title: Claude Code workflow suggestions — round 1 date: 2026-05-24 host: ONE (10.10.1.120) scope: homelab ops/infra, vault knowledge mgmt, agent infra/memory risk: wide net (stable + experimental)


Suggestions — round 1

Companion analysis of your current Claude Code setup with curated additions targeting your three stated focus areas. Items marked [exp] are experimental/newer; [stable] are battle-tested; no marker means active but not yet 1.0.


1. Your current footprint (what's already in place)

13 plugin marketplaces installed — already very rich. You have:

Category Already covered by
Memory/observability claude-mem (timeline, knowledge-agent, weekly-digests, oh-my-issues, babysit, design-is, pathfinder, version-bump, smart-explore, wowerpoint)
Markdown tooling han/markdown (just fixed — marksman LSP), claude-mem:make-plan/do
Karpathy guidelines andrej-karpathy-skills
Vault automation 50+ custom /vault-* commands (your own)
Dev infra claude-dev-infrastructure (qa, plugin-creator, ai-truthfulness, etc.)
Sub-agents voltagent-subagents (35 agents loaded)
LSPs claude-code-lsps (4 LSP servers, incl. marksman now)

25 MCP servers configured — heavy investment in: cloudns, cognee, context7, docker-mcp, fetch, filesystem, firecrawl, lean-ctx, nmap, obsidian, pfsense, plesk, postgres, powershell-ssh, proxmox, puppeteer, qdrant-memory, sequential-thinking, shell, silverbullet, sqlite, ssh, web-reader, web-search-prime, zread.

Pain points surfaced from mem-search (last 30 days): - Cognee Gemini max_tokens truncations on cognify runs (#3589, #3590) - GRAPH_COMPLETION search timeouts via MCP 3s client limit (#3550) - SMB file enumeration timeouts after 120s (#3334) - Repeated MCP transport tracebacks corrupting poller loops (#3512) - Plugin LSP install scripts assuming brew/cargo only (today's marksman issue) - ClouDNS MCP didn't exist — you wrote your own (#2882, #2886) - Pre-cache claude-mem corpora before query, else null (already noted in CLAUDE.md)


2. MCP Servers worth evaluating

Homelab / infra ops

Vault / knowledge management

Agent infra / memory


3. Plugins & marketplaces worth scanning

Claude Code marketplaces not yet installed

Skills worth lifting / reimplementing

You already have an extensive /vault-* family. Gaps worth filling:


4. Operational tools (CLI / containerized)

Knowledge graph / RAG alternatives or complements to cognee

Observability for your homelab stacks

Networking & infra utilities

Vault publishing pipeline

Memory / agent infra


5. Targeted fixes for surfaced pain points

Pain point (obs ID) Suggested addition
Cognee Gemini max_tokens truncations (#3589) Add litellm proxy in front of cognee; set max_tokens ceiling + automatic chunking + fallback to local Ollama on truncation
GRAPH_COMPLETION MCP 3s timeout (#3550) Wrap cognee MCP with a retry+REST-fallback shim (you already do this manually for claude-mem)
SMB file enum 120s timeout (#3334) Cache vault tree to a local SQLite mirror; install Everything mcp or use fd -L w/ exclude rules
MCP transport tracebacks corrupting poller (#3512) mcp-supervisor pattern: PM2/supervisord watching every MCP stdio, restart on health failure
ClouDNS had no MCP, you built one (#2886) Publish your cloudns-mcp to the marketplace; check pfsense-mcp write-ops branch too
Plugin install assumes brew/cargo (today) plugin-doctor skill that auto-detects platform + installs binaries; PR back upstream to han/markdown
Repeated "is process X already running?" checks Add Beszel or Dozzle for at-a-glance container/process state; reduce bash probing

6. Quick wins (low cost, high signal)

  1. Symlink-fix pattern as a hook — your marksman fix today (symlink ~/.local/bin/usr/local/bin) is a recurring pattern. Add a SessionStart hook that ensures /usr/local/bin has symlinks for all ~/.local/bin/* binaries plugins might need.
  2. /mcp-health slash command — 30-line bash that hits every MCP's known health endpoint; would have caught marksman LSP within 1 cycle.
  3. vault-cognee-sync skill — incremental cognee re-ingest only for vault files changed since last cognify run; avoids the 40+ minute full rebuilds.
  4. /doctor autorun on SessionStart — surface plugin issues immediately, not next time you remember.
  5. mem-search corpus prewarm cron — daily background prime so you never hit the null-on-cold-cache trap.
  6. One-line marksman-style installers — script + symlink any binary plugins need; commit to a ~/.claude/local-bin-bootstrap.sh.
  7. NPM credentials → docker secrets — surfaced repeatedly in mem-search (#3624 today); ~30 min to migrate.

7. Things to deliberately NOT add

Resist the urge to install: - Another vector DB — you have qdrant (×2), falkordb, cognee's internal. Consolidate, don't add. - Yet another memory layer — you have claude-mem, openmemory, mcp-memory, qdrant-memory, cognee. The architecture sprawl is itself a maintenance load. - More UI dashboards — silverbullet, hermes, vault-site, openwebui, cognee-ui, NPM admin, portainer (if active). Each is a small upkeep tax.

When evaluating any of the above sections, the question to ask is: does this replace something already running, or just add to the inventory? Replacement proposals are higher-value than additions at this stage.


Open questions for you

  1. Is Komodo (/opt/komodo) actively used? If yes, several entries above are redundant. If no, it's a strong candidate to centralize the 25-stack management.
  2. Is litellm (/opt/litellm) running? Several pain-point fixes depend on it being the front for Gemini/Ollama.
  3. Tailscale in active use? Several MCP/network suggestions hinge on this.
  4. k3s/k8s on the roadmap? If no, drop the k8s suggestions; if yes, prioritize differently.
  5. Cognee: stay or migrate? Multiple pain points cluster here. Worth a decision rather than continued patching.
  6. Vault publish stack: keep MkDocs or evaluate Quartz? Quartz natively handles wikilinks and might eliminate the SilverBullet/pygments crash class entirely.

Next round (suggestions-2.md) can drill into whichever of these you want to explore. Just say which sections to expand or which open question to resolve first.