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/smk-labs/claude-plugins/connectnpx skills add smk-labs/claude-plugins --skill connectgit clone --depth 1 https://github.com/smk-labs/claude-pluginsWrote 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/smk-labs/claude-plugins/connect)<a href="https://agentmods.dev/skills/smk-labs/claude-plugins/connect"><img src="https://agentmods.dev/badge/skills/smk-labs/claude-plugins/connect.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 | $0.00105 | $0.01552 |
| Opus 5 | $0.00053 | $0.00776 |
| Sonnet 5 | $0.00021 | $0.00310 |
| Haiku 4.5 | $0.00011 | $0.00155 |
Grade A, and why
connect scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 5d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 69 lines — stays where its author put it; the contents beside it link to each section on GitHub.
readable connect
Registration is automatic: the first session after install copies the server to a version-free stable path and registers it in every Claude desktop profile on the machine, then says so once. So this skill is not a setup step. It is the diagnostic, the opt-out, and the fallback for the one case automation cannot reach.
Start with status, always
sh "$CLAUDE_PLUGIN_ROOT/hooks/connect.sh" status
It lists every Claude profile found here and, for each, whether readable-card is registered and whether the path it names still resolves. Read the result out to the user before doing anything else. A missing-card complaint is almost always one of these, and status tells you which:
- not registered anywhere — no Claude Code session has run since install (desktop chat runs no hooks, so nothing had a chance to register). Run
connect. - registered, path does not exist — a stale hand-made entry pointing into a versioned cache dir. Run
connect; it replaces that with the stable path. - registered and the path resolves — registration is fine, so the problem is elsewhere. The app has not been restarted since the entry appeared, or the host simply cannot paint cards. Claude Code sessions are the second case and it is not a bug: those hosts negotiate no MCP Apps UI, so the card tool is not offered there at all and replies arrive as a widget or as BiDi-safe plain text instead.
If the user reports raw HTML in a chat bubble, they are on a version older than 6.0.0. The fix is an update, not a reconnect.
When status says everything is fine and cards still do not appear
Then registration is not the problem and the host is. Read the handshake the server logged, which is the only place that records whether a given host can paint at all:
grep -a "client=" ~/Library/Logs/Claude/mcp-server-readable-card.log | tail -5
Each line ends in mcp-apps=YES or mcp-apps=NO. NO means that host negotiated no MCP Apps UI, so the card tool was never offered to it and the reply correctly arrived as a widget or as plain text. Do not treat that as a fault to fix.
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.
- 5d ago First seen · 69 lines · 105 tokens per session scan A 00801a48f49b
connect is a skill published in the GitHub repository smk-labs/claude-plugins (11 stars, last pushed 4d ago), licensed MIT. It adds 105 tokens to every session and 1,552 once invoked, about $0.0005 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
ab-test-analysis
Analyze A/B test results with statistical significance, sample size validation, confidence intervals, and ship/extend/stop recommendations. Use when evaluating experiment results, checking if a test reached significance, interpreting split test data, or deciding whether to ship a variant.
brainstorm-okrs
Brainstorm team-level OKRs aligned with company objectives — qualitative objectives with measurable key results. Use when setting quarterly OKRs, aligning team goals with company strategy, drafting objectives, or learning how to write effective OKRs.
dummy-dataset
Generate realistic dummy datasets for testing with customizable columns, constraints, and output formats (CSV, JSON, SQL, Python script). Use when creating test data, building mock datasets, or generating sample data for development and demos.
outcome-roadmap
Transform an output-focused roadmap into an outcome-focused one that communicates strategic intent. Rewrites initiatives as outcome statements reflecting user and business impacts. Use when shifting to outcome roadmaps, making a roadmap more strategic, or rewriting feature lists as outcomes.
pre-mortem
Run a pre-mortem risk analysis on a PRD or launch plan. Categorizes risks as Tigers (real problems), Paper Tigers (overblown concerns), and Elephants (unspoken worries), then classifies as launch-blocking, fast-follow, or track. Use when preparing for launch, stress-testing a product plan, or identifying what could go…
shipping-artifacts
The durable documentation set that makes an AI-built (vibe-coded) app reviewable before shipping. A small core every app needs — architecture, user/permission flows, permissions, variables/secrets, and a test-coverage map — plus conditional docs added only when they apply: emails, scheduled work, SEO, and embedded…