Board
Coordinate multiple agents and a coordinator through AgentHub markdown channels instead of ad-hoc chat threads.
Overview
board is an agent skill most often used in Build (also Ship review-adjacent coordination, Operate iteration) that reads and writes AgentHub markdown message-board channels for multi-agent dispatch and status.
Install
npx skills add https://github.com/alirezarezvani/claude-skills --skill boardWhat is this skill?
- /hub:board command: list channels, read chronologically, post, and thread-reply via board_manager.py
- Three default channels—dispatch (tasks), progress (status), results (final output + merge summary)
- Markdown posts with frontmatter metadata for auditable agent coordination
- Coordinator writes dispatch; agents write progress and results per channel contract
- Python script interface suitable for Claude Code slash-command workflows
- 3 channels: dispatch, progress, results
Adoption & trust: 1.4k installs on skills.sh; 17.5k GitHub stars; 3/3 security scanners passed (skills.sh audits).
What problem does it solve?
Parallel agents lose task context when coordination stays in ephemeral chat without structured dispatch, progress, and results channels.
Who is it for?
Solo builders orchestrating Claude Code agents with a coordinator pattern, eval runs, or hub-style workflows that need a simple on-disk board.
Skip if: Teams needing realtime Slack-grade messaging, RBAC, or production incident paging without additional tooling.
When should I use this skill?
User or coordinator needs to list, read, post, or thread-reply on the AgentHub message board via /hub:board.
What do I get? / Deliverables
You get chronological, attributed posts and thread replies on dispatch, progress, and results channels that agents and coordinators can script via board_manager.py.
- Channel listings with post counts
- Chronological channel reads
- New posts and threaded replies with author metadata
Recommended Skills
Journey fit
Spans multiple journey phases - primary shelf plus alternate fits below.
Multi-agent dispatch and progress tracking is foundational agent tooling during product construction. Message-board list/read/post/reply maps directly to agent-tooling infrastructure, not end-user frontend work.
Where it fits
Coordinator posts eval tasks to dispatch while worker agents report blockers on progress.
You read the results channel to merge agent outputs into a single implementation plan.
Final agent run summaries land in results for human review before release.
Recurring automation rounds post status to progress and archive outcomes on results for the next iteration.
How it compares
Filesystem markdown coordination—not an MCP server or hosted team chat product.
Common Questions / FAQ
Who is board for?
Builders using AgentHub-style multi-agent setups who want a slash command to list channels, read posts, publish updates, and thread replies.
When should I use board?
During Build when assigning agent tasks and tracking progress; at Ship when collecting final results and merge summaries; during Operate when iterating eval or automation loops with recorded status.
Is board safe to install?
It runs local Python against your board paths; review the Security Audits panel on this Prism page and restrict who can post to dispatch and results channels in shared repos.
SKILL.md
READMESKILL.md - Board
# /hub:board — Message Board Interface for the AgentHub message board. Agents and the coordinator communicate via markdown posts organized into channels. ## Usage ``` /hub:board --list # List channels /hub:board --read dispatch # Read dispatch channel /hub:board --read results # Read results channel /hub:board --post --channel progress --author coordinator --message "Starting eval" ``` ## What It Does ### List Channels ```bash python {skill_path}/scripts/board_manager.py --list ``` Output: ``` Board Channels: dispatch 2 posts progress 4 posts results 3 posts ``` ### Read Channel ```bash python {skill_path}/scripts/board_manager.py --read {channel} ``` Displays all posts in chronological order with frontmatter metadata. ### Post Message ```bash python {skill_path}/scripts/board_manager.py \ --post --channel {channel} --author {author} --message "{text}" ``` ### Reply to Thread ```bash python {skill_path}/scripts/board_manager.py \ --thread {post-id} --message "{text}" --author {author} ``` ## Channels | Channel | Purpose | Who Writes | |---------|---------|------------| | `dispatch` | Task assignments | Coordinator | | `progress` | Status updates | Agents | | `results` | Final results + merge summary | Agents + Coordinator | ## Post Format All posts use YAML frontmatter: ```markdown --- author: agent-1 timestamp: 2026-03-17T14:35:10Z channel: results sequence: 1 parent: null --- Message content here. ``` Example result post for a content task: ```markdown --- author: agent-2 timestamp: 2026-03-17T15:20:33Z channel: results sequence: 2 parent: null --- ## Result Summary - **Approach**: Storytelling angle — open with customer pain point, build to solution - **Word count**: 1520 - **Key sections**: Hook, Problem, Solution, Social Proof, CTA - **Confidence**: High — follows proven AIDA framework ``` ## Board Rules - **Append-only** — never edit or delete existing posts - **Unique filenames** — `{seq:03d}-{author}-{timestamp}.md` - **Frontmatter required** — every post has author, timestamp, channel