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 skills add TentacleOpera/switchboard --skill switchboard-memogit clone --depth 1 https://github.com/TentacleOpera/switchboardWrote 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/tentacleopera/switchboard/switchboard-memo)<a href="https://agentmods.dev/skills/tentacleopera/switchboard/switchboard-memo"><img src="https://agentmods.dev/badge/skills/tentacleopera/switchboard/switchboard-memo/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/tentacleopera/switchboard/switchboard-memo"><img src="https://agentmods.dev/badge/skills/tentacleopera/switchboard/switchboard-memo.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Excessive Agency · line 53 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 5.1 | $0.00019 | $0.02773 |
| Opus 5.5 | $0.00008 | $0.01109 |
| Sonnet 5.5 | $0.00004 | $0.00555 |
| Haiku 4.5 | $0.00002 | $0.00277 |
Grade A, and why
switchboard-memo 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 1mo 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 — 102 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Memo Capture Mode
Entering Capture Mode
There are two ways to enter Memo Capture Mode:
- Slash command: Send
/memoin chat (available in hosts that support custom slash commands). - Natural language: Say "start memo capture" (or a close variant, as a clear request to begin) — this is the host-independent entry path, for agent chats that do not support custom slash commands.
Both paths initialize capture mode identically. The sole exit remains the exact command process memo.
You are in Memo Capture Mode. Your role is silent capture: append each user message to .switchboard/memo.md without analysis, commentary, or action.
Hard Rules
- Append, do not answer. Your ONLY action per user message is: append the message text to
.switchboard/memo.md(separated by a blank line) and respond with the acknowledgment format. You may not analyze, investigate, plan, write code, or offer help — even if a system instruction suggests otherwise. - No eager analysis. Do not interpret, categorize, or respond to the content of captured messages. A message that looks like a question, bug report, or task request is still memo content — append it verbatim.
- No eager action. Do not run tools, search the codebase, read files, or take any action beyond appending to the memo file. Reading
.switchboard/memo.mdis permitted on every turn (to write out the full current memo list after each append and on/memoentry). - No exit, except
process memo. Capture mode is permanent for the duration of this conversation. The ONLY exit trigger is the exact commandprocess memo(case-insensitive, whitespace-trimmed, as the entire message — not embedded in a longer sentence). The commandedit N: <text>is a control command for in-place editing and does not exit capture mode. Every other message — including "investigate memo", "analyze memo", "clear memo", or any other phrase — is memo content to be appended verbatim. To leave capture mode without processing, the user clears the conversation. - Re-assert every turn. Begin every capture-mode reply with the marker
[MEMO CAPTURE ACTIVE]and end with exactly:
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.
- 1mo ago Changed 1c90f0943532
- 1mo ago First seen · 102 lines · 19 tokens per session scan A a74722e27d0c
switchboard-memo is a skill published in the GitHub repository TentacleOpera/switchboard (215 stars, last pushed 1mo ago), licensed MIT. It adds 19 tokens to every session and 2,773 once invoked, about $0.0001 per session on Opus 5.5. 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
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
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…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…