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-ship-fastgit 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-ship-fast)<a href="https://agentmods.dev/skills/oai-labs/vibe-flow/vibe-ship-fast"><img src="https://agentmods.dev/badge/skills/oai-labs/vibe-flow/vibe-ship-fast/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-ship-fast"><img src="https://agentmods.dev/badge/skills/oai-labs/vibe-flow/vibe-ship-fast.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 | $0.00058 | $0.02659 |
| Opus 5 | $0.00029 | $0.01329 |
| Sonnet 5 | $0.00012 | $0.00532 |
| Haiku 4.5 | $0.00006 | $0.00266 |
Grade A, and why
vibe-ship-fast 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 11d 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 — 282 lines — stays where its author put it; the contents beside it link to each section on GitHub.
vibe-ship-fast
Overview
Local-mode dispatch. No vibe-kanban API, no per-feature PR. Sub-agents work in git worktrees off a single integration branch (dev-wave-<ts>), waves merge locally, one PR opens to main at the end.
Core principle: Same wave/DAG model as vibe-ship, but every API call goes to the local git tree and the Agent tool. Cheap when you don't need kanban tracking — quick prototypes, solo runs, offline work.
Announce at start: "I'm using the vibe-ship-fast skill (local mode)."
When to use
.vibe-flow/plan-local.jsonexists (fromvibe-plan --local) OR user passes a spec inline- No need for vibe-kanban tracking on this run
- User wants one PR at the end, not one-per-issue
Do NOT use if:
- Run is already tracked in vibe-kanban → use
vibe-ship - User explicitly wants per-feature PRs and review-on-GitHub → use
vibe-ship - Spec is one trivial change → just do it inline
Required references
references/executor-routing.md— tier triage (subagent_type mapping below)references/wave-scheduler.md— DAG → wave algorithmreferences/prompt-templates.md— closing protocol (still injected into each subagent)
Tier → subagent_type mapping
Local mode uses the Agent tool, not VK executors. Default mapping:
| Tier | Agent subagent_type | Model override |
|---|---|---|
| T0 | general-purpose | haiku |
| T1 | general-purpose | sonnet |
| T2 | general-purpose | sonnet |
| T3 | general-purpose | opus |
| T4 | vibe-flow:vibe-explorer (per approach, N=3) then general-purpose with winner | opus |
Override via .vibe-flow.yaml → local.tier_agents.
The process
Step 1: Load plan + config
- Read
.vibe-flow.yaml. Apply defaults. - Read
.vibe-flow/plan-local.json. If missing AND$ARGUMENTShas a spec → invokevibe-plan --localfirst, then continue. - Check
.vibe-flow/state-local.json:- Has incomplete run → resume: skip already-merged issues, re-dispatch failed
- Else → fresh
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.
- 11d ago First seen · 282 lines · 58 tokens per session scan A d27c36951d5e
vibe-ship-fast is a skill published in the GitHub repository OAI-Labs/vibe-flow (1 stars, last pushed 1mo ago), licensed MIT. It adds 58 tokens to every session and 2,659 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
loop-on-ci
Monitor PR checks and fix failures until green. Uses gh pr checks as the source of truth for PR-attached checks.
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.
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.
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.
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…
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.