agy(gemini): RTFM audit — confirmed healthy, version + verified-date refresh

Audited the Gemini wrapper against the CLI's bundled help/README (gemini 0.45.2),
same pass as the grok skill. Unlike grok, found NO functional bug:
- All flags correct and real: -p, --skip-trust, -o json, --approval-mode plan|yolo,
  --include-directories, -m (verified against `gemini --help`).
- JSON schema {session_id, response, stats} -> .response confirmed via live probe.
- Pinned model gemini-3.1-pro-preview STILL VALID (live PONG); the GA-looking
  gemini-3.1-pro and gemini-3-pro both ModelNotFoundError -> keep the -preview suffix.
- Default text model is gemini-3.1-flash-lite (by design; verify/review/search/image
  pin pro). No thought-suppression flag exists in the CLI, so the gresponse() reasoning
  -leak scrub stays (justified, signature-gated, byte-exact otherwise).
- Live `search` re-validated end-to-end through the wrapper (58s, grounded sources).

Only change: version 0.45.1 -> 0.45.2 in SKILL.md + wrapper header, and refreshed the
verified-date notes with the 2026-06-17 re-validation findings.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>

.claude/skills/agy/SKILL.md

@@ -14,12 +14,14 @@ description: >
 # AGY — Gemini capability router
 
 Claude shells out to the locally-installed **Google Gemini CLI** (`gemini`, npm
-global, v0.45.1) for a genuinely independent, different-vendor second model.
+global, v0.45.2) for a genuinely independent, different-vendor second model.
 AGY is the sibling of [`grok`](../grok/SKILL.md): both are second-opinion /
 review routers. Use whichever you want a second model from (or both, to triangulate).
-Verified working on this machine (2026-06-05): text, verify, review (single
-file / file set / git diff), image-analyze (vision input), search (live Google
-web search). All KEYLESS — they work on Google OAuth, no API key.
+Verified working on this machine (2026-06-05; re-validated 2026-06-17 against the
+CLI's bundled help/README — JSON schema, all flags, pinned model, and live search
+all confirmed): text, verify, review (single file / file set / git diff),
+image-analyze (vision input), search (live Google web search). All KEYLESS — they
+work on Google OAuth, no API key.
 
 **Auth:** Gemini uses **Google login (OAuth)** — **no API key**. Creds live at
 `~/.gemini/oauth_creds.json`. If calls fail with an auth error, run `gemini`
@@ -63,7 +65,8 @@ never corrupts the parse.
 
 - `text` uses Gemini's **default routing** (currently a flash-tier model) — fast, cheap.
 - `verify` / `review*` pin a **strong** model — `gemini-3.1-pro-preview` (verified
-  available on this account 2026-06-05; the CLI's own pro tier).
+  available 2026-06-05, still valid 2026-06-17; the GA-looking `gemini-3.1-pro` and
+  `gemini-3-pro` both `ModelNotFoundError`, so keep the `-preview` suffix).
 - Override either with `GEMINI_MODEL=<id>` (e.g. `GEMINI_MODEL=gemini-2.5-pro`).
 - `image-analyze` and `search` also pin the strong model (`GEMINI_MODEL` still honored).
 
@@ -149,7 +152,7 @@ run both and compare — disagreement between them is a strong signal to slow do
 ## Reference
 - Binary: npm global `gemini` (`C:/Users/guru/AppData/Roaming/npm/gemini` on the
   host; the npm global dir is on PATH). The wrapper auto-locates it or honors `GEMINI=`.
-- Version 0.45.1. Auth: Google OAuth (`~/.gemini/oauth_creds.json`), no API key.
+- Version 0.45.2. Auth: Google OAuth (`~/.gemini/oauth_creds.json`), no API key.
 - Headless contract: `gemini -p "<prompt>" -o json --skip-trust </dev/null` →
   `{session_id, response, stats}`; answer is `.response`.
 - Sibling router: [`grok`](../grok/SKILL.md) (image/video/live-data + second opinion).

.claude/skills/agy/scripts/ask-gemini.sh

@@ -9,7 +9,7 @@
 # If a call fails with an auth error, run `gemini` interactively once and pick
 # "Login with Google".
 #
-# Output contract (VERIFIED on GURU-5070, gemini 0.45.1):
+# Output contract (VERIFIED on GURU-5070, gemini 0.45.2):
 #   - Prefer JSON: `gemini -p ... -o json` -> {session_id, response, stats}.
 #     The answer text is `.response`. stdout may carry two cosmetic warning lines
 #     ("True color..." / "Ripgrep is not available...") before the JSON; we extract