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 pandysp/claude-plugins --skill agent-boardgit clone --depth 1 https://github.com/pandysp/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/pandysp/claude-plugins/agent-board)<a href="https://agentmods.dev/skills/pandysp/claude-plugins/agent-board"><img src="https://agentmods.dev/badge/skills/pandysp/claude-plugins/agent-board/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/pandysp/claude-plugins/agent-board"><img src="https://agentmods.dev/badge/skills/pandysp/claude-plugins/agent-board.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00129 | $0.00896 |
| Opus 5.5 | $0.00052 | $0.00358 |
| Sonnet 5.5 | $0.00026 | $0.00179 |
| Haiku 4.5 | $0.00013 | $0.00090 |
Grade A, and why
agent-board 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 21d 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 — 36 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent board
A board is a folder of threads that every agent session and the user can read. Each post is its own file, so sessions writing at the same time never overwrite or mix up each other's posts. Ask the user where the board lives if you don't know.
Layout
- Thread: a folder named
<YYYY-MM-DD>-<channel>-<topic>, with the date the thread started, the channel (the team or group it belongs to) and a short kebab-case topic. - Post: a file in the thread folder named
<YYYYMMDD-HHMMSS>-<sender>-to-<recipient>.md. The recipient is a session name,group(everyone in the channel) orall. Only files named like this are posts; ignore anything else in the board folder.
Posting
- Write a new file named with the time from the clock (for example
date +%Y%m%d-%H%M%S), never a time you make up; if the name is taken, use the next second. Start a new thread folder for a new topic. - Make the post self-contained: the reader cannot see your conversation.
- Decide who needs to know now. If it can wait, just post; others find it when they check the board. If a session must act on it, answer it or is waiting for it, message that session with the messaging tool your setup has (for example
agent-manager send <id> "New post for you: <path>"). Message everyone only when everyone's work changes now. A correction or addition gets a message only if the reader already used the old post and is still working with it. A message only points to the post; everything else stays on the board. - Never change a post once it is written, not even your own: others may already have read it. To fix or update it, write a new post that names the post it replaces.
- If you need something from another session, ask it on the board. If you can't go on until it posts, do what you can and end your turn: its message wakes you. Don't wait in a loop, whether on the board, with
agent-manager waitor by checking whether your message arrived; while you are busy, messages to you can't arrive.
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.
- 21d ago First seen · 36 lines · 129 tokens per session scan A d3e433578711
agent-board is a skill published in the GitHub repository pandysp/claude-plugins (6 stars, last pushed 7d ago), licensed MIT. It adds 129 tokens to every session and 896 once invoked, about $0.0005 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 2026-10-06.
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…