Fähigkeiten vibe-kanban
📦

vibe-kanban

v1.2.0 Inhaltsrevision r1 Kritisch 🌐 Netzwerkzugriff🔑 Umgebungsvariablen📁 Dateisystemzugriff⚙️ Externe Befehle

KI-Agenten auf einem Kanban-Board koordinieren

Parallele KI-Coding-Arbeit lässt sich über Branches, Logs und Pull Requests hinweg schwer nachverfolgen. Dieser Skill bietet praktische Anleitung zur Einrichtung von Vibe Kanban für lokale Boards, MCP-Verbindungen, Worktree-Isolierung und den Review-Ablauf.

Unterstützt: Claude Codex Code(CC)
⚠️ 38 Schlecht

Mit meinem Agent installieren

Kopieren Sie diese Anfrage in Ihren Agent. Sie enthält die maßgebliche Skill-Seite und das Manifest.

Agent-Anfrage
Review the Skillstore skill "vibe-kanban" from https://skillstore.io/skills/supercent-io-vibe-kanban.md and its manifest at https://skillstore.io/api/skills/supercent-io-vibe-kanban/manifest. Verify the artifact. Do not auto-install. Inspect the skill and report your findings, then wait for an operator or manual installation decision.

Ihr Agent sollte weiterhin seinen Plan anzeigen und alle von der Sicherheitsrichtlinie verlangten Bestätigungen anfordern.

Agent-lesbare Ressourcen

Verwenden Sie diese Links, wenn ein KI-Agent, Crawler oder Skript sauberen Kontext benötigt, statt die vollständige Seite zu lesen.

Markdown-Detailseite GET /skills/supercent-io-vibe-kanban.md Signiertes manifest GET /api/skills/supercent-io-vibe-kanban/manifest Signiertes lockfile GET /api/skills/supercent-io-vibe-kanban/lockfile

Testen

„vibe-kanban“ wird verwendet. Vibe Kanban für ein Repository auf einem nicht standardmäßigen Port starten.

Erwartetes Ergebnis:

Eine knappe Checkliste zu Node-Verfügbarkeit, ausgewähltem Port, lokaler Board-URL, Browserverhalten und Authentifizierungsstatus der Agenten.

„vibe-kanban“ wird verwendet. Drei unabhängige Karten für ein Billing-Feature planen.

Erwartetes Ergebnis:

Drei klar abgegrenzte Kartentitel mit vorgeschlagenen Agenten, erwarteten Dateien oder Bereichen, Review-Nachweisen und Pull-Request-Grenzen.

„vibe-kanban“ wird verwendet. Veraltete Vibe Kanban-Worktrees vor der Bereinigung prüfen.

Erwartetes Ergebnis:

Eine Bereinigungsempfehlung, die eindeutig gemergte Worktrees von Branches trennt, die manuelle Freigabe erfordern.

Sicherheitsaudit

Kritisch
v4 • 7.7.2026 Versionsbericht öffnen

The audit confirmed a critical Docker deployment risk from combining an unpinned container image with a host Docker socket mount. Additional confirmed risks include sourcing .env as shell code, persistent hidden agent configuration writes, secret-printing troubleshooting guidance, unpinned npx execution, and destructive cleanup behavior. Most Markdown backtick, localhost URL, loopback IP, and placeholder secret detections were false positives in documentation context.

10
Gescannte Dateien
1,394
Analysierte Zeilen
21
Prüfelemente
0
Falschmeldungen ignoriert

Bestätigte Sicherheitsbedenken (11)

Kritisch
templates/docker-compose.yml:17
Docker socket access
- /var/run/docker.sock:/var/run/docker.sock
The Docker Compose template mounts /var/run/docker.sock into the container. A compromised container or dependency could control the host Docker daemon and escalate to host-level access.
Kritisch
templates/docker-compose.yml:5templates/docker-compose.yml:17
Unpinned Docker Image with Host Docker Access
The Docker template uses the latest Vibe Kanban image while also mounting the host Docker socket. A future or compromised image release would receive direct access to the host Docker daemon.
The compose file directly uses an unpinned latest image and mounts /var/run/docker.sock. The combination creates a clear supply-chain path to host-level control.
Hoch
scripts/start.sh:78
Environment file access
# .env 파일 로드 (존재하는 경우)
The start script loads a local .env file and line 82 sources it as shell code. A malicious or unreviewed .env can execute commands and expose secrets when the wrapper runs.
Hoch
scripts/start.sh:79
Environment file access
if [[ -f ".env" ]]; then
The start script loads a local .env file and line 82 sources it as shell code. A malicious or unreviewed .env can execute commands and expose secrets when the wrapper runs.
Hoch
scripts/start.sh:80
Environment file access
info ".env 파일 로드 중..."
The start script loads a local .env file and line 82 sources it as shell code. A malicious or unreviewed .env can execute commands and expose secrets when the wrapper runs.
Hoch
scripts/start.sh:82
Environment file access
source .env
The start script loads a local .env file and line 82 sources it as shell code. A malicious or unreviewed .env can execute commands and expose secrets when the wrapper runs.
Hoch
SKILL.md:124
Environment file access
Set in `.env` file before starting the server.
The skill tells users to place configuration in a .env file before startup. In this package, the start script sources .env as shell, so the guidance can lead to executing untrusted env-file content.
Hoch
SKILL.md:70-75scripts/start.sh:109-113
Unpinned npx Package Execution
The skill repeatedly starts Vibe Kanban through npx without pinning a package version or checksum, including the executable start wrapper. This creates supply-chain risk because a future package release or dependency compromise would run in the user workspace.
The command examples and start script directly invoke npx vibe-kanban without a pinned version. npx execution is legitimate for this tool but high impact because it runs external package code locally.
Alle 11 bestätigten Funde anzeigen
Hoch
scripts/start.sh:78-82
Environment File Sourced as Shell Code
The start script loads .env with shell source instead of parsing key-value pairs. A crafted .env can execute arbitrary shell commands before Vibe Kanban starts.
Line 82 directly uses source .env, which executes shell syntax from the file. This is a clear code execution risk when .env content is untrusted or copied from another source.
Hoch
SKILL.md:417-423
Auto-Approved Agent Actions Increase Blast Radius
The skill documents Auto Approve as enabled by default for agents. In a board that launches coding agents in git worktrees, default approval can allow broad filesystem and command actions before human review.
The documentation explicitly states Auto Approve is on by default and the surrounding workflow runs agent CLIs against repositories. The exact runtime permissions depend on agent configuration, so confidence is high but not absolute.
Mittel
scripts/cleanup.sh:70-88
Cleanup Script Can Force Delete Worktrees and Branches
The cleanup helper identifies Vibe Kanban worktrees and can force-remove worktrees and delete branches. A parsing error or broad --all run can remove local work that has not been reviewed.
The script loops over detected worktrees and runs forced removal and branch deletion commands. It supports dry-run, but the destructive path is present and automated.
Elemente der Fähigkeitsprüfung (21)

Dies sind echte lokale Fähigkeiten, die für diese Fähigkeit erwartet werden können; daher müssen sie überprüft werden, werden jedoch nicht als bestätigtes bösartiges Verhalten gezählt.

Hoch
scripts/mcp-setup.sh:61
Hidden file access
CLAUDE_CONFIG="$HOME/.claude/claude_desktop_config.json"
The MCP setup script targets hidden Claude configuration under the user home directory. Writing agent MCP configuration is persistent and can change future tool execution behavior.
Hoch
scripts/mcp-setup.sh:62
Hidden file access
CLAUDE_DIR="$HOME/.claude"
The MCP setup script targets hidden Claude configuration under the user home directory. Writing agent MCP configuration is persistent and can change future tool execution behavior.
Hoch
scripts/mcp-setup.sh:97
Hidden file access
CODEX_CONFIG="$HOME/.codex/config.toml"
The MCP setup script targets hidden Codex configuration under the user home directory. Writing agent MCP configuration is persistent and can change future tool execution behavior.
Hoch
scripts/mcp-setup.sh:98
Hidden file access
CODEX_DIR="$HOME/.codex"
The MCP setup script targets hidden Codex configuration under the user home directory. Writing agent MCP configuration is persistent and can change future tool execution behavior.
Hoch
SKILL.md:140
Hidden file in home directory
`~/.claude/settings.json` or project `.mcp.json`:
The documentation directs users to hidden agent configuration files in the home directory. Registering MCP servers there persists executable tool configuration across future agent sessions.
Hoch
SKILL.md:159
Hidden file in home directory
Add to `~/.config/opencode/opencode.json`:
The documentation directs users to hidden agent configuration files in the home directory. Registering MCP servers there persists executable tool configuration across future agent sessions.
Hoch
SKILL.md:200
Hidden file in home directory
This command adds the `vibe-kanban` MCP server config to `~/.codex/config.toml`.
The documentation directs users to hidden agent configuration files in the home directory. Registering MCP servers there persists executable tool configuration across future agent sessions.
Hoch
SKILL.md:613
Hidden file in home directory
Opencode: ~/.config/opencode/opencode.json
The documentation directs users to hidden agent configuration files in the home directory. Registering MCP servers there persists executable tool configuration across future agent sessions.
Hoch
SKILL.md:614
Hidden file in home directory
Claude Code: ~/.claude/settings.json or .mcp.json
The documentation directs users to hidden agent configuration files in the home directory. Registering MCP servers there persists executable tool configuration across future agent sessions.
Hoch
SKILL.md:140
Hidden file access
`~/.claude/settings.json` or project `.mcp.json`:
The documentation directs users to hidden agent configuration files in the home directory. Registering MCP servers there persists executable tool configuration across future agent sessions.
Hoch
SKILL.md:159
Hidden file access
Add to `~/.config/opencode/opencode.json`:
The documentation directs users to hidden agent configuration files in the home directory. Registering MCP servers there persists executable tool configuration across future agent sessions.
Hoch
SKILL.md:200
Hidden file access
This command adds the `vibe-kanban` MCP server config to `~/.codex/config.toml`.
The documentation directs users to hidden agent configuration files in the home directory. Registering MCP servers there persists executable tool configuration across future agent sessions.
Hoch
SKILL.md:613
Hidden file access
Opencode: ~/.config/opencode/opencode.json
The documentation directs users to hidden agent configuration files in the home directory. Registering MCP servers there persists executable tool configuration across future agent sessions.
Hoch
SKILL.md:614
Hidden file access
Claude Code: ~/.claude/settings.json or .mcp.json
The documentation directs users to hidden agent configuration files in the home directory. Registering MCP servers there persists executable tool configuration across future agent sessions.
Hoch
SKILL.md:313
Generic API/secret keys
-e ANTHROPIC_API_KEY=$ANTHROPIC_API_KEY \
The Docker example passes ANTHROPIC_API_KEY into the container. That gives the containerized application access to a high-value credential and increases impact if the image or runtime is compromised.
Hoch
SKILL.md:367
Generic API/secret keys
echo $ANTHROPIC_API_KEY
The troubleshooting guidance echoes ANTHROPIC_API_KEY to the terminal. Printing secret values can leak credentials into shell history, logs, recordings, or shared terminals.
Hoch
SKILL.md:368
Generic API/secret keys
echo $OPENAI_API_KEY
The troubleshooting guidance echoes OPENAI_API_KEY to the terminal. Printing secret values can leak credentials into shell history, logs, recordings, or shared terminals.
Mittel
scripts/cleanup.sh:72
Shell command substitution
BRANCH=$(git worktree list | grep "$wt" | awk '{print $3}' | tr -d '[]')
The branch selected for deletion is parsed from git worktree output using command substitution and grep. If parsing selects the wrong branch, the later cleanup step can delete unintended local branches.
Mittel
scripts/cleanup.sh:86
Standard device file access
git worktree remove "$wt" --force 2>/dev/null || true
This line force-removes a worktree while suppressing errors. The redirection is harmless by itself, but the flagged line performs destructive filesystem cleanup.
Mittel
scripts/cleanup.sh:87
Standard device file access
git branch -D "$BRANCH" 2>/dev/null || true
This line force-deletes a git branch while suppressing errors. The redirection is harmless by itself, but the flagged line performs destructive repository cleanup.
Niedrig
SKILL.md:95
Hardcoded URL
Remote client initialized with URL: https://api.vibekanban.com
The startup log documents a remote client initialized against api.vibekanban.com. This is a real external network dependency that users should understand, though the line alone does not show data exfiltration.

Risikofaktoren

🌐 Netzwerkzugriff (36)
references/environment-variables.md:45 references/environment-variables.md:55 scripts/health-check.sh:30 scripts/health-check.sh:123 scripts/mcp-setup.sh:49 scripts/mcp-setup.sh:113 scripts/start.sh:39 scripts/start.sh:90 scripts/start.sh:101 scripts/start.sh:103 SKILL.md:10 SKILL.md:84 SKILL.md:88 SKILL.md:95 SKILL.md:103 SKILL.md:216 SKILL.md:220 SKILL.md:314 SKILL.md:322 SKILL.md:325 SKILL.md:356 SKILL.md:535 SKILL.md:536 SKILL.md:537 SKILL.md:538 SKILL.md:539 SKILL.md:540 SKILL.md:591 SKILL.md:595 SKILL.md:116 SKILL.md:149 SKILL.md:168 SKILL.toon:25 SKILL.toon:32 templates/claude-mcp-config.json:7 templates/docker-compose.yml:14
🔑 Umgebungsvariablen (30)
references/environment-variables.md:37 references/environment-variables.md:47 references/environment-variables.md:29 references/environment-variables.md:30 references/environment-variables.md:31 references/environment-variables.md:46 scripts/start.sh:60 scripts/start.sh:61 scripts/start.sh:63 scripts/start.sh:66 scripts/start.sh:67 scripts/start.sh:69 SKILL.md:51 SKILL.md:52 SKILL.md:53 SKILL.md:120 SKILL.md:121 SKILL.md:122 SKILL.md:127 SKILL.md:128 SKILL.md:129 SKILL.md:313 SKILL.md:367 SKILL.md:368 SKILL.md:408 SKILL.md:409 SKILL.md:410 SKILL.md:596 SKILL.md:597 SKILL.md:598
📁 Dateisystemzugriff (42)
references/mcp-api.md:94 references/mcp-api.md:30 references/mcp-api.md:72 references/mcp-api.md:30 references/mcp-api.md:72 scripts/cleanup.sh:36 scripts/cleanup.sh:76 scripts/cleanup.sh:86 scripts/cleanup.sh:87 scripts/health-check.sh:37 scripts/health-check.sh:46 scripts/health-check.sh:50 scripts/health-check.sh:67 scripts/health-check.sh:82 scripts/health-check.sh:84 scripts/health-check.sh:102 scripts/health-check.sh:123 scripts/mcp-setup.sh:61 scripts/mcp-setup.sh:62 scripts/mcp-setup.sh:97 scripts/mcp-setup.sh:98 scripts/mcp-setup.sh:69 scripts/start.sh:38 scripts/start.sh:51 scripts/start.sh:100 scripts/start.sh:101 scripts/start.sh:102 scripts/start.sh:103 SKILL.md:140 SKILL.md:159 SKILL.md:200 SKILL.md:277 SKILL.md:613 SKILL.md:614 SKILL.md:140 SKILL.md:159 SKILL.md:200 SKILL.md:277 SKILL.md:332 SKILL.md:613 SKILL.md:614 templates/docker-compose.yml:16
⚙️ Externe Befehle (127)
scripts/cleanup.sh:47 scripts/cleanup.sh:72 scripts/health-check.sh:38 scripts/health-check.sh:40 scripts/health-check.sh:46 scripts/health-check.sh:47 scripts/health-check.sh:51 scripts/health-check.sh:52 scripts/health-check.sh:82 scripts/health-check.sh:85 scripts/health-check.sh:86 scripts/health-check.sh:87 scripts/health-check.sh:88 scripts/health-check.sh:95 scripts/health-check.sh:109 scripts/mcp-setup.sh:43-55 scripts/mcp-setup.sh:70 scripts/mcp-setup.sh:71 scripts/mcp-setup.sh:104-116 scripts/start.sh:43 scripts/start.sh:45 scripts/start.sh:48 SKILL.md:20 SKILL.md:21 SKILL.md:22 SKILL.md:23 SKILL.md:46-55 SKILL.md:55-70 SKILL.md:70-82 SKILL.md:82-84 SKILL.md:84-87 SKILL.md:87-88 SKILL.md:88 SKILL.md:91-98 SKILL.md:98-102 SKILL.md:102-107 SKILL.md:107-115 SKILL.md:115 SKILL.md:116 SKILL.md:117 SKILL.md:118-119 SKILL.md:119-120 SKILL.md:120-121 SKILL.md:121-122 SKILL.md:122-124 SKILL.md:124-127 SKILL.md:127-128 SKILL.md:128-129 SKILL.md:129-140 SKILL.md:140 SKILL.md:142-155 SKILL.md:155-159 SKILL.md:159-161 SKILL.md:161-174 SKILL.md:174-176 SKILL.md:176-183 SKILL.md:183-184 SKILL.md:184-185 SKILL.md:185-186 SKILL.md:186-187 SKILL.md:187-189 SKILL.md:189 SKILL.md:196-198 SKILL.md:198-200 SKILL.md:200 SKILL.md:213-221 SKILL.md:221-225 SKILL.md:225-227 SKILL.md:227-233 SKILL.md:233-237 SKILL.md:237-248 SKILL.md:248 SKILL.md:276-281 SKILL.md:281-284 SKILL.md:284-287 SKILL.md:287-290 SKILL.md:290-293 SKILL.md:293-296 SKILL.md:296-299 SKILL.md:299-307 SKILL.md:307-316 SKILL.md:316-320 SKILL.md:320-326 SKILL.md:326-331 SKILL.md:331-333 SKILL.md:333-341 SKILL.md:341-350 SKILL.md:350-354 SKILL.md:354-357 SKILL.md:357-361 SKILL.md:361-369 SKILL.md:369-373 SKILL.md:373-379 SKILL.md:379-383 SKILL.md:383-386 SKILL.md:386-394 SKILL.md:394-395 SKILL.md:395-396 SKILL.md:396-407 SKILL.md:407-408 SKILL.md:408 SKILL.md:409 SKILL.md:410 SKILL.md:411-412 SKILL.md:412-413 SKILL.md:413-414 SKILL.md:414-415 SKILL.md:415-419 SKILL.md:419-429 SKILL.md:429-435 SKILL.md:435-439 SKILL.md:439-444 SKILL.md:444-448 SKILL.md:448-453 SKILL.md:453-457 SKILL.md:457-462 SKILL.md:462-468 SKILL.md:468-489 SKILL.md:489-497 SKILL.md:497-504 SKILL.md:504-529 SKILL.md:529-546 SKILL.md:546-562 SKILL.md:562-566 SKILL.md:566-581 SKILL.md:581-587 SKILL.md:587-620

Erkannte Muster

Docker socket access
Geprüft von: codex Audit-Verlauf anzeigen →
Diesen Bericht teilen & zitieren

Teile den versionierten Bewertungsbericht, das neutrale Badge, die Einbettungskarte und Zitate. Skillstore berichtet Nachweise, ohne zu entscheiden, ob dieser Skill sicher ist.

Versionsbericht öffnen
Sicherheitsbewertung

Berichtslink kopieren

https://skillstore.io/skills/supercent-io-vibe-kanban/audits/4?utm_source=security_passport&utm_medium=share&utm_campaign=versioned_report

Markdown-Badge

[![Skillstore security assessment](https://skillstore.io/badges/skills/supercent-io-vibe-kanban/security.svg)](https://skillstore.io/skills/supercent-io-vibe-kanban?utm_source=security_passport_badge)

HTML-Badge

<a href="https://skillstore.io/skills/supercent-io-vibe-kanban?utm_source=security_passport_badge"><img src="https://skillstore.io/badges/skills/supercent-io-vibe-kanban/security.svg" alt="Skillstore security assessment" loading="lazy"></a>

Einbettungskarte

<iframe src="https://skillstore.io/embed/skills/supercent-io-vibe-kanban.html" title="Skillstore Security Assessment" sandbox="allow-popups allow-popups-to-escape-sandbox" loading="lazy" referrerpolicy="no-referrer" width="420" height="180"></iframe>
Wissenschaftliche Zitate (APA · BibTeX · CFF)

APA-Zitat

supercent-io. (2026). vibe-kanban security audit report (audit version 4) [Author version 1.2.0]. Skillstore. https://skillstore.io/skills/supercent-io-vibe-kanban/audits/4

BibTeX-Zitat

@techreport{supercent-io-supercent-io-vibe-kanban-2026, author = {supercent-io}, title = {vibe-kanban security audit report (audit version 4)}, institution = {Skillstore}, year = {2026}, number = {4}, url = {https://skillstore.io/skills/supercent-io-vibe-kanban/audits/4}, note = {Author version 1.2.0} }

CITATION.cff

cff-version: 1.2.0 message: "If you use this Skill, cite its author and this versioned security audit report." title: "vibe-kanban security audit report (audit version 4)" version: "1.2.0" type: report authors: - name: "supercent-io" date-released: "2026-07-07" url: "https://skillstore.io/skills/supercent-io-vibe-kanban/audits/4" identifiers: - type: other value: "skillstore:supercent-io-vibe-kanban:audit:4" description: "Skillstore immutable audit report identifier"

Skillstore-Score

Warum dieser Score Evidenzvertrauen: Mittel
64
Architektur
100
Wartbarkeit
87
Inhalt
70
Gemeinschaft
87
Spezifikationskonformität

Was Sie erstellen können

Parallele Feature-Arbeit koordinieren

Ein Epic in unabhängige Vibe Kanban-Workspaces aufteilen, Agenten zuweisen und jedes Ergebnis als separaten Branch oder Pull Request reviewen.

Agent-Implementierungen vergleichen

Dieselbe klar abgegrenzte Aufgabe mit verschiedenen Agenten ausführen und Diffs, Logs und Testergebnisse vergleichen, bevor eine Richtung gewählt wird.

Lokale Agent-Orchestrierung vorbereiten

Lokale MCP-Verbindungen, Umgebungsvariablen und Health Checks einrichten, damit Agent-Arbeit über ein einziges Board überwacht werden kann.

Diese Prompts ausprobieren

Ein lokales Board starten 
Verwende den Vibe Kanban-Skill, um mir beim Starten eines lokalen Boards für dieses Repository zu helfen. Prüfe die Voraussetzungen, wähle einen sicheren Port und erkläre, was ich vor dem Erstellen eines Workspaces verifizieren sollte.
Workspaces für ein Epic planen 
Verwende Vibe Kanban, um dieses Feature in drei unabhängige Workspaces aufzuteilen. Schlage für jeden Workspace einen fokussierten Titel, eine Agent-Auswahl, Review-Nachweise und eine Pull-Request-Grenze vor.
MCP für Codex konfigurieren 
Überprüfe meine aktuelle Einrichtung und bereite die Vibe Kanban-MCP-Konfiguration für Codex vor. Zeige die Dateien, die geändert würden, und frage nach, bevor versteckte Konfigurationsdateien geschrieben werden.
Remote-Bereitstellung prüfen 
Bewerte den Vibe Kanban-Plan für Remote-Bereitstellung für dieses Team. Identifiziere Netzwerkfreigabe, Umgang mit Secrets, Docker-Risiken und sichere Alternativen, bevor Bereitstellungsschritte erfolgen.

Bewährte Praktiken

  • Jede Vibe Kanban-Karte klein genug halten, um sie als einen Pull Request reviewen zu können.
  • Diffs, Logs und Testergebnisse prüfen, bevor Agent-Arbeit nach Done verschoben oder ein Pull Request gemergt wird.
  • Remote-Modus, Docker-Bereitstellung und MCP-Konfigurationsänderungen nur nach ausdrücklicher menschlicher Freigabe vornehmen.

Vermeiden

  • Nicht mehrere breit angelegte Agenten ohne Worktree-Isolierung auf dieselben Dateien ansetzen.
  • Den Vibe Kanban-Remote-Modus nicht mit geladenen Secrets untrusted networks aussetzen.
  • Host-Docker-Socket nicht mounten und versteckte Agent-Konfigurationen nicht ohne Sicherheitsprüfung schreiben.

Häufig gestellte Fragen

Installiert dieser Skill Vibe Kanban selbstständig?
Nein. Er bietet Einrichtungsanleitung und Skripte, die das externe Vibe Kanban-Paket und lokale Agent-CLIs verwenden.
Welche KI-Tools werden abgedeckt?
Die Dokumentation behandelt Claude, Codex, Claude Code, OpenCode, Gemini und mehrere von Vibe Kanban unterstützte Agenten.
Kann er Pull Requests erstellen?
Er beschreibt den Vibe Kanban-Workflow für Draft Pull Requests, wenn die GitHub-Integration konfiguriert ist.
Ist Remote-Bereitstellung standardmäßig sicher?
Nein. Remote-Modus, CORS, Secrets und Docker-Konfiguration sollten geprüft werden, bevor ein Board freigegeben wird.
Schützt er API-Keys?
Nein. Benutzer müssen API-Keys sorgfältig verwalten und vermeiden, sie auszugeben, in unsicheren Dateien zu speichern oder untrusted containers offenzulegen.
Kann ich es ohne MCP verwenden?
Ja. Das Board kann über die Browser-UI genutzt werden, während MCP eine optionale Agent-Integration ist.

Entwicklerdetails

Lizenz

MIT

Autorenversion

v1.2.0

Skillstore-Revision

r1

Repository

https://github.com/supercent-io/skills-template/tree/main/.agent-skills/vibe-kanban/

Ref.

36e07d5e13068e5be64447e8f20b427cf2cbd21a

Aktualität der Wartung

28.7.2026

Nutzung

9 Downloads · 192 Aufrufe

Dateistruktur

📁 references/

📄 environment-variables.md

📄 mcp-api.md

📁 scripts/

📄 cleanup.sh

📄 health-check.sh

📄 mcp-setup.sh

📄 start.sh

📁 templates/

📄 claude-mcp-config.json

📄 docker-compose.yml

📄 SKILL.md

📄 SKILL.toon