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/tentacleopera/switchboard/switchboard-remotenpx skills add TentacleOpera/switchboard --skill switchboard-remotegit clone --depth 1 https://github.com/TentacleOpera/switchboardWhat 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 | $0.04831 |
| Opus 5 | $0.00016 | $0.02416 |
| Sonnet 5 | $0.00006 | $0.00966 |
| Haiku 4.5 | $0.00003 | $0.00483 |
Grade A, and why
switchboard-remote 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.
How it starts
The opening of the file, as written. The whole thing — 353 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Connections & Remote Switchboard Session Entry Point
You are entering a Connections & Remote Switchboard planning session. Drive board planning either remotely (away from desk) or side-by-side using external AI surfaces (e.g. Gemini Spark or Claude Cowork). Plans live in Linear, Notion, or external file return paths. MCP or file watchers serve as the integration layer.
This is the external/remote counterpart to /sw (switchboard-chat). Use /sw when you have local access; use /sw-remote for external surfaces or away-from-desk control.
1. Confirm Remote Context
Check which MCP servers are connected (Linear, Notion, GitHub):
- Report what's available and note any missing connections.
- If neither Linear nor Notion is connected, warn the user that remote planning won't
be possible and offer to fall back to
/swif the user has local access.
2. Remote-Mode Rules
- Plans are stored in Linear/Notion — do NOT write
.mdfiles to.switchboard/plans/or commit to a branch for planning work. - Use
list_issues(Linear) / Notion database queries to read the current kanban state (not localkanban.dborkanban-board.md). - To improve a plan: use
/improve-remote-plan(not/improve-plan). - To create a new plan: write directly to a new Linear issue or Notion page, set status to "Created".
- Column transitions happen via status updates in Linear/Notion — the extension picks them up on next IDE startup via the startup reconciler.
- To trigger local execution: set the Linear/Notion status to the execution-trigger
state (confirm the name with
list_issue_statusesfirst for Linear; read theKanban Columnselect options for Notion).
3. Read Current Board State
- Query Linear/Notion for issues in the Switchboard-mapped project, grouped by status.
- Present a brief summary: how many plans per column, any plans in a state that suggests remote action is needed (e.g. "Created" plans that could be improved).
4. Prompt for Intent
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 · 353 lines · 32 tokens per session scan A 489cba3b99cf
switchboard-remote is a skill published in the GitHub repository TentacleOpera/switchboard (213 stars, last pushed 3d ago), licensed MIT. It adds 32 tokens to every session and 4,831 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
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.
auto-perf-optimize
Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.
chat-perf
Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.
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…