vibe-link

vibe-link is a skill for Claude Code from OAI-Labs/vibe-flow. It costs 41 tokens per session (1,873 once invoked), scanned A, original, MIT.

A workflow tool that connects a completed Vibe Kanban workspace and its pushed Git branch to a GitHub pull request. Vibe Kanban is a system for coordinating coding tasks, while a pull request is a proposed code change for review.

In plain words
What is it for?
Use it after a workspace finishes to find or create its GitHub pull request, add the link to the related issue, and synchronize the pull request status.
Why use it?
It keeps the workspace, branch, pull request, and issue connected, so developers do not have to link them manually or lose track of completed work.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

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

Good fit Use it after a workspace finishes to find or create its GitHub pull request, add the link to the related issue, and synchronize the pull request status.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/oai-labs/vibe-flow/vibe-link
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-link
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-link

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/oai-labs/vibe-flow/vibe-link"><img src="https://agentmods.dev/badge/skills/oai-labs/vibe-flow/vibe-link.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 41 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,873 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 $0.00041 $0.01873
Opus 5 $0.00020 $0.00937
Sonnet 5 $0.00008 $0.00375
Haiku 4.5 $0.00004 $0.00187

Measured 12d ago against content hash 111b5a4629c2, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

vibe-link 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 12d 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-link/SKILL.md · 248 lines

How it starts

The opening of the file, as written. The whole thing — 248 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Overview

Bridge between vibe-kanban workspace output (a pushed branch) and GitHub pull requests. Ensures every completed workspace has a tracked PR, and the issue comments reference it.

Core principle: One workspace → one branch → one PR → one issue. Keep the graph tight.

Announce at start: "I'm using the vibe-link skill to link PR to workspace."

When to use

  • A workspace just reported status: complete with a branch pushed
  • User explicitly invokes /vibe-flow:vibe-link <workspace_id>
  • Auto-triggered by vibe-ship after each workspace completes

Do NOT use if:

  • Workspace is still running (wait for FINAL REPORT)
  • Workspace reported status: blocked (no branch pushed)
  • Branch already has a PR that's linked in issue comments (idempotent skip)

Required context

  • workspace_id from vibe-kanban
  • Repo path on disk (to run gh commands)
  • gh CLI authenticated with repo access

The process

Step 1: Fetch workspace info

Call MCP get_execution or list_sessions for the workspace. Extract:

  • branchprefer the value from the agent's FINAL REPORT. VK workspace metadata also exposes a "working branch" field, but it is VK's internal auto-generated name (sometimes truncated in the UI) and is NOT guaranteed to equal the actual branch the agent pushed to origin. Trust the FINAL REPORT first; fall back to VK metadata only if FINAL REPORT is missing.
  • issue_id (from workspace link)
  • commit_sha (from FINAL REPORT)

Verify branch exists on origin:

git fetch origin
git ls-remote --heads origin <BRANCH_NAME>

If branch not on origin:

  • If FINAL REPORT was the source → STOP, workspace didn't push. Mark push_missing, alert user.
  • If VK metadata was the source (FINAL REPORT missing) → flag branch_mismatch and ask the user to inspect; do NOT silently try the truncated working branch name.

Record the verified branch into state.json[issue].branch so downstream skills (vibe-status, vibe-merge) have a single canonical value.

Read the full file on GitHub · 248 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. 12d ago First seen · 248 lines · 41 tokens per session scan A 111b5a4629c2

Subscribe to this mod's changes

vibe-link is a skill published in the GitHub repository OAI-Labs/vibe-flow (1 stars, last pushed 1mo ago), licensed MIT. It adds 41 tokens to every session and 1,873 once invoked, about $0.0002 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

loop-on-ci

Monitor PR checks and fix failures until green. Uses gh pr checks as the source of truth for PR-attached checks.

Kripu77/software-factory · 28 tokens

pr-watch

Local PR watcher. Monitors CI status, automatically fixes failing checks by reading failure logs and applying targeted fixes, then optionally merges when all checks pass. Local CLI analog to Claude Code's cloud auto-fix feature.

SethGammon/Citadel · 46 tokens

deploy-steward

Mainline deploy steward. Consumes ready PRs, owns a lease on mainline landing, refreshes PR state, updates stale branches, waits for CI and deploy gates, merges or queues one candidate at a time, and opens repair tasks for failures.

SethGammon/Citadel · 56 tokens

merge-review

Reviews pending fleet worktree merges before they're accepted. Reads the merge-check queue, detects file-level conflicts between branches, proposes a safe merge order, and surfaces reconciliation plans for overlapping changes.

SethGammon/Citadel · 40 tokens

branch-and-worktree-workflow

Isolates feature work in its own branch or worktree and integrates it cleanly when done. Use this when starting work that should not disturb the current workspace, when several efforts must proceed in parallel on one repository, or when implementation is finished and the change needs merging, rebasing, or splitting…

cbrock84/headcount · 70 tokens

pr-feedback

Work a reviewer's comments on a pull request to the end - all three comment surfaces enumerated before any is triaged, every comment fixed, declined with a reason, or ticketed, push before you reply. Use when a PR comes back with review feedback or a red check.

jjanczur/tyran · 57 tokens