kuker24 · kuker24 · Sep 15, 2026 · Sep 15, 2026
diff --git a/CHANGELOG.md b/CHANGELOG.md
@@ -2,8 +2,13 @@
 
 ## Unreleased
 
-Catalog hygiene patch. No new skills, no new MCP, no foreign harness runtime. Totals stay **62** (46 model-invoked, 16 manual slash commands).
+Catalog update for AI LABS 8-repo wave adaptation and hygiene patch. Totals become **63** (47 model-invoked, 16 manual slash commands).
 
+- Add first-party model-invoked specialist `img2threejs` for code-only procedural Three.js TypeScript model reconstruction from reference object images (editable Group factory, visible vs. inferred geometry spec, screenshot loop gate; no mesh blob downloads).
+- Add optional `reticle` MCP (`opencode-bf reticle enable` / `disable`) registering local perception server (`npx -y @reticlehq/server mcp`). `FOREIGN_ON_DEMAND`, server is FSL-1.1-ALv2, perception only, never an auto-implementer; default verification remains `playwright-qa` / `chrome-devtools-axi`.
+- Add optional `ui-skills` remote MCP (`opencode-bf ui-skills enable` / `disable`) registering `https://www.ui-skills.com/mcp` for design-skill lookup only. Product UI remains Design Bank + Impeccable + Design V2 atoms + shadcn; `BANK_MISS` never generates from random ui-skills documents.
+- Anti-slop selective merge: incorporate visual and copy anti-patterns (no default purple-gradient hero, glowing mesh, Inter-on-white-card slop, fake testimonials, or "Let's dive in" clichés) into `skills/impeccable/reference/taste-guard.md` and `rules/03-prose-discipline.md` with attribution to `miqdadbadjuber/anti-slop` MIT in `skills/install-anti-slop/NOTICE.md`. Zero extra catalog skills added.
+- Document warehouse dispositions for AI LABS 8 wave: `img2threejs` (NEW), `reticle` (FOREIGN_ON_DEMAND), `ui-skills` (FOREIGN_ON_DEMAND), `chisel` hooks (REJECT), `ouroboros`/Q00 (REJECT), `swiftui-skills` (DEFER), `caliper` (FOREIGN_ON_DEMAND maintainer CLI), and `anti-slop` (MERGE).
 - Sync stale user-facing catalog copy (`59` / `43 model-invoked`) to the measured tree in `README.md`, `docs/skills.md`, and `docs/architecture.md`. Historical release entries keep their original numbers.
 - `skill-stocktake`: replace the schema-only sweep with a verdict protocol. Every catalog item resolves to exactly one of `KEEP`, `COMPRESS`, `UPDATE`, `MERGE → <target>`, or `RETIRE`, backed by an existence pass, a currency pass, and cited evidence. The skill never rewrites or deletes another skill; `COMPRESS`/`UPDATE` hand off to `writing-for-agents` or `prompt-optimizer`.
 - `eval-harness`: add `references/skill-utility.md`, an A/B utility gate that scores a task with the skill (Run B) against the same task without it (Run A). Quality parity with lower token or latency passes; `A ≈ B` on the skill's own claimed task is evidence for `RETIRE` or `COMPRESS`. Deterministic assertions first, no external harness, no API key.

diff --git a/README.md b/README.md
@@ -1,14 +1,14 @@
 # OpenCodeBestFriend
 
 Production-ready capability layer for OpenCode:
-62 routed skills (core + Wave 2/3 warehouse specialists), MCP, Codebase Memory,
+63 routed skills (core + Wave 2/3 warehouse specialists), MCP, Codebase Memory,
 Design Bank, Design Intelligence, SmartDoc, browser and verification tooling.
 
 OpenCodeBestFriend is an installer and runtime overlay for [OpenCode](https://opencode.ai). It is **not** Claude Code, **not** a model provider, and **not** a dump of a developer home directory.
 
 ## What it is
 
-- 62 skills: 46 model-invoked, 16 manual slash commands
+- 63 skills: 47 model-invoked, 16 manual slash commands
 - A thin `AGENTS.md` router (lazy, one primary specialist)
 - Core MCP: Codebase Memory, Context7, shadcn
 - Design Bank discovery or download (media is **not** in git)
@@ -97,6 +97,7 @@ Default: repository evidence first. Then at most one specialist.
 | Photoreal / media | `visual-studio` |
 | Scroll-led storytelling | `scroll-craft` |
 | Scroll-driven 3D / camera world | `scroll-world` |
+| Procedural Three.js object from image | `img2threejs` |
 | Deterministic HTML composition video | `hyperframes` |
 | Documents (PDF/DOCX/answer/extract/review) | `smartdoc` |
 | Reusable book/module knowledge | `smartbook-ingest` |
@@ -125,10 +126,12 @@ Core (installed):
 Optional:
 
 - `serena` — host binary may exist; MCP is **not** registered unless you run `opencode-bf serena enable`
-- `exa` — `FOREIGN_ON_DEMAND`; installer never adds, removes, or overwrites it
 - `stitch` — `opencode-bf stitch enable` registers Google Stitch as a remote comp/mock source. Not an owned core server and not a production UI implementer: hand screens to `found-this-design` or `impeccable` before shipping. Keys are never written into config, only referenced as `{env:STITCH_API_KEY}`, or omitted with `--oauth`. `opencode-bf stitch disable` removes only that server key. Absent is not a `doctor` failure; a malformed entry fails closed.
+- `reticle` — `opencode-bf reticle enable` registers Reticle as a local perception server (`npx -y @reticlehq/server mcp`). `FOREIGN_ON_DEMAND`. Server package is FSL-1.1-ALv2 (competing-use clause); SDK packages (Apache-2.0) are not vendored. Never an auto-implementer; default verification remains `playwright-qa` / `chrome-devtools-axi`. `opencode-bf reticle disable` removes only that server key. Absent is not a `doctor` failure; a malformed entry fails closed.
+- `ui-skills` — `opencode-bf ui-skills enable` registers UI Skills (`https://www.ui-skills.com/mcp`) as an optional remote MCP server. `FOREIGN_ON_DEMAND` for design-skill lookup only. Product UI remains Design Bank + Impeccable + Design V2 atoms + shadcn; `BANK_MISS` never generates from a random ui-skills document. `opencode-bf ui-skills disable` removes only that server key. Absent is not a `doctor` failure; a malformed entry fails closed.
+- `exa` — `FOREIGN_ON_DEMAND`; installer never adds, removes, or overwrites it
 
-NVIDIA SkillEvaluator is `FOREIGN_ON_DEMAND` in the same sense: a maintainer may run it externally for embedding-based overlap scoring or live catalog evaluation. The installer never adds it, `doctor` does not fail when it is absent, and a malformed MCP entry for it fails closed like any other schema violation.
+NVIDIA SkillEvaluator is `FOREIGN_ON_DEMAND` in the same sense: a maintainer may run it externally for embedding-based overlap scoring or live catalog evaluation. Caliper is `FOREIGN_ON_DEMAND` similarly: a maintainer may `pipx install caliper-eval` off-tree for prompt/agent benchmark evaluation. Neither is vendored into `lib/`, the installer never adds them, `doctor` does not fail when they are absent, and a malformed MCP entry fails closed like any other schema violation.
 
 The installer merges only owned MCP keys. Provider, model, permissions, plugins, and foreign MCP stay yours.
 

diff --git a/docs/architecture.md b/docs/architecture.md
@@ -10,8 +10,8 @@
         ┌───────────────────┼────────────────────┐
         ▼                   ▼                    ▼
       Skills               MCP                 Rules
-     46 automatic       Codebase Memory        Verification
-     16 manual          Context7              Engineering
+      47 automatic       Codebase Memory        Verification
+      16 manual          Context7              Engineering
                        shadcn
         │
         ▼

diff --git a/docs/mcp.md b/docs/mcp.md
@@ -14,6 +14,8 @@ Optional:
 
 - `serena` — `opencode-bf serena enable` if the binary is on PATH
 - `stitch` — `opencode-bf stitch enable` (remote comp/mock source only; auth via `{env:STITCH_API_KEY}` or `--oauth`)
+- `reticle` — `opencode-bf reticle enable` (local stdio via `npx -y @reticlehq/server mcp`; perception only, never auto-implementer)
+- `ui-skills` — `opencode-bf ui-skills enable` (remote HTTP `https://www.ui-skills.com/mcp`; design-skill lookup only)
 - `exa` — foreign; never add/remove/overwrite
 
 Merge is parse-aware. Comment-free JSON is rewritten with `json.dumps`. JSONC with comments is patched surgically (owned MCP keys only). If surgical merge cannot be verified, install fails closed instead of destroying comments.
@@ -23,3 +25,7 @@ Doctor reports `CONFIGURED` for owned MCP entries present in config. That is not
 `opencode-bf serena enable` adds Serena only if absent. JSONC comments, provider keys, and foreign MCP are preserved via the same surgical merge as core MCP. Invalid config fails closed.
 
 `opencode-bf stitch enable` configures Google Stitch as an optional remote comp/mock server (`https://stitch.googleapis.com/mcp`). It is not an owned core server and not a UI implementer. Keys are never written directly to config, only referenced via `{env:STITCH_API_KEY}` or omitted when using `--oauth`. `opencode-bf stitch disable` surgically removes only the stitch server key.
+
+`opencode-bf reticle enable` configures Reticle as an optional local perception MCP server (`npx -y @reticlehq/server mcp`). It is `FOREIGN_ON_DEMAND`. The server package is FSL-1.1-ALv2 (competing-use clause); SDK packages (Apache-2.0) are not vendored. Reticle is never an auto-implementer; after a feature is done, default verification remains `playwright-qa` or `chrome-devtools-axi`. Reticle is extra perception if the user enabled it. `opencode-bf reticle disable` surgically removes only the reticle server key. Absent is not a doctor failure; a malformed entry fails closed.
+
+`opencode-bf ui-skills enable` configures UI Skills as an optional remote MCP server (`https://www.ui-skills.com/mcp`). It is `FOREIGN_ON_DEMAND` for design-skill lookup only (`list_skills`, `get_skill`). Product UI remains Design Bank + Impeccable + Design V2 atoms + shadcn; `BANK_MISS` never generates from a random ui-skills document. `opencode-bf ui-skills disable` surgically removes only the ui-skills server key. Absent is not a doctor failure; a malformed entry fails closed.
diff --git a/docs/routing.md b/docs/routing.md
@@ -22,7 +22,7 @@ MANUAL_NOT_INVOKED
 
 Never list unused tools as used.
 
-UI direction from the bank routes to `found-this-design` first, which stops before component implementation. Visual UI and UI atoms (buttons, inputs, cards, nav) route to `impeccable` after Design V2 shortlist; BANK_MISS ≠ generate (+ shadcn/Design V2 internal). Stitch MCP is for screen/comp generation only, then found-this-design or impeccable with Design V2 atom shortlisting; never implement production UI from Stitch alone. Motion UI routes to `emil-design-eng`. Still/ads/non-UI surface route to `visual-studio`. Scroll-led stories route to `scroll-craft`, while continuous camera 3D fly-throughs route to `scroll-world`.
+UI direction from the bank routes to `found-this-design` first, which stops before component implementation. Visual UI and UI atoms (buttons, inputs, cards, nav) route to `impeccable` after Design V2 shortlist; BANK_MISS ≠ generate (+ shadcn/Design V2 internal). Stitch MCP is for screen/comp generation only, then found-this-design or impeccable with Design V2 atom shortlisting; never implement production UI from Stitch alone. UI Skills MCP is design-skill lookup only; product UI remains Design Bank + Impeccable + Design V2 atoms + shadcn; BANK_MISS ≠ generate from a random ui-skills document. Motion UI routes to `emil-design-eng`. Still/ads/non-UI surface route to `visual-studio`. Scroll-led stories route to `scroll-craft`, while continuous camera 3D fly-throughs route to `scroll-world`. Procedural Three.js object models from reference images route to `img2threejs`.
 
 Browser verification follows four explicit doors: exploratory application UI routes to `playwright-qa`, persistent multi-account sessions route to `browser-act`, observed Chromium cause routes to `chrome-devtools-axi`, and button handler sequential undo / shared-store side effects route to `click-path-audit`.
 

diff --git a/docs/skills.md b/docs/skills.md
@@ -2,10 +2,10 @@
 
 Policy: `vendor/skill-policy.json` plus `vendor/skill-allowlist.txt`.
 
-- 46 model-invoked skills live under `skills/` and install to `~/.config/opencode/skills/` (core + Wave 2/3 warehouse specialists)
+- 47 model-invoked skills live under `skills/` and install to `~/.config/opencode/skills/` (core + Wave 2/3 warehouse specialists)
 - 16 manual skills live under `manual-skills/` and install to `~/.config/opencode/bestfriend/skills/` plus `commands/`
 
-`smartdoc` is per-job document intelligence. `smartbook-ingest` compiles reusable local knowledge. `humanizer` cleans user-facing prose tells (`/unslop` is its manual alias). `academic` manages scholarly research, writing, and peer review. `hyperframes` handles deterministic HTML-to-MP4 video composition. `diagram-design` crafts editorial HTML/SVG diagrams. Warehouse diagnostics include `agent-architecture-audit` (agent stack layers), `cost-aware-llm-pipeline` (token budgeting), `eval-harness` (benchmarks), `prompt-optimizer` (prompt refinement), and `skill-stocktake` (catalog hygiene). Wave 3 adds `api-design`, `contract-first`, `automation-audit-ops`, `code-tour`, and `click-path-audit`. Handwriting is a SmartDoc renderer, not a skill.
+`smartdoc` is per-job document intelligence. `smartbook-ingest` compiles reusable local knowledge. `humanizer` cleans user-facing prose tells (`/unslop` is its manual alias). `academic` manages scholarly research, writing, and peer review. `hyperframes` handles deterministic HTML-to-MP4 video composition. `diagram-design` crafts editorial HTML/SVG diagrams. `img2threejs` reconstructs procedural Three.js models from reference images. Warehouse diagnostics include `agent-architecture-audit` (agent stack layers), `cost-aware-llm-pipeline` (token budgeting), `eval-harness` (benchmarks), `prompt-optimizer` (prompt refinement), and `skill-stocktake` (catalog hygiene). Wave 3 adds `api-design`, `contract-first`, `automation-audit-ops`, `code-tour`, and `click-path-audit`. Handwriting is a SmartDoc renderer, not a skill.
 
 OpenCode 1.18.x has no `disable-model-invocation` field. Manual skills must not be copied into the discovered skills directory.
 

diff --git a/docs/warehouse-inventory.md b/docs/warehouse-inventory.md
@@ -350,3 +350,20 @@ This inventory establishes the contract for warehouse skills across the five ana
 | `affaan-m/ECC` | `windows-desktop-e2e` | **REJECT** | `-` | Language/framework pattern sprawl already covered by repo context + Context7 docs | `-` |
 | `affaan-m/ECC` | `workspace-surface-audit` | **DEFER** | `-` | Specialized domain procedure deferred for future warehouse wave evaluation | `-` |
 | `affaan-m/ECC` | `x-api` | **REJECT** | `-` | Third-party vendor operations and niche business workflows; reject proprietary automation | `-` |
+
+---
+
+## Wave AI LABS 8 Evaluation
+
+Evaluation and disposition contract for the AI LABS 8-repo wave (procedural 3D, perception, hooks, UI registries, harness runtimes, mobile platforms, eval benchmarks, anti-slop):
+
+| Candidate / Repo | Decision | BestFriend Target | Reason |
+| :--- | :---: | :--- | :--- |
+| `img2threejs` | **NEW** | `skills/img2threejs` | Procedural Three.js TypeScript Group reconstruction from reference object image; quality-gated, no downloaded mesh blobs. |
+| `reticle` | **FOREIGN_ON_DEMAND** | `mcp.reticle` | Optional visual perception MCP (`npx -y @reticlehq/server mcp`). Server licensed under FSL-1.1-ALv2; not vendored. Perception only, never auto-implementer. |
+| `chisel` (hooks) | **REJECT** | `-` | Session/prompt/tool hooks coupled to Claude Code runtime. Context Guard remains NOT_PORTED. |
+| `ui-skills` | **FOREIGN_ON_DEMAND** | `mcp.ui-skills` | Optional remote MCP (`https://www.ui-skills.com/mcp`) for design-skill lookup only. Product UI remains Design Bank + Impeccable + Design V2 + shadcn. |
+| `ouroboros` / Q00 | **REJECT** | `-` | Autonomous evolution harness / continuous-learning runtime rejected. Interview primitives already live in `grill-with-docs` / `ask-matt` / `to-spec`. |
+| `swiftui-skills` | **DEFER** | `-` | Apple platform / Xcode 26 ecosystem deferred. Target platform gate remains Linux x86_64 and OpenCode 1.18.x. |
+| `caliper` | **FOREIGN_ON_DEMAND** | `-` | Benchmark CLI runner (`caliper-eval`). Maintainer may run off-tree via pipx; zero `lib/` vendor coupling. |
+| `anti-slop` | **MERGE** | `install-anti-slop`, `impeccable`, `rules/03-prose-discipline.md` | Anti-pattern guardrails merged into existing taste, prose, and linting references; zero extra catalog skills. |
diff --git a/lib/cli.py b/lib/cli.py
@@ -24,9 +24,13 @@
     cmd_install,
     cmd_restore,
     cmd_restore_list,
+    cmd_reticle_disable,
+    cmd_reticle_enable,
     cmd_serena_enable,
     cmd_stitch_disable,
     cmd_stitch_enable,
+    cmd_ui_skills_disable,
+    cmd_ui_skills_enable,
     cmd_uninstall,
 )
 from lib.integrity import cmd_verify  # noqa: E402
@@ -104,6 +108,12 @@ def build_parser() -> argparse.ArgumentParser:
     st.add_argument("action", choices=["enable", "disable"])
     st.add_argument("--oauth", action="store_true", help="use OAuth/Bearer auth instead of STITCH_API_KEY header")
 
+    ret = sub.add_parser("reticle", help="optional Reticle local perception MCP")
+    ret.add_argument("action", choices=["enable", "disable"])
+
+    uis = sub.add_parser("ui-skills", help="optional UI Skills remote MCP")
+    uis.add_argument("action", choices=["enable", "disable"])
+
     sd = sub.add_parser("smartdoc", help="document profiles, extract, status")
     add_smartdoc_cli(sd)
     sb = sub.add_parser("smartbook", help="reusable SmartBook lifecycle")
@@ -163,6 +173,14 @@ def main(argv: list[str] | None = None) -> int:
         if args.action == "enable":
             return cmd_stitch_enable(oauth=args.oauth)
         return cmd_stitch_disable()
+    if cmd == "reticle":
+        if args.action == "enable":
+            return cmd_reticle_enable()
+        return cmd_reticle_disable()
+    if cmd == "ui-skills":
+        if args.action == "enable":
+            return cmd_ui_skills_enable()
+        return cmd_ui_skills_disable()
     if cmd == "smartdoc":
         return dispatch_smartdoc(args)
     if cmd == "smartbook":

diff --git a/lib/doctor.py b/lib/doctor.py
@@ -118,13 +118,14 @@ def mcp_status_map() -> dict[str, str]:
         try:
             data = jsonc.load_path(cfg)
         except (OSError, json.JSONDecodeError, ValueError):
-            return {k: "FAIL" for k in ("codebase-memory-mcp", "context7", "shadcn", "serena", "stitch", "exa")}
+            return {k: "FAIL" for k in ("codebase-memory-mcp", "context7", "shadcn", "serena", "stitch", "reticle", "ui-skills", "exa")}
     mcp = data.get("mcp") or {}
     owned = {"codebase-memory-mcp", "context7", "shadcn"}
-    for name in ("codebase-memory-mcp", "context7", "shadcn", "serena", "stitch", "exa"):
+    optional = {"serena", "stitch", "reticle", "ui-skills", "exa"}
+    for name in ("codebase-memory-mcp", "context7", "shadcn", "serena", "stitch", "reticle", "ui-skills", "exa"):
         spec = mcp.get(name)
         if spec is None:
-            out[name] = "OPTIONAL_ABSENT" if name in {"serena", "stitch", "exa"} else "FAIL"
+            out[name] = "OPTIONAL_ABSENT" if name in optional else "FAIL"
             continue
         if not isinstance(spec, dict):
             out[name] = "FAIL"
@@ -144,6 +145,26 @@ def mcp_status_map() -> dict[str, str]:
                 continue
             out[name] = "CONFIGURED"
             continue
+        if name == "reticle":
+            typ = spec.get("type")
+            cmd = spec.get("command")
+            if typ != "local" or not isinstance(cmd, list) or not cmd:
+                out[name] = "FAIL"
+                continue
+            out[name] = "CONFIGURED"
+            continue
+        if name == "ui-skills":
+            typ = spec.get("type")
+            url = spec.get("url")
+            if typ != "remote" or url != "https://www.ui-skills.com/mcp":
+                out[name] = "FAIL"
+                continue
+            headers = spec.get("headers")
+            if headers is not None and not isinstance(headers, dict):
+                out[name] = "FAIL"
+                continue
+            out[name] = "CONFIGURED"
+            continue
         if name not in owned:
             out[name] = "FOREIGN"
             continue