slot (1.59.1.0, via gstack-next-version)
  and add a CHANGELOG entry, matching every merged gstack PR.

Verified: `bun run gen:skill-docs --host all` is clean across all hosts, and
`bun test` is green except 5 pre-existing gstack-gbrain-detect failures that
fail identically on origin/main (local gbrain tooling absent).

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>

Author: ljodea

AGENTS.md

@@ -29,6 +29,7 @@ Invoke them by name (e.g., `/office-hours`).
 |-------|-------------|
 | `/review` | Pre-landing PR review. Finds bugs that pass CI but break in prod. |
 | `/codex` | Second opinion via OpenAI Codex. Review, challenge, or consult modes. |
+| `/grok` | Second opinion via xAI Grok. Review, challenge, or consult modes. |
 | `/investigate` | Systematic root-cause debugging. No fixes without investigation. |
 | `/design-review` | Live-site visual audit + fix loop with atomic commits. |
 | `/design-shotgun` | Generate multiple AI design variants, comparison board, iterate. |

CHANGELOG.md

@@ -1,5 +1,27 @@
 # Changelog
 
+## [1.59.1.0] - 2026-06-16
+
+## **A second outside voice. `/grok` is the symmetric counterpart to `/codex` —**
+## **an independent review, challenge, or consult from xAI's Grok, same contract.**
+
+Cross-model independence was a single point of failure: every automatic outside-voice
+step routed through Codex, so when Codex was down or you wanted a genuinely different
+model, the chain fell back to a Claude subagent and lost the cross-model signal. `/grok`
+adds a second, independent voice with the exact `/codex` contract: **review** (diff-scoped,
+`[P1]`/`[P2]` findings, pass/fail gate), **challenge** (adversarial failure-mode hunt), and
+**consult** (open Q&A with session resume via `-r`/`-c`). It runs read-only through
+`gstack-grok-probe`, which handles auth (`~/.grok/auth.json` or `$XAI_API_KEY`), a timeout
+wrapper, and telemetry.
+
+The plan-review dashboard now distinguishes the two outside voices: the GSTACK REVIEW
+REPORT carries a `grok-review` row alongside `codex-review`, labels each as OpenAI vs xAI,
+and the CROSS-MODEL line fires when **two or more** outside-voice reviews exist instead of
+assuming Claude-plus-Codex. `/ship`'s dashboard reads the `grok-review` log the same way.
+
+Run `/grok review`, `/grok challenge security`, or `/grok Is this migration ordering safe?`
+after `./setup`. Requires `grok` on PATH and auth via `grok login` or `$XAI_API_KEY`.
+
 ## [1.58.4.0] - 2026-06-18
 
 ## **A community bug-fix wave plus a test-gate that finally sees the questions it was missing.**

VERSION

@@ -1 +1 @@
-1.58.4.0
+1.59.1.0

package.json

@@ -1,6 +1,6 @@
 {
   "name": "gstack",
-  "version": "1.58.4.0",
+  "version": "1.59.1.0",
   "description": "Garry's Stack — Claude Code skills + fast headless browser. One repo, one install, entire AI engineering workflow.",
   "license": "MIT",
   "type": "module",

test/fixtures/golden/claude-ship-SKILL.md

@@ -887,7 +887,7 @@ After completing the review, read the review log and config to display the dashb
 ~/.claude/skills/gstack/bin/gstack-review-read
 ```
 
-Parse the output. Find the most recent entry for each skill (plan-ceo-review, plan-eng-review, review, plan-design-review, design-review-lite, adversarial-review, codex-review, codex-plan-review). Ignore entries with timestamps older than 7 days. For the Eng Review row, show whichever is more recent between `review` (diff-scoped pre-landing review) and `plan-eng-review` (plan-stage architecture review). Append "(DIFF)" or "(PLAN)" to the status to distinguish. For the Adversarial row, show whichever is more recent between `adversarial-review` (new auto-scaled) and `codex-review` (legacy). For Design Review, show whichever is more recent between `plan-design-review` (full visual audit) and `design-review-lite` (code-level check). Append "(FULL)" or "(LITE)" to the status to distinguish. For the Outside Voice row, show the most recent `codex-plan-review` entry — this captures outside voices from both /plan-ceo-review and /plan-eng-review.
+Parse the output. Find the most recent entry for each skill (plan-ceo-review, plan-eng-review, review, plan-design-review, design-review-lite, adversarial-review, codex-review, grok-review, codex-plan-review). Ignore entries with timestamps older than 7 days. For the Eng Review row, show whichever is more recent between `review` (diff-scoped pre-landing review) and `plan-eng-review` (plan-stage architecture review). Append "(DIFF)" or "(PLAN)" to the status to distinguish. For the Adversarial row, show whichever is more recent between `adversarial-review` (new auto-scaled) and `codex-review` (legacy). For Design Review, show whichever is more recent between `plan-design-review` (full visual audit) and `design-review-lite` (code-level check). Append "(FULL)" or "(LITE)" to the status to distinguish. For the Outside Voice row, show the most recent `codex-plan-review` entry — this captures outside voices from both /plan-ceo-review and /plan-eng-review.
 
 **Source attribution:** If the most recent entry for a skill has a \`"via"\` field, append it to the status label in parentheses. Examples: `plan-eng-review` with `via:"autoplan"` shows as "CLEAR (PLAN via /autoplan)". `review` with `via:"ship"` shows as "CLEAR (DIFF via /ship)". Entries without a `via` field show as "CLEAR (PLAN)" or "CLEAR (DIFF)" as before.
 

test/fixtures/golden/codex-ship-SKILL.md

@@ -859,7 +859,7 @@ After completing the review, read the review log and config to display the dashb
 $GSTACK_ROOT/bin/gstack-review-read
 ```
 
-Parse the output. Find the most recent entry for each skill (plan-ceo-review, plan-eng-review, review, plan-design-review, design-review-lite, adversarial-review, codex-review, codex-plan-review). Ignore entries with timestamps older than 7 days. For the Eng Review row, show whichever is more recent between `review` (diff-scoped pre-landing review) and `plan-eng-review` (plan-stage architecture review). Append "(DIFF)" or "(PLAN)" to the status to distinguish. For the Adversarial row, show whichever is more recent between `adversarial-review` (new auto-scaled) and `codex-review` (legacy). For Design Review, show whichever is more recent between `plan-design-review` (full visual audit) and `design-review-lite` (code-level check). Append "(FULL)" or "(LITE)" to the status to distinguish. For the Outside Voice row, show the most recent `codex-plan-review` entry — this captures outside voices from both /plan-ceo-review and /plan-eng-review.
+Parse the output. Find the most recent entry for each skill (plan-ceo-review, plan-eng-review, review, plan-design-review, design-review-lite, adversarial-review, codex-review, grok-review, codex-plan-review). Ignore entries with timestamps older than 7 days. For the Eng Review row, show whichever is more recent between `review` (diff-scoped pre-landing review) and `plan-eng-review` (plan-stage architecture review). Append "(DIFF)" or "(PLAN)" to the status to distinguish. For the Adversarial row, show whichever is more recent between `adversarial-review` (new auto-scaled) and `codex-review` (legacy). For Design Review, show whichever is more recent between `plan-design-review` (full visual audit) and `design-review-lite` (code-level check). Append "(FULL)" or "(LITE)" to the status to distinguish. For the Outside Voice row, show the most recent `codex-plan-review` entry — this captures outside voices from both /plan-ceo-review and /plan-eng-review.
 
 **Source attribution:** If the most recent entry for a skill has a \`"via"\` field, append it to the status label in parentheses. Examples: `plan-eng-review` with `via:"autoplan"` shows as "CLEAR (PLAN via /autoplan)". `review` with `via:"ship"` shows as "CLEAR (DIFF via /ship)". Entries without a `via` field show as "CLEAR (PLAN)" or "CLEAR (DIFF)" as before.
 

test/fixtures/golden/factory-ship-SKILL.md

@@ -861,7 +861,7 @@ After completing the review, read the review log and config to display the dashb
 $GSTACK_ROOT/bin/gstack-review-read
 ```
 
-Parse the output. Find the most recent entry for each skill (plan-ceo-review, plan-eng-review, review, plan-design-review, design-review-lite, adversarial-review, codex-review, codex-plan-review). Ignore entries with timestamps older than 7 days. For the Eng Review row, show whichever is more recent between `review` (diff-scoped pre-landing review) and `plan-eng-review` (plan-stage architecture review). Append "(DIFF)" or "(PLAN)" to the status to distinguish. For the Adversarial row, show whichever is more recent between `adversarial-review` (new auto-scaled) and `codex-review` (legacy). For Design Review, show whichever is more recent between `plan-design-review` (full visual audit) and `design-review-lite` (code-level check). Append "(FULL)" or "(LITE)" to the status to distinguish. For the Outside Voice row, show the most recent `codex-plan-review` entry — this captures outside voices from both /plan-ceo-review and /plan-eng-review.
+Parse the output. Find the most recent entry for each skill (plan-ceo-review, plan-eng-review, review, plan-design-review, design-review-lite, adversarial-review, codex-review, grok-review, codex-plan-review). Ignore entries with timestamps older than 7 days. For the Eng Review row, show whichever is more recent between `review` (diff-scoped pre-landing review) and `plan-eng-review` (plan-stage architecture review). Append "(DIFF)" or "(PLAN)" to the status to distinguish. For the Adversarial row, show whichever is more recent between `adversarial-review` (new auto-scaled) and `codex-review` (legacy). For Design Review, show whichever is more recent between `plan-design-review` (full visual audit) and `design-review-lite` (code-level check). Append "(FULL)" or "(LITE)" to the status to distinguish. For the Outside Voice row, show the most recent `codex-plan-review` entry — this captures outside voices from both /plan-ceo-review and /plan-eng-review.
 
 **Source attribution:** If the most recent entry for a skill has a \`"via"\` field, append it to the status label in parentheses. Examples: `plan-eng-review` with `via:"autoplan"` shows as "CLEAR (PLAN via /autoplan)". `review` with `via:"ship"` shows as "CLEAR (DIFF via /ship)". Entries without a `via` field show as "CLEAR (PLAN)" or "CLEAR (DIFF)" as before.
 

test/skill-coverage-matrix.ts

@@ -150,6 +150,7 @@ export const SKILL_COVERAGE: Record<string, SkillCoverage> = {
   benchmark: { gate: ['test/skill-e2e-benchmark-providers.test.ts', 'test/skill-coverage-floor.test.ts'], periodic: [] },
   'benchmark-models': { gate: ['test/skill-coverage-floor.test.ts'], periodic: [] },
   codex: { gate: ['test/skill-coverage-floor.test.ts'], periodic: [] },
+  grok: { gate: ['test/grok-hardening.test.ts', 'test/skill-coverage-floor.test.ts'], periodic: [] },
   retro: {
     gate: ['test/skill-coverage-floor.test.ts'],
     periodic: ['test/regression-1624-retro-stale-base.test.ts'],