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/loosedays/vibsync-mcp/vibsync-setupnpx skills add loosedays/vibsync-mcp --skill vibsync-setupgit clone --depth 1 https://github.com/loosedays/vibsync-mcpWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/loosedays/vibsync-mcp/vibsync-setup)<a href="https://agentmods.dev/skills/loosedays/vibsync-mcp/vibsync-setup"><img src="https://agentmods.dev/badge/skills/loosedays/vibsync-mcp/vibsync-setup.svg" alt="Measured on agentmods" height="20"></a>What 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 | $0.00065 | $0.00532 |
| Opus 5 | $0.00032 | $0.00266 |
| Sonnet 5 | $0.00013 | $0.00106 |
| Haiku 4.5 | $0.00006 | $0.00053 |
Grade A, and why
Vibsync setup 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 3d 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
Vibsync setup & troubleshooting
Vibsync gives your AI coding agents a shared team brain — long-term memory of
decisions and product knowledge, async agent Q&A, task coordination, and
file-claim conflict avoidance — over a remote MCP server at
https://mcp.vibsync.com/mcp. On connect, the server itself tells the agent how
to use its tools; this skill only covers getting connected and verifying it.
Connect (one time)
- This plugin bundles the Vibsync MCP server. On first use, Claude Code opens your browser to sign in and authorize. When asked, approve the team you want to work in. No token or secret to copy — it's browser OAuth.
- Confirm it's live: call the
whoamitool — it returns your team and member. Then callonboardto pull the team's current context.
Installing the plugin is not the same as connecting. A connection exists only after you complete the browser OAuth above and your agent makes a real request.
Verify the handoff (the whole point of Vibsync)
- Save one real decision: ask the agent to record it with
remember(e.g. "API errors use RFC 9457 Problem Details"). - Start a new conversation in the same project and ask, citing the source: "From Vibsync, what did we decide for this project? Cite the source." If it answers from Vibsync, the handoff works — that's Vibsync, not the tool's own memory.
Troubleshooting
- Vibsync tools missing: confirm the plugin is installed and enabled
(
/plugin), then complete the one-time browser OAuth above. - Wrong or empty team: you may have authorized a different team, or the team is new and empty. A credential belongs to exactly one team, so connect again to work in another team.
- Handoff didn't carry over: make sure it's a NEW conversation in the same
project, that the reply cites Vibsync, and that the earlier
rememberactually saved.
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.
- 3d ago First seen · 46 lines · 65 tokens per session scan A 535a057b92a8
Vibsync setup is a skill published in the GitHub repository loosedays/vibsync-mcp (0 stars, last pushed 27d ago), licensed MIT. It adds 65 tokens to every session and 532 once invoked, about $0.0003 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 2026-08-31.
Other skills, from other repositories
lov-auto-context
Manual or hook-triggered context operator. Evaluates the current session for pollution (long conversations, topic drift, stale noise), AND takes concrete context-shaping actions: writing project memory, updating global or project CLAUDE.md (with diff + confirm), and recommending harness commands like /fork, /compact…
lov-fill-web-form
Fill web forms by fetching form fields from a URL, deep-searching the user's local knowledge base for relevant info, and generating a markdown document with all answers pre-filled. Use when the user provides a URL to a web form (conference application, speaker submission, event registration, profile form) and wants…
lov-ataru-indexing
检查并构建本地 Ataru 会话记忆索引，让无界面调用方在检索前拿到 searchable 状态。 Use when asked to build, rebuild, repair, or check the Ataru memory index.
handoff
Use when a coding session is getting long, before stopping complex implementation/migration/debugging work, when the operator says "prepare a handoff" / "hand this off" / "continue in a new chat" / "/handoff", or when a long autonomous run needs continuity (Mode run-ledger, announced in chat) — archives the superseded…
supermemory-agent-learning
Build and integrate SuperMemory — MCP-first agent learning for Claude, Cursor, and custom orchestrators. Use when implementing selective memory capture, evidence-first reflection, lesson validation, promotion queues, retrieval telemetry, experiments, rollback, or wiring SuperMemory via MCP, REST, or SDK. Trigger on…
knowledge-capture-policy
Decide when high-value work should become a Joplin pending capture draft through joplin-llm-wiki MCP tools, without bypassing user confirmation.