vibe-status

vibe-status is a skill for Claude Code from OAI-Labs/vibe-flow. It costs 52 tokens per session (2,109 once invoked), scanned A, original, MIT.

A read-only dashboard for checking active Vibe Kanban workspaces, branches, pull requests, automated checks, and reviews. Vibe Kanban is a tool for coordinating coding work across separate workspaces.

In plain words
What is it for?
Use it to see what is running, inspect branch and pull-request status, check continuous-integration results, and investigate work that appears stuck.
Why use it?
It compares recorded workspace information with Git and GitHub so stuck or inconsistent work is easier to spot. It does not start work or change project state.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: positional $N argument.

Part of the vibe-flow plugin — 14 skills, 2 agents shipped together

Good fit Use it to see what is running, inspect branch and pull-request status, check continuous-integration results, and investigate work that appears stuck.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/oai-labs/vibe-flow/vibe-status
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 OAI-Labs/vibe-flow --skill vibe-status
Clone the repo
git clone --depth 1 https://github.com/OAI-Labs/vibe-flow

Made for: Claude Code.

Or install vibe-flow, the plugin that ships this one along with the rest of its 14 skills, 2 agents.

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 vibe-status

README.md
[![agentmods](https://agentmods.dev/badge/skills/oai-labs/vibe-flow/vibe-status/github.svg)](https://agentmods.dev/skills/oai-labs/vibe-flow/vibe-status)
Your own site
<a href="https://agentmods.dev/skills/oai-labs/vibe-flow/vibe-status"><img src="https://agentmods.dev/badge/skills/oai-labs/vibe-flow/vibe-status/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for vibe-status

Your own site · 80×15
<a href="https://agentmods.dev/skills/oai-labs/vibe-flow/vibe-status"><img src="https://agentmods.dev/badge/skills/oai-labs/vibe-flow/vibe-status.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 52 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,109 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. 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 $0.00052 $0.02109
Opus 5 $0.00026 $0.01055
Sonnet 5 $0.00010 $0.00422
Haiku 4.5 $0.00005 $0.00211

Measured 10d ago against content hash 9279b5b2386b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

vibe-status 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 10d 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.

plugins/vibe-flow/skills/vibe-status/SKILL.md · 176 lines

How it starts

The opening of the file, as written. The whole thing — 176 lines — stays where its author put it; the contents beside it link to each section on GitHub.

vibe-status

Overview

Quick read-only dashboard of active work. Reconciles state.json with live MCP + GitHub data to detect inconsistencies.

Core principle: Reality check — surface what's really happening across vibe-kanban, git, and GitHub.

Announce at start: "I'm using the vibe-status skill to check work state."

When to use

  • User asks "what's running?" / "status?" / "how's the queue?"
  • Debugging why a wave is stuck
  • Before starting new work, to see current load

This skill is read-only. It never modifies state or dispatches.

The process

Step 1: Load state.json

Read .vibe-flow/state.json. If missing → "No active run. Start with /vibe-flow:vibe-ship or /vibe-flow:vibe-plan."

Step 2: Reconcile each tracked issue

Primary source of truth is git + GitHub, not the VK MCP API. VK status calls have been flaky, so derive workspace state from observable branch activity instead. VK MCP is a soft check — used if it responds quickly, ignored on error/timeout.

Branch naming — critical gotcha. Vibe-kanban auto-creates an internal "working branch" per workspace (visible in VK workspace metadata, sometimes shown truncated in the UI). This is NOT the same as the actual git branch the agent pushed to origin. Always use the branch reported in the agent's FINAL REPORT (recorded by vibe-link into state.json[issue].branch) as canonical. The VK working branch may be: (a) truncated, (b) prefixed differently, or (c) absent on origin entirely if the agent renamed it before push. If state.json[issue].branch fails git ls-remote, do NOT silently fall back to VK's working branch — flag branch_mismatch and let the user inspect.

For each issue in state.json (each has a recorded branch field from vibe-link, sourced from the FINAL REPORT — this is the actual pushed git branch, not VK's working branch):

A. git fetch origin <branch> --quiet  (single ref, fast)
B. git ls-remote origin refs/heads/<branch> → exists? remote SHA?
C. If branch exists:
     git log --format="%H %ct %an %s" origin/main..origin/<branch>
       → commit count, last commit time, last author, last subject
D. gh pr list --head <branch> --json number,state,mergeable,statusCheckRollup,reviewDecision
     → PR state, CI, review decision (-- if no PR)
E. SOFT: try get_issue(issue_id) with short timeout (~3s). On success, cross-check
     against derived state and flag drift. On error/timeout, skip silently.
F. Derive workspace state from B/C/D — see rules below.

Read the full file on GitHub · 176 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. 10d ago First seen · 176 lines · 52 tokens per session scan A 9279b5b2386b

Subscribe to this mod's changes

vibe-status is a skill published in the GitHub repository OAI-Labs/vibe-flow (1 stars, last pushed 1mo ago), licensed MIT. It adds 52 tokens to every session and 2,109 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 2026-08-31.

Related

Other skills, from other repositories