kanban-dashboard

kanban-dashboard is a skill for Claude Code, Codex from humanerd-drew/opencode-drewgent. It costs 21 tokens per session (4,428 once invoked), scanned A, original, MIT.

A Flask web server that displays a kanban board, a visual task board with columns such as To Do, In Progress, Blocked, and Completed. It includes live updates, drag-and-drop cards, and a mobile layout.

In plain words
What is it for?
It helps render filtered boards, task cards, detail views, event histories, results, metadata, and links to Obsidian notes.
Why use it?
It gives teams a browser-based view of task status and makes board changes easier to follow.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit It helps render filtered boards, task cards, detail views, event histories, results, metadata, and links to Obsidian notes.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/humanerd-drew/opencode-drewgent/kanban-dashboard
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.

Any agent
npx skills add humanerd-drew/opencode-drewgent --skill kanban-dashboard
Clone the repo
git clone --depth 1 https://github.com/humanerd-drew/opencode-drewgent

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 kanban-dashboard

README.md
[![agentmods](https://agentmods.dev/badge/skills/humanerd-drew/opencode-drewgent/kanban-dashboard.svg)](https://agentmods.dev/skills/humanerd-drew/opencode-drewgent/kanban-dashboard)
Your own site
<a href="https://agentmods.dev/skills/humanerd-drew/opencode-drewgent/kanban-dashboard"><img src="https://agentmods.dev/badge/skills/humanerd-drew/opencode-drewgent/kanban-dashboard.svg" alt="Measured on agentmods" height="20"></a>
Per session 21 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 4,428 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00021 $0.04428
Opus 5 $0.00010 $0.02214
Sonnet 5 $0.00004 $0.00886
Haiku 4.5 $0.00002 $0.00443

Measured 3d ago against content hash c3c410be87e4, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

kanban-dashboard scanned grade A with 1 finding 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

| `_obsidian_url(vault_path)` | 절대경로 → `obsidian://open?vault={{AGENT_NAME}}&file=...` URL 변환 (`urllib.parse.quote`로 인코딩) |
skills/kanban-dashboard/SKILL.md · 360 lines

How it starts

The opening of the file, as written. The whole thing — 360 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Kanban Dashboard Skill

Kanban Dashboard — Flask Server (Primary)

Flask server가 kanban board를 렌더링. SSE 실시간 업데이트 + 드래그드롭 + 모바일 대응.

URL: http://macmini:8765/kanban

레이아웃

  • 보드 탭: All / default / content / integrations — 탭 클릭으로 보드 필터
  • 컬럼: To Do | Ready | In Progress | Blocked | Completed — 상태별 한 줄
  • 카드 표시 (3줄):
    • Title: 제목 (60자 truncation, hover 시 전체 표시)
    • Summary: body에서 ## Topic 첫 문단 추출한 1줄 요약 (.card-summary, 2줄 clamp)
    • Meta row 1: Priority badge + Category badge (컬러 + 이모지: draft-trend=📈#5bc0eb, draft-conversation=💬#aa66ff, draft-seo=🔍#00c853 등) + Board + Worker + Created + Assignee
    • Meta row 3 (if draft path exists): Draft file link (📄, 보라색 obsidian://open 링크) — _extract_draft_path()로 body ## Draft 파일 위치 파싱, _obsidian_url()로 URL 변환
  • 카드 상세 모달: 카드 클릭 시 모달 오픈. 5개 탭:
    • Description (기본): task body (내용/설명) 표시 + 📄 Open in Obsidian 버튼 (body에 ## Draft 파일 위치 경로가 있으면 렌더링) + ✏️ Edit 버튼
    • Events: 생성, 완료, 블록, 클레임 등 이벤트 히스토리
    • Result: task result 필드 (작업 결과물)
    • Info: 모든 메타 필드 (trigger_source, tenant, claim_lock, worker_pid, heartbeat 등)
    • Escape 키 또는 overlay 클릭으로 닫기
    • 데이터 출처: GET /kanban/api/task/<id>
  • Body 에디터: Description 탭에서 Edit 버튼 → title input + body textarea + Save/Cancel 버튼으로 전환. 저장 시 POST /kanban/api/edit 호출. 저장 후 SSE 브로드캐스트로 보드 새로고침.
  • 실시간: SSE 스트림 연결 → 카드 액션 시 즉시 화면 반영 (초록 점으로 연결 상태 표시)
  • 드래그드롭: 카드를 다른 컬럼으로 드래그하면 상태 자동 변경
  • 모바일: 터치 스크롤, 작은 화면에서 컬럼 너비 축소

LaunchAgent (Self-Healing, Auto-Restart)

~/Library/LaunchAgents/ai.{{AGENT_NAME_LOWER}}.kanban-dashboard.plist
  • KeepAlive: SuccessfulExit=false → 프로세스 죽으면 자동 재시작
  • MacMini 재부팅해도 자동 실행
  • 로그: ~/.{{AGENT_NAME_LOWER}}/P6-prefrontal/logs/kanban-server.log

관리 명령

# 상태 확인
launchctl list | grep kanban

# 수동 시작/정지
launchctl start ai.{{AGENT_NAME_LOWER}}.kanban-dashboard
launchctl stop ai.{{AGENT_NAME_LOWER}}.kanban-dashboard

# 로그 확인
tail -f ~/.{{AGENT_NAME_LOWER}}/P6-prefrontal/logs/kanban-server.log

Read the full file on GitHub · 360 lines

Files

What ships with it

3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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 · 360 lines · 0 tokens per session scan A c3c410be87e4

Subscribe to this mod's changes

kanban-dashboard is a skill published in the GitHub repository humanerd-drew/opencode-drewgent (2 stars, last pushed 1mo ago), licensed MIT. It adds 21 tokens to every session and 4,428 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.

Related

Other skills, from other repositories