huddle

huddle is a skill for Claude Code, Codex from marcoloco23/huddle-mcp. It costs 70 tokens per session (877 once invoked), scanned A, original, MIT.

A scheduling and review tool for queued briefings from coding agents. It connects those requests to Google Calendar and records the decisions made during the briefing.

In plain words
What is it for?
Use it to book urgent agent blockers for the next free slot, group other requests into review blocks, and save your decisions after each briefing.
Why use it?
It keeps agent questions and plans from interrupting your work one by one. Instead, it groups them into private calendar meetings at suitable times.

Skill for Claude CodeCodex

Install

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.

agentmods
npx agentmods add skills/marcoloco23/huddle-mcp/huddle
Any agent
npx skills add marcoloco23/huddle-mcp --skill huddle
Clone the repo
git clone --depth 1 https://github.com/marcoloco23/huddle-mcp

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for huddle

README.md
[![agentmods](https://agentmods.dev/badge/skills/marcoloco23/huddle-mcp/huddle.svg)](https://agentmods.dev/skills/marcoloco23/huddle-mcp/huddle)
Your own site
<a href="https://agentmods.dev/skills/marcoloco23/huddle-mcp/huddle"><img src="https://agentmods.dev/badge/skills/marcoloco23/huddle-mcp/huddle.svg" alt="Measured on agentmods" height="20"></a>
Per session 70 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 877 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00070 $0.00877
Opus 5 $0.00035 $0.00439
Sonnet 5 $0.00014 $0.00175
Haiku 4.5 $0.00007 $0.00088

Measured 3d ago against content hash 0464a186c56f, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

huddle 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.

skills/huddle/SKILL.md · 71 lines

How it starts

The opening of the file, as written. The whole thing — 71 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Huddle — book and run agent briefings

huddle-mcp is a coordination broker: parallel coding agents queue their plans and questions into it instead of interrupting the user. This skill is the orchestrator side — it turns that queue into real calendar events and records the user's decisions back. The broker never touches the calendar itself; you bridge it to whatever Google Calendar MCP the user has connected.

Prerequisites: both huddle-mcp and a Google Calendar MCP are connected.

Booking the queue

  1. plan_meetings → returns unbookedMeetings, each with desiredWindow (asap | next-block), durationMinutes, and briefingMarkdown.
  2. For each meeting, find a free slot via the calendar MCP (its suggest_time / list_events / freebusy tools) within the user's working hours:
    • asap (blockers) → the soonest free slot today.
    • next-block → the next review block (late morning / late afternoon); bundle, don't scatter. Create the event with:
    • title = the meeting title,
    • description = the meeting briefingMarkdown verbatim (this is the agenda),
    • duration = durationMinutes,
    • visibility = private — briefings carry plans and code into the calendar.
  3. confirm_meeting with the meeting_id, the calendar event id the calendar MCP returned, and the start/end you booked.

Then tell the user what you scheduled and when — one line per meeting.

Each briefing description ends with a writable answer block (tkt_xxx → ), so the user can reply inside the event itself — that's the read-back path below.

Closing the loop — two ways, both unblock the waiting agents

A. The user answers inside the calendar event (e.g. they say "read my huddle answers", or you're checking after a booked briefing's time):

  1. list_agenda → find booked meetings and their calendarEventId.
  2. For each, fetch the event via the calendar MCP (get_event) and take its description — the user will have filled in the tkt_xxx → … lines.
  3. Pass that description to ingest_answers. It parses every filled answer and resolves the matching tickets in one call, returning resolved + skipped.
  4. Report what was resolved; the worker agents unblock on their next check_response. FYIs need no answer.

Read the full file on GitHub · 71 lines

Changes

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.

  1. 3d ago First seen · 71 lines · 70 tokens per session scan A 0464a186c56f

Subscribe to this mod's changes

huddle is a skill published in the GitHub repository marcoloco23/huddle-mcp (0 stars, last pushed 2mo ago), licensed MIT. It adds 70 tokens to every session and 877 once invoked, about $0.0003 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 2026-09-01.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

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.

obra/superpowers · 37 tokens

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.

microsoft/vscode · 62 tokens

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.

microsoft/vscode · 51 tokens

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.

microsoft/vscode · 53 tokens

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…

microsoft/vscode · 71 tokens