sync: auto-sync from GURU-5070 at 2026-06-03 11:52:45

Author: Mike Swanson
Machine: GURU-5070
Timestamp: 2026-06-03 11:52:45

.grok/HOOKS.md

@@ -0,0 +1,11 @@
+# .grok/HOOKS.md
+
+**Grok pointer.** See `.claude/HOOKS.md` for the full hooks protocol.
+
+Grok equivalents are in `.grok/hooks/claudetools.json` (SessionStart, UserPromptSubmit, PreToolUse) that call the shared .claude/scripts/ (check-messages, sync-memory, block-backslash) with env glue (GROK_WORKSPACE_ROOT, CLAUDE_PROJECT_DIR) and full exe paths for bash on Windows.
+
+See .grok/README.md hooks section, .grok/hooks/claudetools.json , and the .claude/hooks/ originals (unchanged).
+
+In Grok TUI: /hooks-trust , /hooks or Ctrl+L to load/inspect.
+
+This enables "each time we do a thing" coord checks for Grok too.

.grok/MCP_SERVERS.md

@@ -0,0 +1,13 @@
+# .grok/MCP_SERVERS.md
+
+**Grok pointer.** See `.claude/MCP_SERVERS.md` and the root MCP_SERVERS.md for historical setup.
+
+For Grok native: use .grok/config.toml (we added [mcp_servers.grepai] here for the semantic search / context tool) and ~/.grok/config.toml .
+
+Grok loads .mcp.json compat (lower prio) so Claude config works, but .grok/ is higher for Grok.
+
+See .grok/README.md MCP section, user-guide 07-mcp-servers.md , and the .grok/config.toml we created for grepai (without touching .mcp.json).
+
+Use `search_tool` / `use_tool` for all MCP including grepai__* .
+
+/mcps in TUI to manage.

.grok/OLLAMA.md

@@ -0,0 +1,13 @@
+# .grok/OLLAMA.md
+
+**Grok pointer.** The full Ollama / local AI / GrepAI config and routing (tier 0 prose/structured, embedding for GrepAI nomic-embed-text, identity.json per-machine, migrate script) is in `.claude/OLLAMA.md`.
+
+Grok uses the same (via identity, sync-memory, etc.).
+
+See the GrepAI section in .claude/OLLAMA.md for the config overrides applied to .grepai/config.yaml (boosts for session-logs/.claude/clients, remove .md penalty) and watcher scheduled task.
+
+In .grok/config.toml we added the native mcp_servers.grepai .
+
+For Grok TUI, local models via the same endpoints.
+
+See .grok/README.md memory section and .grok/skills/ for usage.

.grok/ONBOARDING.md

@@ -0,0 +1,11 @@
+# .grok/ONBOARDING.md
+
+**Grok pointer.** See `.claude/ONBOARDING.md` for the full onboarding.
+
+Grok uses the same identity.json , migrate-identity.sh , machines/ docs, etc.
+
+See .grok/README.md for the Grok-specific parts (hooks, skills, recovery, memory, MCP config).
+
+For new Grok machine: follow the Claude onboarding, then add the .grok/ pieces (or they are in the repo), run the ensure-git-bash, source profile, trust hooks/skills in TUI.
+
+The .grok/ was added for coexistence without breaking Claude.

.grok/README.md

@@ -96,14 +96,101 @@ To "tell Grok" in future: Describe the fact, and we (or you via /memory if on) w
 
 See also: `.claude/CLAUDE.md` (Automatic Context Loading, memory sections), Grok user-guide 12-project-rules.md and 13-memory.md, and the new windows-bash skill.
 
+## MCP Servers (GrepAI and others)
+
+Grok has first-class native MCP support (see `~/.grok/docs/user-guide/07-mcp-servers.md`).
+
+MCP servers (including the GrepAI semantic search server) are configured in:
+- Global: `~/.grok/config.toml` under `[mcp_servers.<name>]`
+- Project-scoped (this repo): `.grok/config.toml` (higher priority for Grok than global; only `[mcp_servers]` section is used here)
+
+Grok also loads for compatibility (lower priority):
+- `.mcp.json` (the vendor-neutral file used by Claude Code)
+- Claude/Cursor formats
+
+**For GrepAI specifically (semantic code + context searches):**
+
+We added `.grok/config.toml` (native Grok TOML) with the `grepai` server entry:
+
+```toml
+[mcp_servers.grepai]
+command = "D:\\claudetools\\grepai.exe"
+args = ["mcp-serve"]
+enabled = true
+```
+
+This is the **exact equivalent** of the entry in `.mcp.json`, but expressed in Grok's preferred native config format. It lives only in `.grok/` so Claude's `.mcp.json` (and its MCP loading) is untouched and continues to work exactly as before.
+
+**Using GrepAI for context searches in Grok:**
+
+- Tools are exposed as `grepai__grepai_search`, `grepai__grepai_trace_callers`, `grepai__grepai_trace_callees`, `grepai__grepai_index_status`, `grepai__grepai_stats`, etc.
+- Discovery + invocation: use the built-in `search_tool` (to list/find by keyword/desc) then `use_tool` with the fully-qualified name and exact schema params.
+- **MANDATORY per harness (CLAUDE.md + .claude/standards/context-lookup/grepai-first.md, which Grok loads):** For any context lookup, "what did we do with X", "how is Y configured", semantic search over code/session-logs/wiki/skills, or before `read_file` / `grep` / `list_dir` on source files — call `grepai__grepai_search` (or trace tools) **first**. Only fall back to direct file tools when you need the full verbatim content for editing.
+- CLI fallback (if MCP not handy): `D:/claudetools/grepai.exe search "query" --json -c -n 5`
+- The index covers the full repo + session logs with boosts for `.claude/`, `session-logs/`, `clients/`, etc. (see `.claude/OLLAMA.md` for the exact overrides applied on this machine).
+- In `/mcps` modal (or `Ctrl+L`) you can toggle, inspect status, see tools.
+
+This gives Grok the same (or better, native) access to GrepAI for context that Claude gets, with zero changes to Claude's working config.
+
+See also: `.grok/skills/context/SKILL.md` (updated to enforce), `.claude/standards/context-lookup/grepai-first.md`, the grepai watcher task, and `grepai.exe status`.
+
+## Automatic Context Loading for Grok (same ability as Claude)
+
+Grok has the **exact same automatic context loading** as Claude because:
+
+- Grok natively loads `CLAUDE.md` (and AGENTS.md etc.) as always-in project rules (deeper subdirs win).
+- We have mirrored/enforced the GrepAI-first rule everywhere (.grok/config.toml for native MCP, .grok/skills/context/SKILL.md with full trigger table + MSP example, .grok/README.md, all skills/agents, .grok/standards/README.md pointing to grepai-first standard).
+- .grok/ pointers for memory history (.grok/memory/README.md for .claude/memory/ feedback files), references, standards, etc.
+- Native GrepAI MCP (higher prio via .grok/config.toml) + CLI for semantic searches before any read_file/grep.
+- Context skill + deep-explore agent + backup agent for discovery.
+- Full delegation to shared wiki/clients/, projects/, systems/, session-logs/, CONTEXT.md, coord, B2 skill, etc.
+
+**When you say something like "Go ahead and remove that machine from MSP backups" (with implied glaztech + SBS):**
+
+Grok will (via the enhanced context skill + rules):
+
+1. Detect triggers: "mspbackups" (B2/MSP storage + RMM backup status), client "glaztech" (or machine name), "remove machine" (SBS).
+2. **GrepAI-first:** `search_tool` + `use_tool` (grepai__grepai_search "SBS glaztech mspbackups backup machine remove B2 key prefix") to find relevant chunks in code, logs, memory, wiki.
+3. Load wiki/clients/glaztech.md FIRST, then clients/glaztech/ (session-logs, backup docs, README, DEPLOYMENT etc.).
+4. Load mspbackups context: .grok/skills/b2/SKILL.md (Grok mirror of .claude/skills/b2/), RMM migrations for mspbackups_integration + multi_provider_backup, .claude/agents/backup.md , .claude/memory/ references to mspbackups/B2 rate, account structure (MSPBackups20200311 bucket etc.).
+5. Find the specific machine: Search for SBS in glaztech files, RMM agents, backup prefixes (e.g. in MSP360/CloudBerry destinations or glaztech bucket). Use GrepAI + RMM /rmm skill if needed.
+6. For the removal action: Use b2 skill (Grok version) to list buckets/keys/files for the machine's backup prefix/key, then gated delete-key / delete-prefix / delete-bucket --confirm (as per b2 safety). Update RMM backup status if applicable.
+7. Update context: Append to clients/glaztech/session-logs/ (new dated file or existing), update wiki/clients/glaztech.md if infrastructure changes, add feedback to .claude/memory/ if new lesson (or .grok/memory/), claim coord lock if significant, use /save or checkpoint.
+8. Never ask for info already in wiki/CONTEXT.md/logs/memory/coord.
+
+This is explicitly documented in the updated .grok/skills/context/SKILL.md (full trigger table + MSP example) and .grok/README.md.
+
+See CLAUDE.md "Automatic Context Loading (CRITICAL)" for the source table (Grok loads it). Use GrepAI MCP for "mspbackups" + client + machine in any such request.
+
+## Full Grok Equivalents / Mirroring (without touching originals)
+
+Following the GrepAI/MCP native config pattern, we have created thin .grok/ equivalents for *all other* commands, references, memory history, skills, agents, standards, docs, etc. that Claude Code uses. All additive in .grok/ tree; originals in .claude/ (and shared scripts/hooks/memory/wiki/etc.) untouched.
+
+### Commands
+- .grok/skills/<all 25+ from .claude/commands/>/SKILL.md (already present from initial coexistence setup + updates): thin adapters. Read .claude/commands/<name>.md + adapt tools (run_terminal_command etc.), obey CLAUDE.md + GrepAI-first.
+
+### Skills (the advanced .claude/skills/ ones)
+- Created .grok/skills/ thin SKILL.md for all that lacked them: b2, bitdefender, frontend-design, gc-audit, impeccable, memory-dream, packetdial, rmm-audit, skill-creator, stop-slop, theme-factory (self-check and remediation-tool already had mirrors).
+- Pattern: copy frontmatter, "Read the .claude/skills/<name>/SKILL.md (GrepAI MCP first), follow adapting for Grok tools (run_terminal_command with bash mapping, spawn_subagent, search_tool/use_tool for MCP/grepai, etc.)."
+
+### Agents (subagent personas)
+- Created .grok/agents/README.md + thin .md for key ones (deep-explore, coding, code-review, backup, gitea, database, documentation-squire, testing) + pointers for the rest (video-analysis, photo, dos-coding, code-fixer, the ST_ enhancements, quick ref, DB info).
+- "See .claude/agents/<name>.md ; adapt for Grok tools and GrepAI-first."
+
+### References, Memory History, Standards, Docs
+- Created .grok/ thin pointers: REFERENCE.md, RECOVERY.md, OLLAMA.md, MCP_SERVERS.md, HOOKS.md, ONBOARDING.md .
+- .grok/memory/README.md : points to .claude/memory/ (the "memory history" feedback_*.md , MEMORY.md etc. — use GrepAI for them, sync-memory bridges to Grok native ~/.grok/memory/).
+- .grok/standards/README.md : points to .claude/standards/ (including the critical context-lookup/grepai-first.md); use via inject-standards skill (which has .grok/ mirror) + GrepAI.
+- Machines/ and other fleet docs: referenced via identity + CLAUDE.md context loading + GrepAI; .claude/machines/ are the source.
+
+### Other
+- .grok/config.toml : native MCP (grepai and future) — higher prio for Grok than .mcp.json compat layer.
+- .grok/skills/self-check/SKILL.md : enhanced to call out .grok/ artifacts (config, agents, skills mirrors, pointer docs, memory) for Grok machine census/baseline.
+- All new/updated files mandate GrepAI MCP (search_tool + use_tool for grepai__*) + the full harness rules (CLAUDE.md, git-bash, vault, coord "each time", no emojis, additive only, etc.).
+- .grok/hooks/ already provided the hook equivalents.
+
+This gives Grok *native* first-class access to the entire harness (commands via /name skills, skills via auto / , agents via spawn_subagent with .grok/ personas, references/memory via GrepAI + pointers + CLAUDE.md loading, MCP via native config + /mcps) exactly parallel to Claude, but without any changes to Claude's files or behavior.
+
+See the individual files for details. Restart Grok TUI / reload skills/hooks after changes. Use /self-check to validate the new .grok/ pieces are seen on this machine.
+
 ## Future / polish
-
-- Make the hook JSON more robust across PATH/bash resolution (full exe path or a small finder launcher).
-- Full parity in recover_grok_session.py (chat turns, exact file edits via search_replace equivalents, Ollama prose).
-- Self-check updates to explicitly verify `.grok/hooks/` and `.grok/skills/` presence (or treat as capability).
-- Consider a small generator script or "grokify" command to keep the thin wrappers in sync if command docs change significantly.
-- Optional deeper `.grok/agents/` mirrors if you want Grok-specific subagent personas for the coding agents defined in `.claude/agents/`.
-
-All changes here are additive and keep the single source of truth in `.claude/`.
-
-See also: CLAUDE.md (the behavioral contract, loaded by both drivers), the self-check skill, and `.claude/HOOKS.md`.

.grok/RECOVERY.md

@@ -0,0 +1,13 @@
+# .grok/RECOVERY.md
+
+**Grok pointer / notes.** See `.claude/RECOVERY.md` for the full recovery protocol for crashed/unsaved sessions.
+
+Grok-specific: `.claude/scripts/recover_grok_session.py` (already in scripts/, used via .grok/skills/recover/SKILL.md).
+
+Use GrepAI for searching prior session logs during recovery.
+
+The .grok/ setup (hooks, skills, README) was built with recovery in mind for coexistence.
+
+See .grok/skills/recover/SKILL.md and the python script for Grok transcript parsing (from ~/.grok/sessions/...).
+
+Obey the same rules as Claude for session logs, /save etc.

.grok/REFERENCE.md

@@ -0,0 +1,11 @@
+# .grok/REFERENCE.md
+
+**Grok pointer.** The full reference for the ClaudeTools project (endpoints, workflows, etc.) is in `.claude/REFERENCE.md`.
+
+Grok loads CLAUDE.md (and related) as project rules, which incorporate the reference knowledge.
+
+Use GrepAI MCP for searching the reference content (it is indexed).
+
+See .claude/REFERENCE.md for the authoritative content. Do not duplicate here.
+
+For machine-specific: .claude/machines/<hostname>.md (Grok uses identity.json + these via context loading).

.grok/agents/README.md

@@ -0,0 +1,31 @@
+# .grok/agents/
+
+Grok equivalents / thin adapters for the subagent personas defined in `.claude/agents/`.
+
+**Pattern (same as .grok/skills/ for commands and .claude/skills/):** 
+- Thin files here that say "See the corresponding .claude/agents/<name>.md for the full persona definition and instructions."
+- Adapt for Grok: use `run_terminal_command`, `spawn_subagent`, `search_tool` + `use_tool` (esp. grepai__* for deep exploration), other Grok tools (image/video if relevant).
+- All agents must obey CLAUDE.md (Grok loads it), .grok/README.md, GrepAI-first rule before any direct file reads, and the coexistence rules.
+- Do not edit or duplicate the original .claude/agents/ files.
+
+This keeps single source of truth in .claude/ while giving Grok native discovery for subagents (via .grok/agents/ and project rules).
+
+See .claude/agents/AGENT_QUICK_REFERENCE.md and the individual .md for details.
+
+## Key Grok-adapted agents (full list mirrors .claude/agents/):
+- coding.md
+- deep-explore.md (heavy GrepAI/grepai MCP + trace callers/callees)
+- code-review.md
+- backup.md
+- gitea.md
+- database.md
+- documentation-squire.md
+- testing.md
+- photo.md , video-analysis.md
+- dos-coding.md
+- code-fixer.md
+- And the supporting: CODE_REVIEW_ST_*.md , DATABASE_CONNECTION_INFO.md , AGENT_QUICK_REFERENCE.md
+
+For subagent spawning in Grok, use the `spawn_subagent` tool with the persona from the .grok/ or .claude/ definition (deeper wins or as specified).
+
+See also: .grok/skills/ for the main /command skills, CLAUDE.md for when to use subagents.

.grok/agents/backup.md

@@ -0,0 +1,18 @@
+---
+name: backup
+description: Backup operations custodian.
+---
+
+**Grok agent equivalent.** See `.claude/agents/backup.md` (full custodian for all backups including MSP360/CloudBerry, B2 offsite, RMM agent_backup_status, database, etc.).
+
+For MSP backups removal (e.g. "remove SBS machine from mspbackups" for glaztech client):
+- Auto context load via GrepAI + wiki/clients/glaztech + clients/glaztech/backup docs + B2 skill + RMM mspbackups migrations + .claude/memory/ mspbackups refs.
+- Use .grok/skills/b2/SKILL.md (Grok mirror) to list buckets/keys for the machine's prefix (e.g. in MSPBackups* or ACG-GLAZTECH bucket), then gated delete-key/delete-prefix --confirm for the SBS backup destination.
+- Update RMM if backup status tracked per-agent.
+- Document: session log in client, update wiki if infra change, memory feedback if new lesson.
+- GrepAI-first before any reads; use run_terminal_command for b2.py (py + vault), spawn_subagent if complex.
+
+Grok tools (GrepAI MCP primary, b2 skill, terminal with git-bash, coord for locks) for all backup ops. See .grok/skills/b2/SKILL.md and context skill for MSP example.
+
+Use for all backup/restore with vault aware terminal, GrepAI for context in scripts/configs/memory/wiki.
+

.grok/agents/code-fixer.md

@@ -0,0 +1,8 @@
+---
+name: code-fixer
+description: Autonomous code quality agent that scans and fixes coding violations.
+---
+
+**Grok agent equivalent.** See `.claude/agents/code-fixer.md` and related CODE_REVIEW_ST_*.
+
+Use GrepAI, run tests/builds via terminal, search_replace for fixes, spawn_subagent. Follow review-fix-verify.

.grok/agents/code-review.md

@@ -0,0 +1,12 @@
+---
+name: code-review
+description: Code review agent. Mandatory after changes.
+---
+
+**Grok agent equivalent.** Full persona in `.claude/agents/code-review.md` (and supporting CODE_REVIEW_ST_*).
+
+For Grok: Use GrepAI MCP heavily for diffs/context, run_terminal_command for builds/tests, spawn_subagent, read_file after search.
+
+Enforce the review standards from source + CLAUDE.md + CODING_GUIDELINES.
+
+See .grok/agents/coding.md etc.

.grok/agents/coding.md

@@ -0,0 +1,12 @@
+---
+name: coding
+description: General-purpose coding agent.
+---
+
+**Grok agent equivalent.** See the full definition in `.claude/agents/coding.md`.
+
+Adapt for Grok tools: run_terminal_command (git-bash aware), search_replace/write/read (GrepAI MCP first for context), spawn_subagent, MCP use_tool for grepai etc.
+
+Follow the same coding standards, review-fix-verify loops, etc. from the source and CLAUDE.md / .claude/CODING_GUIDELINES.md (Grok loads the rules).
+
+See also: .grok/agents/code-review.md , code-fixer.md , deep-explore.md .

.grok/agents/database.md

@@ -0,0 +1,10 @@
+---
+name: database
+description: Database transaction authority and single source of truth for data operations.
+---
+
+**Grok agent equivalent.** See `.claude/agents/database.md` and DATABASE_CONNECTION_INFO.md .
+
+Use for DB queries etc. with run_terminal_command (vault for creds), GrepAI searches.
+
+See .claude/agents/DATABASE_CONNECTION_INFO.md .

.grok/agents/deep-explore.md

@@ -0,0 +1,14 @@
+---
+name: deep-explore
+description: Deep codebase exploration using grepai semantic search and call graph tracing. Use this agent for understanding code architecture, finding implementations by intent, analyzing function relationships, and exploring unfamiliar code areas.
+---
+
+**Grok agent equivalent.** See the full persona and instructions in `.claude/agents/deep-explore.md`.
+
+For Grok: Use `search_tool` + `use_tool` (grepai__grepai_search, grepai__grepai_trace_callers, grepai__grepai_trace_callees, grepai__grepai_trace_graph, etc.) as primary for semantic search and call graph (exactly as the source emphasizes "Use GrepAI first").
+
+Then use `read_file` only for full content when needed, `run_terminal_command`, `spawn_subagent`, etc.
+
+Obey CLAUDE.md, GrepAI-first (this agent is the embodiment of it), .grok/README.md .
+
+The core is deep exploration with GrepAI MCP + traces before traditional tools.

.grok/agents/documentation-squire.md

@@ -0,0 +1,10 @@
+---
+name: documentation-squire
+description: Documentation and task management specialist.
+---
+
+**Grok agent equivalent.** See `.claude/agents/documentation-squire.md`.
+
+Grok version for docs, session logs, wiki, memory updates. Use GrepAI, read/write, run for sync etc.
+
+See .grok/README.md for memory/docs coexistence.

.grok/agents/gitea.md

@@ -0,0 +1,10 @@
+---
+name: gitea
+description: Version control custodian for Git and Gitea operations.
+---
+
+**Grok agent equivalent.** See `.claude/agents/gitea.md`.
+
+For Grok: run_terminal_command with git (system ssh, not git's for windows issues), GrepAI for repo context.
+
+Follow git standards in .claude/standards/git/ .

.grok/agents/photo.md

@@ -0,0 +1,8 @@
+---
+name: photo
+description: Image analysis specialist for screenshots, photos, and visual documentation.
+---
+
+**Grok agent equivalent.** See `.claude/agents/photo.md`.
+
+For Grok: use image analysis tools if available, run_terminal_command, GrepAI for related code/docs. Adapt the persona.

.grok/agents/testing.md

@@ -0,0 +1,10 @@
+---
+name: testing
+description: Test execution specialist for running and validating tests.
+---
+
+**Grok agent equivalent.** See `.claude/agents/testing.md`.
+
+For Grok: run_terminal_command for test commands (pytest, cargo test, etc.), GrepAI for test code context, spawn_subagent.
+
+Follow .claude/standards/ for testing.

.grok/config.toml

@@ -0,0 +1,19 @@
+# Project-scoped Grok configuration for ClaudeTools
+# This is native Grok format (higher priority for Grok TUI than compatibility layers).
+# Claude continues to use .mcp.json exclusively (we do not touch it).
+# See .grok/README.md and ~/.grok/docs/user-guide/07-mcp-servers.md for details.
+
+[mcp_servers.grepai]
+# Native stdio MCP server for GrepAI semantic code search.
+# This makes grepai__* tools (grepai__grepai_search, trace_*, status, stats, etc.)
+# available to Grok via search_tool + use_tool, for context searches.
+# Matches the entry in .mcp.json so behavior is identical, but configured for Grok.
+command = "D:\\claudetools\\grepai.exe"
+args = ["mcp-serve"]
+enabled = true
+startup_timeout_sec = 15
+tool_timeout_sec = 120
+
+# You can add other project-specific MCP servers here for Grok only.
+# Global ones go in ~/.grok/config.toml .
+# Higher priority sources (this file) override lower ones (e.g. .mcp.json) on name conflicts.

.grok/machines/README.md

@@ -0,0 +1,9 @@
+# .grok/machines/
+
+**Grok pointer.** Fleet machine specs and onboarding are in `.claude/machines/` (per-host <hostname>.md + LINUX_PC_ONBOARDING.md).
+
+Grok uses the same via .claude/identity.json (machine, vault_path, etc.) + context loading in CLAUDE.md + GrepAI searches over the docs.
+
+See .claude/machines/ for details. Add Grok-specific notes here if needed per machine (e.g. Grok TUI + hooks trust steps), but keep source in .claude/.
+
+Current machine from identity: GURU-5070 (mike).

.grok/memory/README.md

@@ -0,0 +1,15 @@
+# .grok/memory/
+
+Grok native memory (if [memory] enabled in ~/.grok/config.toml or via flags) lives in ~/.grok/memory/ (global + per-workspace MEMORY.md + sessions/).
+
+**For the shared ClaudeTools memory history:** The authoritative "memory history" (feedback_*.md files, MEMORY.md, project references, all the lessons from past sessions) is in `.claude/memory/`.
+
+- It is git-tracked and synced across machines.
+- sync-memory.sh (called from .grok/hooks/ SessionStart and UserPromptSubmit) bridges repo memory to Grok's profile memory.
+- Use /memory , /flush , /dream in Grok TUI for native.
+- For harness memory: use GrepAI (grepai__grepai_search) over the .claude/memory/ files (they are indexed with boosts), read_file after search, edit with search_replace/write if needed (but coordinate via coord if multi-user).
+- The feedback files are "memory history" — search them with GrepAI for prior decisions (e.g. "windows bash mapping", "grok coexistence").
+
+See .claude/memory/MEMORY.md , .claude/scripts/sync-memory.sh , .grok/README.md "Making Grok Remember Things", and CLAUDE.md Automatic Context Loading / memory sections.
+
+Do not duplicate the feedback files here; the sync + GrepAI + CLAUDE.md loading make them available to Grok.

.grok/skills/b2/SKILL.md

@@ -0,0 +1,36 @@
+---
+name: b2
+description: >-
+  Manage Arizona Computer Guru's (ACG) Backblaze B2 storage account via the B2
+  Native API v3. Talks to the LIVE production B2 account (accountId 46f69bc61163,
+  region us-west-001) that holds the per-client MSP360/CloudBerry backup
+  destinations. List buckets and application keys, list files / file versions,
+  compute per-bucket stored size, and produce the headline storage-cost report
+  (the mspbackups storage-cost calc). Provision buckets and scoped backup keys
+  and delete buckets/keys (all destructive ops are gated behind --confirm).
+  Read-only by default. Invoke for: "backblaze", "b2", "b2 storage", "bucket",
+  "storage cost", "backup storage", "mspbackups storage", "list buckets b2".
+---
+
+**Grok skill.** This maps to the shared skill in `.claude/skills/b2/SKILL.md`.
+
+Read `.claude/skills/b2/SKILL.md` (first use GrepAI via `search_tool` + `use_tool` (grepai__grepai_search etc.) for semantic context lookup per the GrepAI-first rule in CLAUDE.md, .grok/README.md, and .grok/skills/context/SKILL.md; only fall back to `read_file` if full verbatim content is needed for editing/review) and follow it exactly, adapting for Grok's tools:
+
+- Use `run_terminal_command` (with Git Bash mapping via .grok/skills/windows-bash/SKILL.md or full "C:\\Program Files\\Git\\bin\\bash.exe" + PATH export as per harness and .grok/hooks/) to run the Python CLI in `.claude/skills/b2/scripts/b2.py` (use `py` per identity.json, with CLAUDETOOLS_ROOT or derived from identity).
+- Use `spawn_subagent` for any delegation.
+- For searches/context: always prefer `search_tool` + `use_tool` for MCP tools (grepai__* primary for code/wiki/session logs).
+- Destructive subcommands remain gated behind `--confirm` exactly as in the source.
+- Obey CLAUDE.md (Grok loads it as always-in project rules), .grok/README.md, use GrepAI-first before any direct file tools.
+
+The full details — running the CLI, credentials (always via vault.sh or 1password skill, never hardcoded), cache model, safety gating, common commands (status, buckets, files, usage/cost, create/delete with --confirm), prefix purge/lifecycle mechanism, storage cost calc ($0.00695/GB decimal, mspbackups), account structure (12 buckets, keys), and references — are in the source `.claude/skills/b2/SKILL.md` (and its scripts/ and references/).
+
+Invoke via the documented commands (e.g. py .../b2.py status, $B2 usage --json, gated deletes/purges), using the Grok terminal tool. The skill talks to the live B2 account — treat writes conservatively.
+
+**For MSP backups machine removal (e.g. "remove SBS from mspbackups" for glaztech):**
+- First, context load via GrepAI + .grok/skills/context/SKILL.md (wiki/clients/glaztech.md, clients/glaztech/, RMM mspbackups, .claude/memory/ mspbackups refs, account structure in source).
+- List buckets/keys/files for the machine (often per-client MSP360 prefix like MBS-<guid>/CBB_SBS/ or in MSPBackups20200311 / ACG-GLAZTECH).
+- Use gated delete-key (for the machine's backup key), delete-prefix (for the SBS/ machine prefix to schedule lifecycle purge), or delete-bucket if decommissioning the whole destination --confirm.
+- Follow prefix purge/lifecycle exactly (dry-run without --confirm, commit with, wait ~24-48h for B2 lifecycle, verify with bucket-size, cleanup rule with lifecycle-remove).
+- Update client docs, session log, memory as needed after.
+
+See also: .grok/skills/1password/SKILL.md for secrets if needed, the mspbackups context in memory/wiki, .grok/agents/backup.md , .grok/skills/context/SKILL.md (has explicit MSP + glaztech + SBS example).

.grok/skills/bitdefender/SKILL.md

@@ -0,0 +1,31 @@
+---
+name: bitdefender
+description: >-
+  Manage the Arizona Computer Guru (ACG) Bitdefender GravityZone Cloud MSP
+  tenant via the Public JSON-RPC API. Inventory and audit endpoints, run live
+  security sweeps (infected / outdated-signature / outdated-product), list
+  client companies, build and fetch installation packages, manage custom groups,
+  start scans, move/delete endpoints (gated), inspect policies (read-only,
+  shallow), and review quarantine. Invoke for: "bitdefender", "gravityzone",
+  "gravity zone", "add machine to bitdefender", "install bitdefender on",
+  "list endpoints", "infected machines", "av coverage", "security sweep",
+  "endpoint protection", "policy assignment", "quarantine". This skill talks to
+  the real production ACG GravityZone partner tenant — treat destructive actions
+  conservatively.
+---
+
+**Grok skill.** This maps to the shared skill in `.claude/skills/bitdefender/SKILL.md`.
+
+Read `.claude/skills/bitdefender/SKILL.md` (first use GrepAI via `search_tool` + `use_tool` (grepai__grepai_search etc.) for semantic context lookup per the GrepAI-first rule in CLAUDE.md, .grok/README.md, and .grok/skills/context/SKILL.md; only `read_file` if full content needed for editing or review) and follow it, adapting for Grok tools:
+
+- Use `run_terminal_command` (Git Bash aware per .grok/skills/windows-bash, full exe paths for reliability) to invoke the py CLI in `.claude/skills/bitdefender/scripts/gz.py` (py launcher from identity, paths via CLAUDETOOLS_ROOT or identity).
+- Use `spawn_subagent` for delegation.
+- Prefer MCP `search_tool`/`use_tool` (grepai for searches) before direct file tools.
+- Destructive ops gated with --confirm exactly as specified.
+- Obey CLAUDE.md (loaded by Grok), .grok/README.md, GrepAI-first before reads.
+
+The implementation — CLI usage, vault credentials (never hardcoded), cache model, policy limitations, safety gating, common commands (status, companies, sweep, policies, quarantine, packages, groups, scans, blocklist, isolate, raw, destructive), phase-2 hooks, and references — are in the source `.claude/skills/bitdefender/SKILL.md` and its scripts/references/.
+
+Invoke as documented (e.g. py .../gz.py status, $GZ sweep --company <id> --json, gated deletes/isolates). This skill talks to the live production tenant — treat destructive conservatively.
+
+See also: .grok/skills/rmm/SKILL.md for RMM integration ideas.

.grok/skills/context/SKILL.md

@@ -8,20 +8,38 @@ description: >
 
 **Grok skill:** This maps to the shared command in `.claude/commands/context.md`.
 
-Per the harness (and CLAUDE.md "Automatic Context Loading" and "Context Recovery" sections):
+Per the harness (and CLAUDE.md "Automatic Context Loading" and "Context Recovery" sections), Grok MUST automatically load context using this trigger table **before** any response or action when keywords match. This gives Grok the same "automatically know the context" ability as Claude for requests like "Go ahead and remove that machine from MSP backups" (detect "mspbackups" + client "glaztech" + machine "SBS", then load wiki/clients/glaztech.md + clients/glaztech/ + B2/mspbackups context + RMM backup status + relevant session logs + memory + use b2 skill for removal).
 
-- ALWAYS check wiki/ first (clients/, projects/, systems/, patterns/).
-- Then session-logs/ (root, projects/*, clients/*).
-- credentials.md (or vault).
-- Coord API status, locks, messages, components.
-- Project CONTEXT.md files.
+**Automatic Context Loading Trigger Table (Grok equivalent, using GrepAI MCP + tools):**
+
+| Trigger | Action (Grok implementation) |
+|---------|------------------------------|
+| Client name mentioned (e.g. glaztech, cascades) | Use `search_tool` + `use_tool` (grepai__grepai_search "glaztech client wiki mspbackups") FIRST, then read `wiki/clients/<slug>.md` (GrepAI first), then `clients/<name>/session-logs/` for recent detail. Load client backup docs. |
+| "mspbackups", MSP backups, backup storage, B2, MSP360 | Use GrepAI MCP for "mspbackups B2 bucket glaztech SBS remove" , then .grok/skills/b2/SKILL.md (Grok mirror), RMM migrations for mspbackups_integration, .claude/agents/backup.md , client backup.md files. Find machine prefix/key and use b2 delete-*-with-confirm. |
+| GuruRMM / Dataforth / project keywords (e.g. gururmm, msp-tools) | Use GrepAI first, read `wiki/projects/<slug>.md` FIRST, then `projects/<project>/CONTEXT.md`, query coord API status + components via run_terminal_command curl. |
+| Server/hostname/IP mentioned (e.g. SBS, glaztech machine) | Use GrepAI "SBS glaztech server hostname", read `wiki/systems/<slug>.md` FIRST for synthesized knowledge, then RMM agents, client servers/. |
+| "continue", "resume", "back to", "finish", "remove that machine" | Use GrepAI for context, read project wiki article + CONTEXT.md, check coord API for locks + unread messages (display any UNREAD COORD MESSAGES verbatim first). |
+| Servers, IPs, credentials, deploy questions, "MSP backups" | Check wiki/systems or clients first (GrepAI), then CONTEXT.md / .grok/memory/README.md — answer from it, never ask. Use vault via .grok/skills/1password or scripts. |
+| Uncertainty >5% about infra or recent work, or high-level request like remove from backups | ALWAYS: GrepAI search first (e.g. query="mspbackups glaztech SBS remove machine B2 key"), then wiki first, then CONTEXT.md / session-logs / .claude/memory/ before asking the user. Use context skill + deep-explore agent if complex. |
+
+**Grok Context Loading Workflow (MANDATORY in this skill and all context-heavy tasks):**
+- **GrepAI-first (critical, via our .grok/config.toml native MCP + .grok/skills/ enforcement):** Call `search_tool` to discover `grepai__grepai_search` etc., then `use_tool` with natural language query for the request (e.g. "remove SBS machine from mspbackups glaztech B2"). This finds relevant code, logs, memory, wiki chunks semantically. Only then read full files if needed.
+- Use .grok/ pointers: .grok/memory/README.md for history, .grok/standards/README.md (g repai-first), .grok/REFERENCE.md , .grok/agents/backup.md .
+- ALWAYS check wiki/ first (use GrepAI "wiki/clients/glaztech" or direct after search), clients/<name>/ , projects/ , .claude/memory/ feedback files for mspbackups lessons.
+- Then session-logs/ (GrepAI or grep for keywords like "SBS", "mspbackups", "backup key").
+- credentials via vault (1password skill or .claude/scripts/vault.sh via terminal, never hardcode).
+- Coord API for live state (locks, todos, components for the project/client).
+- Project CONTEXT.md and .grok/agents/ for synthesized knowledge.
+- For MSP backups removal specifically: Load glaztech client full context, search B2 account structure for the machine's prefix/key in MSPBackups* or ACG-GLAZTECH bucket, use b2 skill's delete-key / delete-prefix --confirm (gated), update docs (session log in clients/glaztech/session-logs/, wiki if needed, memory feedback if new lesson), claim coord lock if multi-step, publish to coord if applicable. Use RMM if the machine status needs update in backup_provider_registry or agent_backup_status.
+- Never ask the user for info already in these sources.
 
 When this skill runs:
-- Read `.claude/commands/context.md` for the exact protocol.
-- Use tools: `read_file` for wiki and log files (GrepAI via MCP or the dedicated grep tool is excellent for semantic search across session logs).
-- Query coord via `run_terminal_command` with curl to http://172.16.3.30:8001/api/coord/...
-- Never ask the user for info that is already in these sources.
+- Read `.claude/commands/context.md` for the exact protocol (GrepAI first before read).
+- **GrepAI MCP first** for all lookups as detailed above (example query in prompt: "SBS glaztech mspbackups backup machine").
+- Query coord via `run_terminal_command` with curl...
+- For actual work (e.g. the removal), delegate to appropriate Grok skill like b2, and use .grok/agents/backup.md or spawn_subagent with deep-explore/coding if code changes needed.
+- Log the work with /save or session log append in the correct clients/ or projects/ location per FILE_PLACEMENT_GUIDE (GrepAI for placement rules first).
 
-This is one of the most important commands for maintaining continuity across sessions and machines. The CLAUDE.md has a detailed trigger table.
+This is one of the most important for Grok to have the same automatic context ability as Claude for MSP/client/infra tasks. The CLAUDE.md trigger table + GrepAI + .grok/ mirrors give Grok native power here.
 
-See the source command for the full checklist and "Never ask for info in:" rules.
+See the source command for full checklist and "Never ask for info in:" rules. Update .claude/memory/ or .grok/memory/ with new lessons from the task.

.grok/skills/frontend-design/SKILL.md

@@ -0,0 +1,19 @@
+---
+name: frontend-design
+description: Create distinctive, production-grade frontend interfaces with high design quality. MANDATORY AUTOMATIC INVOCATION: Use this skill whenever ANY action affects a UI element to validate visual correctness, functionality, and user experience. Also use when the user asks to build web components, pages, artifacts, posters, or applications (examples include websites, landing pages, dashboards, React components, HTML/CSS layouts, or when styling/beautifying any web UI). Generates creative, polished code and UI design that avoids generic AI aesthetics.
+---
+
+**Grok skill.** This maps to the shared skill in `.claude/skills/frontend-design/SKILL.md`.
+
+Read `.claude/skills/frontend-design/SKILL.md` (use GrepAI MCP `search_tool` + `use_tool` (grepai__*) first for any context/semantic lookup per GrepAI-first rule in CLAUDE.md / .grok/README.md / .grok/skills/context/SKILL.md; `read_file` only for full content when editing) and follow it, adapting for Grok:
+
+- Use `run_terminal_command`, `write`, `search_replace`, `read_file` (GrepAI first), image_gen/image_edit if visual, etc.
+- Use `spawn_subagent` for complex UI tasks.
+- MCP tools via search/use_tool (grepai for code searches).
+- Obey CLAUDE.md, .grok/README.md, GrepAI-first before direct reads.
+
+The full guidelines for distinctive non-slop UI, visual hierarchy, accessibility, performance, theming, anti-patterns, and the design process are in the source `.claude/skills/frontend-design/SKILL.md` (and its sub files if any).
+
+Auto-invoke for any UI change. Use the impeccable skill too if available for polish.
+
+See also: .grok/skills/impeccable/SKILL.md (if created), .claude/skills/stop-slop/SKILL.md .

.grok/skills/gc-audit/SKILL.md

@@ -0,0 +1,14 @@
+---
+name: gc-audit
+description: Periodic end-to-end verification of the GuruConnect codebase and CI/CD infrastructure. Runs 6 parallel audit passes: (1) API/route & surface inventory, (2) Rust code quality & standards, (3) TypeScript/dashboard quality, (4) protocol & wire-format integrity (proto <-> prost <-> manual TS decode), (5) security & remote-session integrity, (6) docs/roadmap reconciliation. A 7th sequential pass audits CI/CD pipeline health (Gitea Actions workflows, runner registration, clippy/audit gates, deploy host). Produces a timestamped audit report and updates the living docs (FEATURE_ROADMAP.md, TECHNICAL_DEBT.md). Takes 10-20 minutes. Invoke explicitly only — no auto-trigger. Use /gc-audit for a full audit. Optional arg: --pass=<name> to run a single pass (api, rust, ts, protocol, security, docs, pipeline). The docs pass reconciles FEATURE_ROADMAP.md, TECHNICAL_DEBT.md, the docs/specs/SPEC-*.md, and the specs/*/plan.md task markers against the code; quality passes check code against the granular .claude/standards/ files.
+---
+
+**Grok skill.** This maps to the shared skill in `.claude/skills/gc-audit/SKILL.md`.
+
+Read `.claude/skills/gc-audit/SKILL.md` (use GrepAI via `search_tool` + `use_tool` (grepai__grepai_search) first for context per GrepAI-first rule in CLAUDE.md, .grok/README.md and .grok/skills/context/SKILL.md; `read_file` only when full content needed) and follow it, adapting for Grok tools (run_terminal_command for the audit script, spawn_subagent for parallel passes if useful, MCP search/use_tool for grepai during code audits).
+
+The full audit process, passes, reporting, and updates to living docs are in the source `.claude/skills/gc-audit/SKILL.md`.
+
+Invoke explicitly with /gc-audit or the skill. Use --pass for single passes. This is for GuruConnect.
+
+See also: .grok/skills/rmm-audit/SKILL.md for the RMM counterpart.

.grok/skills/impeccable/SKILL.md

@@ -0,0 +1,14 @@
+---
+name: impeccable
+description: Use when the user wants to design, redesign, shape, critique, audit, polish, clarify, distill, harden, optimize, adapt, animate, colorize, extract, or otherwise improve a frontend interface. Covers websites, landing pages, dashboards, product UI, app shells, components, forms, settings, onboarding, and empty states. Handles UX review, visual hierarchy, information architecture, cognitive load, accessibility, performance, responsive behavior, theming, anti-patterns, typography, fonts, spacing, layout, alignment, color, motion, micro-interactions, UX copy, error states, edge cases, i18n, and reusable design systems or tokens. Also use for bland designs that need to become bolder or more delightful, loud designs that should become quieter, live browser iteration on UI elements, or ambitious visual effects that should feel technically extraordinary. Not for backend-only or non-UI tasks.
+---
+
+**Grok skill.** This maps to the shared skill in `.claude/skills/impeccable/SKILL.md`.
+
+Read `.claude/skills/impeccable/SKILL.md` (GrepAI-first with `search_tool`/`use_tool` (grepai__*) before any `read_file` per the rule; full read only for review/edit) and follow it, adapting for Grok (use run_terminal_command, write/search_replace for code, image_gen/edit for visuals, spawn_subagent, MCP tools).
+
+The full impeccable toolkit for high-quality frontend work is in the source `.claude/skills/impeccable/SKILL.md` (and its many sub files).
+
+MANDATORY for any UI-affecting work. Combine with frontend-design and stop-slop.
+
+See also: .grok/skills/frontend-design/SKILL.md , .grok/skills/theme-factory/SKILL.md .

.grok/skills/memory-dream/SKILL.md

@@ -0,0 +1,14 @@
+---
+name: memory-dream
+description: Memory lint + consolidation analyzer for the ClaudeTools REPO memory store (.claude/memory/). Audits the index, backlinks, referenced file paths, duplicate/overlap clusters, stale dated facts, and drift against the machine-local harness profile memory store. Default run is read-only. --apply-safe performs the low-risk fixes (append missing index lines, copy any profile-only files into the repo for indexing). Cluster merges, dedup deletes, and stale-fact removal are surfaced as PROPOSED actions for a human to apply -- they're judgment calls, not automation candidates. (Repo is the source of truth as of 2026-06-02; sync-memory.sh mirrors repo to profile, so PROFILE-side cleanup is handled by that script, not here. See feedback_memory_sync_destructive_ok.md.) Invoke for: "memory dream", "consolidate memory", "memory lint", "clean up memory", "memory errors", "dedupe memory".
+---
+
+**Grok skill.** This maps to the shared skill in `.claude/skills/memory-dream/SKILL.md`.
+
+Read `.claude/skills/memory-dream/SKILL.md` (GrepAI-first via MCP tools before read_file per rules) and follow it, adapting for Grok tools (run_terminal_command for the script, MCP grepai for searching memory files since they are indexed).
+
+The memory lint/consolidation for .claude/memory/ (and bridging to Grok native memory) is in the source.
+
+Use to clean/audit the shared memory history. See .grok/README.md for Grok memory layers.
+
+See also: .claude/scripts/sync-memory.sh , .grok/skills/context/SKILL.md .

.grok/skills/packetdial/SKILL.md

@@ -0,0 +1,14 @@
+---
+name: packetdial
+description: Manage the Arizona Computer Guru (ACG) PacketDial / OITVOIP hosted-VoIP platform via the NetSapiens SNAPsolution API v2 (pbx.packetdial.com, v44.4). List and inspect domains, users, devices/phones, DIDs (phone numbers), resellers, and pull CDRs (call detail records). Provision new customer domains, users, SIP devices, and phone numbers (all writes gated behind --confirm). Read-only by default. Invoke for: "packetdial", "oitvoip", "oit voip", "netsapiens", "voip portal", "pbx portal", "voip domain", "voip user", "voip extension", "provision phone", "add did", "phone number on voip", "call detail records", "cdr", "voip.packetdial", "pbx.packetdial". NOTE: voip.packetdial.com is the customer-facing portal (the fax/UC dashboard, e.g. Cascades account 28598) and has no API — the programmable surface is pbx.packetdial.com. This skill talks to the LIVE production reseller PBX; treat writes conservatively.
+---
+
+**Grok skill.** This maps to the shared skill in `.claude/skills/packetdial/SKILL.md`.
+
+Read the source (GrepAI-first with MCP before read_file) and follow, adapting for Grok (run_terminal_command for the voip scripts, vault for creds, MCP tools).
+
+The VoIP management (domains, users, DIDs, CDRs, provisioning gated by --confirm) is in `.claude/skills/packetdial/SKILL.md` and scripts/.
+
+Read-only by default; writes gated. Talks to live pbx.packetdial.com reseller API.
+
+See also: .grok/skills/1password or vault for creds.

.grok/skills/rmm-audit/SKILL.md

@@ -0,0 +1,14 @@
+---
+name: rmm-audit
+description: Periodic end-to-end verification of the GuruRMM codebase and build infrastructure. Runs 5 parallel audit passes: (1) API/route inventory cross-reference, (2) UI coverage and gap update, (3) Rust code quality and standards compliance, (4) TypeScript/frontend quality, (5) security and data integrity. A 6th sequential pass audits build pipeline health (logs, artifacts, change gates, script integrity). Produces a timestamped audit report and updates the living docs (UI_GAPS.md, FEATURE_ROADMAP.md). Takes 10-20 minutes. Invoke explicitly only — no auto-trigger. Use /rmm-audit for a full audit. Optional arg: --pass=<name> to run a single pass (api, ui, rust, ts, security, pipeline, roadmap). The roadmap pass reconciles FEATURE_ROADMAP.md checkboxes against the code and cleans up stale ones.
+---
+
+**Grok skill.** This maps to the shared skill in `.claude/skills/rmm-audit/SKILL.md`.
+
+Read the source (GrepAI MCP first for context, then read_file if needed) and follow, using Grok tools (run_terminal_command for audit runner, spawn_subagent for passes, grepai MCP heavily for code quality/trace during audits).
+
+The RMM audit process, passes, UI_GAPS updates, etc. are in `.claude/skills/rmm-audit/SKILL.md`.
+
+Explicit only. Complements gc-audit for GuruConnect.
+
+See also: .grok/skills/rmm/SKILL.md , .grok/skills/gc-audit/SKILL.md .

.grok/skills/self-check/SKILL.md

@@ -19,8 +19,12 @@ Recommended:
    `SELFCHECK_TS="$(date -u +%Y-%m-%dT%H:%M:%SZ)" bash .claude/skills/self-check/scripts/self-check.sh report`
    (or --json, --publish, etc.)
 
-The self-check is driver-agnostic — it validates the files, scripts, hooks wiring, identity, tools, and the .claude/ + .grok/ harness pieces (including the new Grok hooks and skills we added for coexistence).
+The self-check is driver-agnostic — it validates the files, scripts, hooks wiring, identity, tools, and the .claude/ + .grok/ harness pieces (including the new Grok hooks and skills we added for coexistence, .grok/config.toml for native MCP like grepai, .grok/agents/ mirrors, .grok/ thin reference docs for memory history/references/standards, and all .grok/skills/ adapters).
 
-See the source skill for full details on modes, the baseline manifest, and how it helps keep the fleet consistent across machines (some running Claude Code, some Grok).
+See the source skill for full details on modes, the baseline manifest (now includes .grok/ for Grok machines), and how it helps keep the fleet consistent across machines (some running Claude Code, some Grok).
 
-Also update the census component on coord for this host.
+Also update the census component on coord for this host.
+
+When running under Grok, the census should reflect .grok/config.toml , .grok/hooks/claudetools.json , .grok/skills/* (all the command + .claude/skills mirrors + windows-bash), .grok/agents/, .grok/README.md + the pointer docs (REFERENCE.md etc.), and the native MCP loading.
+
+Use GrepAI MCP in the self-check analysis for finding harness pieces.

.grok/skills/shape-spec/SKILL.md

@@ -6,4 +6,6 @@ description: >
 
 **Grok skill.** See `.claude/commands/shape-spec.md` for the full process (it often invokes analysis of the codebase + roadmap + existing specs).
 
-When used, read the command, explore the relevant project (using grepai or tools), then produce the spec artifacts in the conventional specs/<slug>/ location. This eliminates re-explaining context on resume.
+When used, read the command, explore the relevant project (using grepai or tools), then produce the spec artifacts in the conventional specs/<slug>/ location. This eliminates re-explaining context on resume.
+
+**GrepAI-first (MANDATORY):** For all exploration of code, prior specs, roadmap, or context: start with `search_tool` to find `grepai__grepai_search` (and traces), then `use_tool` calls with natural language queries before any direct `read_file`, `grep`, or broad listing. This follows the harness rule in CLAUDE.md + grepai-first standard (loaded by Grok).

.grok/skills/skill-creator/SKILL.md

@@ -0,0 +1,14 @@
+---
+name: skill-creator
+description: Interactively create a new Grok skill (SKILL.md + optional scripts/references). Use when the user wants to create a skill, scaffold a skill, or runs /create-skill.
+---
+
+**Grok skill.** This maps to the shared skill in `.claude/skills/skill-creator/SKILL.md`.
+
+Read `.claude/skills/skill-creator/SKILL.md` (GrepAI-first) and follow, adapting the interactive creation process for Grok (use run_terminal_command for any scaffolding, write for new SKILL.md in .grok/skills/ or .claude/skills/ as appropriate, but prefer .grok/ for Grok-native without touching Claude originals where possible).
+
+The creation workflow, frontmatter, delegation pattern, testing, and examples are in the source.
+
+For Grok, create in .grok/skills/<name>/SKILL.md that delegates to .claude/ where shared, or native.
+
+See also: .grok/skills/ for examples of the thin adapter pattern we use for coexistence.

.grok/skills/stop-slop/SKILL.md

@@ -0,0 +1,14 @@
+---
+name: stop-slop
+description: Enforce high-quality, slop-free output in all Claude responses. MANDATORY AUTOMATIC INVOCATION: This skill is always active. It governs how Claude writes text, code comments, commit messages, documentation, and any other output. Detects and eliminates generic AI filler, hollow phrases, unnecessary verbosity, and performative enthusiasm. Applies to all output — conversation, code, docs, and generated content.
+---
+
+**Grok skill.** This maps to the shared skill in `.claude/skills/stop-slop/SKILL.md`.
+
+Read the source (GrepAI-first) and follow it for output quality enforcement. For Grok, apply the same slop-free rules in responses, code, docs, commits. Use it to critique and fix generated content.
+
+The rules and detection for high-quality output are in `.claude/skills/stop-slop/SKILL.md`.
+
+MANDATORY for quality in all Grok output too (even though named for Claude, the harness applies).
+
+See also: .grok/README.md , CLAUDE.md coding guidelines.

.grok/skills/theme-factory/SKILL.md

@@ -0,0 +1,14 @@
+---
+name: theme-factory
+description: Toolkit for styling artifacts with a theme. These artifacts can be slides, docs, reportings, HTML landing pages, etc. There are 10 pre-set themes with colors/fonts that you can apply to any artifact that has been creating, or can generate a new theme on-the-fly.
+---
+
+**Grok skill.** This maps to the shared skill in `.claude/skills/theme-factory/SKILL.md`.
+
+Read the source (GrepAI MCP first) and follow, adapting for Grok (use image_gen or terminal for visuals, write for themed markdown/html).
+
+The theming toolkit, 10 presets, and on-the-fly generation are in `.claude/skills/theme-factory/SKILL.md`.
+
+Use when styling artifacts, slides, docs, UIs.
+
+See also: .grok/skills/frontend-design/SKILL.md , impeccable.

.grok/skills/wiki-lint/SKILL.md

@@ -6,4 +6,5 @@ description: >
 
 **Grok skill.** Details in `.claude/commands/wiki-lint.md`.
 
-Runs checks against the wiki/ tree (stale IPs, orphaned pages, bad links to clients/projects/systems). Use `read_file` + grep tools (or the grepai MCP) heavily. Report findings and suggest fixes (often via wiki-compile or manual edits).
+Runs checks against the wiki/ tree (stale IPs, orphaned pages, bad links to clients/projects/systems). 
+**GrepAI-first (MANDATORY):** Use `search_tool` + `use_tool` (grepai__grepai_search etc. via the MCP) **before** any `read_file` or built-in `grep` for discovering issues in wiki, session-logs, or related files. Only read full files when editing or the semantic results are insufficient. Report findings and suggest fixes (often via wiki-compile or manual edits).

.grok/standards/README.md

@@ -0,0 +1,15 @@
+# .grok/standards/
+
+**Grok pointer.** The standards (api, client, git, powershell, security, ssh, syncro, conventions, context-lookup/grepai-first, etc.) are in `.claude/standards/`.
+
+Grok must follow them (via CLAUDE.md instructions, the inject-standards skill which has .grok/skills/inject-standards/SKILL.md mirror, and GrepAI searches).
+
+See .claude/standards/index.yml and the subdirs.
+
+Use the inject-standards skill (/inject-standards) to load them into context.
+
+GrepAI-first when searching standards content.
+
+The grepai-first standard is especially important for this "Grok use GrepAI for context" setup.
+
+See .grok/skills/inject-standards/SKILL.md and .claude/standards/ .