harnessprotocol/board
plugins/board/skills/board/SKILL.md
Use when the user invokes /board or wants to view, create, move, or manage tasks on the Harness Board.
$ install --global
skillsauthnpx skillsauth add harnessprotocol/harness-kit boardInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
Security Scan Results
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
3
Scanners Passed
9
Scanners in report
Clean
TrivyContainer and dependency vulnerability scanner
95%
Clean
SemgrepStatic code analysis for vulnerabilities
95%
Clean
mcp-scan (Snyk)Model Context Protocol security validation
95%
Skipped
Snyk (dep)Open source security scanning
50%
Skipped
Socket.devSupply chain security analysis
50%
Skipped
VirusTotalMulti-engine malware detection
50%
Skipped
CrowdStrikeAdvanced threat intelligence
50%
Skipped
OSV-ScannerOpen Source Vulnerability database check
50%
Skipped
OWASP Dep-Check
50%
Last scanned: Apr 20, 2026, 2:05 AM35.3s1 file scanned
SKILL.md
- name:
- board
- description:
- Use when the user invokes /board or wants to view, create, move, or manage tasks on the Harness Board.
Harness Board
Use this skill when the user invokes /board or asks to manage tasks, create epics, move tasks, or check project status on the Harness Board.
What is Harness Board?
A lightweight Kanban board with real-time two-way sync between Claude and a web UI. Tasks live in ~/.harness/board/projects/<slug>.yaml. Claude interacts via MCP tools; humans interact via browser.
MCP Tools Available
| Tool | Purpose |
|------|---------|
| create_project | Create a new project |
| create_epic | Create an epic under a project |
| create_task | Create a task under an epic |
| update_task | Edit title, description, flags |
| move_task | Change status column |
| add_comment | Post a comment as "claude" or "user" |
| list_tasks | Read board state (filterable) |
| link_branch | Associate branch/worktree with task |
| link_commit | Attach a commit SHA |
| request_review | Flag task ready for human review |
| block_task | Mark blocked with reason |
| unblock_task | Clear blocked status |
Usage Patterns
/board — Open the board UI
Open the board web UI (requires the board server to be running as a background service):
bash ${CLAUDE_PLUGIN_ROOT}/scripts/start-board.sh
If the server is not running, the script prints instructions to install it as a persistent launchd service with pnpm board:install.
/board create <title> — Create a task
- Call
list_tasksto find the active project and epic - Call
create_taskwith the current project + epic - Confirm task ID and status to the user
/board status — Show current board state
Call list_tasks and format a concise summary grouped by status.
/board move <task-id> <status> — Move a task
Call move_task with the appropriate project, task_id, and status.
Workflow Integration
When starting work on a task:
move_task→ "in-progress"link_branchwith the worktree branch- Add progress comments via
add_comment(author: "claude") request_reviewwhen readymove_task→ "done" after merge
Status Values
backlog— not startedin-progress— being worked onreview— ready for human reviewdone— complete
Related Skills
harnessprotocol/rubber-ducky
development
VerifiedTrustedCommunity
Use when you've planned a non-trivial change and are about to implement it, finished a complex or multi-file piece of work, just wrote tests, or are stuck on repeated failures — and any time the user says "rubber duck this", "rubber ducky", "get a second opinion", "sanity-check my plan", "poke holes in this", "what am I missing", "critique my approach", "review this before I build it", or "/rubber-ducky". Spawns independent read-only critics on DIFFERENT Claude models than the one driving the session to catch blind spots, design flaws, and substantive bugs while course corrections are still cheap. Skip it only for small, obvious, well-understood changes. Do NOT use for reviewing a finished diff or PR — use /review for that; rubber-ducky pressure-tests your own in-progress thinking before and during implementation.
8SKILL.mdUpdated Jun 7, 2026
harnessprotocol/dependabot-sweep
tools
VerifiedTrustedCommunity
Use when the user wants to fix, address, clear, or resolve open Dependabot security/vulnerability alerts for a repository, end to end. Fetches open alerts via the gh CLI, fixes them per ecosystem (pnpm/npm overrides + lockfile regen, cargo update, pip/go/bundler), verifies with audit and frozen-lockfile installs, then branches → commits → pushes → opens a PR, and squash-merges once CI is green — escalating only when a fix carries breaking-change risk or can't be resolved. Trigger on "/dependabot-sweep", "address the dependabot alerts", "fix the security vulnerabilities", "clear the dependabot alerts", "handle the dependency vulnerabilities", "sweep dependabot".
8SKILL.mdUpdated Jun 7, 2026
harnessprotocol/harness-docs
tools
VerifiedTrustedCommunity
Harness Kit documentation — installation, plugin catalog, creating plugins, cross-harness setup, architecture, and FAQ. Use when working with or configuring harness-kit plugins, understanding the plugin/skill system, installing slash commands, setting up AI coding tool configuration, answering questions about the plugin marketplace, writing SKILL.md files, using harness.yaml, or integrating with Copilot, Cursor, or Codex. Do NOT use for general Claude Code questions unrelated to harness-kit.
1SKILL.mdUpdated Apr 18, 2026
harnessprotocol/stats
development
VerifiedTrustedCommunity
Use when user invokes /stats or asks about Claude Code usage, token consumption, session history, model distribution, or activity patterns. Generates an interactive HTML dashboard with charts and tables, auto-opens in browser. Also triggers on "how much have I used Claude", "show my usage", "token usage", "session stats", "usage report", "usage dashboard". Do NOT use for API billing or cost estimation — token counts are not costs.
1SKILL.mdUpdated Apr 16, 2026