Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add skills/wbopan/things-cloud-mcp/syncnpx skills add wbopan/things-cloud-mcp --skill syncgit clone --depth 1 https://github.com/wbopan/things-cloud-mcpWhat it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00032 | $0.00484 |
| Opus 5 | $0.00016 | $0.00242 |
| Sonnet 5 | $0.00006 | $0.00097 |
| Haiku 4.5 | $0.00003 | $0.00048 |
Grade A, and why
sync scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
Sync UI & Docs with Code
Ensure landing.go (web UI) and CLAUDE.md (project instructions) stay in sync with main.go (source of truth).
Process
Step 1: Extract current tool definitions from main.go
Read all mcp.NewTool(...) blocks in main.go. For each tool, extract:
- Tool name
- Description
- Parameters (name, type, required, description, enum values)
- Behavioral annotations (readOnly, destructive, etc.)
Count the total number of tools.
Step 2: Audit landing.go
Read the tool documentation sections in landing.go. Compare against main.go and check for:
- Missing tools: tools in main.go not documented in landing.go
- Removed tools: tools in landing.go that no longer exist in main.go
- Parameter mismatches: parameters added, removed, renamed, or changed type (e.g., bool → enum)
- Description drift: tool descriptions that don't match
- Stale counts: the "N Tools" badges in hero section and category headers
Fix all discrepancies found. Match the existing HTML structure and CSS classes in landing.go.
Step 3: Audit CLAUDE.md
Read CLAUDE.md and compare against main.go:
- Architecture section: verify file descriptions, key types, status/schedule values are correct
- Coding Patterns section: verify handler patterns, wire format notes, helper function references still match the code
- Tool count references: any mention of number of tools
Fix discrepancies. Keep CLAUDE.md concise — don't add verbose explanations.
Step 4: Build verification
Run: /usr/local/go/bin/go build ./...
If it fails, fix the issue.
Step 5: Report
Summarize what was changed:
- List each file modified
- List each discrepancy found and fixed
- If nothing was out of sync, say so
Do NOT commit. Leave that to the user.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 2d ago First seen · 59 lines · 32 tokens per session scan A 071efd236989
sync is a skill published in the GitHub repository wbopan/things-cloud-mcp (23 stars, last pushed 13d ago), licensed MIT. It adds 32 tokens to every session and 484 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
beads
Use when working in a repository that uses bd or Beads for durable project task tracking, issue dependencies, blocker management, multi-session handoff, or shared work memory. Trigger when the user asks to find ready work, claim or close tasks, create follow-up work, inspect blockers, recover project context, or…
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
agent-host-chat-contributions
Build and review cross-cutting agent-host chat behavior through lifecycle contributions. Use when adding turn lifecycle side effects, prompt or context injection, restored-history transformation, protocol-action observation, or when reviewing changes that add code to AgentSideEffects or AgentService.