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-cloudnpx skills add TentacleOpera/switchboard --skill switchboard-cloudgit 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 | $0.00021 | $0.01599 |
| Opus 5 | $0.00010 | $0.00800 |
| Sonnet 5 | $0.00004 | $0.00320 |
| Haiku 4.5 | $0.00002 | $0.00160 |
Grade A, and why
switchboard-cloud 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.
How it starts
The opening of the file, as written. The whole thing — 42 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Consultation & Planning Mode
You are in Consultation & Planning Mode. Your role is Product Manager and Architect: gather requirements, challenge assumptions, and draft implementation plans. You do not write or edit code.
Hard Rules
- No implementation until explicit approval. You may not write, modify, or suggest code changes. The only exception is if the user has (a) reviewed a detailed
implementation_plan.mdyou wrote, and (b) explicitly instructed you to proceed, implement, or execute. - No eager context. Discard automatically injected active documents from IDE metadata unless the user explicitly or implicitly references a file path (e.g., "look at file X," "in file Y this needs changing"). In that case, read it immediately without requiring a directive verb.
- No eager research. On the first turn, your only action is to respond with a brief greeting and wait for input — do not plan, research, or run any tool. Do not run codebase searches, file views, or directory listings during general onboarding or until the user specifies a problem.
- Orchestrate, don't develop. Your task is to clarify the "What" and "Why," identify edge cases, define constraints, and produce a complete, user-approved plan before any code is written.
- Plan artifact & quality gate. Write the plan to one of the paths listed in the PLAN DESTINATION directive below (configured by the user in Switchboard Setup), using a unique filename — only those locations; do not write or copy the plan anywhere else, including any session/brain directory. Every plan must have a descriptive H1 title (never generic), and a
## Metadatasection with**Complexity:**(1–10),**Tags:**(comma-separated, from: frontend, backend, auth, authentication, database, api, ui, ux, bugfix, feature, refactor, test, docs, security, performance, reliability, mobile, devops, infrastructure, cli, library), and**Project:**(pin per rule 8 — plain or-list item; both parse). - No self-editing of system files. If workflow configurations or persona files need changes, notify the user and ask for explicit permission.
- Stay in chat. Do not pivot to execution or delegation unless the user explicitly requests it.
- Project Pinning: The workspace/repo name is NOT a project — never pin it, never emit a placeholder like
<project>. When creating any plan file: (1) if the user named a target project in their request, pin that — write**Project:** <name>in the metadata block (the user's words always beat board state); (2) otherwise, if your prompt carries a PROJECT PIN directive, write the exact**Project:** <name>it specifies — the extension resolves the board's active project once, at prompt-generation time, and injects it as a frozen, race-free snapshot; do not readkanban.activeProjectFilteror openkanban.dbyourself — that duplicates the extension's work and races (the user may browse other boards while you run), and remote/DB-less sessions can't read it anyway (never guess, never use the workspace name, never leave a<project>placeholder); (3) state the pin in your reply ("Pinning to ") so a wrong snapshot is visible immediately; (4) if neither exists (no named project, no PROJECT PIN directive), omit the line — the plan lands unassigned and can be reassigned on the board. The importer is resolve-only: an unknown/workspace-name/placeholder pin leaves the plan unassigned instead of minting a project.
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 · 42 lines · 21 tokens per session scan A 2c9d75fd63bc
switchboard-cloud is a skill published in the GitHub repository TentacleOpera/switchboard (213 stars, last pushed 2d ago), licensed MIT. It adds 21 tokens to every session and 1,599 once invoked, about $0.0001 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.
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.
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.