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.
npx skills add OAI-Labs/vibe-flow --skill vibe-initgit clone --depth 1 https://github.com/OAI-Labs/vibe-flowWrote 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.
[](https://agentmods.dev/skills/oai-labs/vibe-flow/vibe-init)<a href="https://agentmods.dev/skills/oai-labs/vibe-flow/vibe-init"><img src="https://agentmods.dev/badge/skills/oai-labs/vibe-flow/vibe-init/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.
<a href="https://agentmods.dev/skills/oai-labs/vibe-flow/vibe-init"><img src="https://agentmods.dev/badge/skills/oai-labs/vibe-flow/vibe-init.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00056 | $0.01501 |
| Opus 5 | $0.00028 | $0.00750 |
| Sonnet 5 | $0.00011 | $0.00300 |
| Haiku 4.5 | $0.00006 | $0.00150 |
Grade A, and why
vibe-init 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 9d 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.
How it starts
The opening of the file, as written. The whole thing — 174 lines — stays where its author put it; the contents beside it link to each section on GitHub.
vibe-init
Overview
One-shot setup for a repo that will use vibe-flow. Replaces the manual "copy .vibe-flow.example.yaml, hunt for project_id, create state dir" dance. Asks only what's needed — nothing else.
Core principle: One required answer (which project). Everything else has defaults.
Announce at start: "I'm using the vibe-init skill to set up vibe-flow for this repo."
When to use
- User says "set up vibe-flow", "init vibe-flow", or runs
/vibe-flow:vibe-init - First time using vibe-flow in a repo (no
.vibe-flow.yamlpresent) - User wants to reconfigure (re-run to re-pick project / edit defaults)
Do NOT use if:
.vibe-flow.yamlalready exists AND user hasn't asked to reconfigure — skip with a note- Not inside a git repo — bail and ask user to
git initfirst vibe-kanbanMCP not connected — bail and point at README "MCP setup"
The process
Step 1: Preflight
# Must be in a git repo
git rev-parse --show-toplevel
Verify MCP:
- Call
list_organizations. If it errors → stop, tell user MCP isn't reachable, point to README.
Check idempotency:
- If
.vibe-flow.yamlexists → ASK: "Config already present. Reconfigure, show current, or cancel?" - If cancel → exit cleanly.
Step 2: Ask the minimum
Q1 (required): Project.
Call list_projects. Show a numbered list of name — project_id. User picks one.
Do NOT ask the user to paste an ID. Always offer selection.
Q2 (optional, one prompt): Concurrency + budget. Offer defaults inline; accept Enter to keep them:
max_parallel [5]:
cost_budget_usd [50]:
wave_barrier [merge / pr-open] (default: merge):
Q3 (optional): Notifications.
Slack webhook (Enter to skip):
Discord webhook (Enter to skip):
Q4 (optional): ready_to_merge column.
vibe-kanban ships with todo / in_progress / in_review / done by default but projects can add custom columns. MCP does NOT expose a way to create columns — if the user wants this one, they must add it themselves in vibe-kanban UI → Project Settings → Statuses first.
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.
- 9d ago First seen · 174 lines · 56 tokens per session scan A cf7dc318823a
vibe-init is a skill published in the GitHub repository OAI-Labs/vibe-flow (1 stars, last pushed 1mo ago), licensed MIT. It adds 56 tokens to every session and 1,501 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.
Other skills, from other repositories
implement
Use when implementing a spec or GitHub ticket in this checkout.
loop-on-ci
Monitor PR checks and fix failures until green. Uses gh pr checks as the source of truth for PR-attached checks.
run-smoke-tests
Run Playwright smoke tests, debug failures, and verify fixes. Use for smoke, e2e, Playwright, or pre-ship browser verification.
browser-use
Drive a real browser to QA a running app. Screenshots, clicks, forms, evidence. Use when there is no Playwright suite, or when a human flow must be walked.
tdd
Use when implementing features or bug fixes test-first.
to-tickets
Use when breaking a plan into tracer-bullet GitHub issues with blocking edges.