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-shipgit 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)<a href="https://agentmods.dev/skills/oai-labs/vibe-flow/vibe-ship"><img src="https://agentmods.dev/badge/skills/oai-labs/vibe-flow/vibe-ship/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"><img src="https://agentmods.dev/badge/skills/oai-labs/vibe-flow/vibe-ship.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 | $0.00046 | $0.02418 |
| Opus 5 | $0.00023 | $0.01209 |
| Sonnet 5 | $0.00009 | $0.00484 |
| Haiku 4.5 | $0.00005 | $0.00242 |
Grade A, and why
vibe-ship 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.
How it starts
The opening of the file, as written. The whole thing — 247 lines — stays where its author put it; the contents beside it link to each section on GitHub.
vibe-ship
Overview
Wave-based parallel dispatch for vibe-kanban issues. Route each issue to the cheapest executor that can plausibly solve it, run waves in parallel, barrier between waves.
Core principle: Cheap first, escalate on failure. Barrier between waves, never between issues within a wave.
Announce at start: "I'm using the vibe-ship skill to dispatch issues."
When to use
- User has issues in a vibe-kanban project ready to work on (from
vibe-planor manually created) - User wants agents to actually do the work, not just plan
- Multiple issues with or without dependencies
Do NOT use if:
- Issues don't exist yet → use
vibe-planfirst - User wants to manually pick one issue → use
start_workspacedirectly via MCP - Running in a subagent that was dispatched by
vibe-shipitself
Required references
Load before dispatching:
references/executor-routing.md— tier triage + fallback chainreferences/prompt-templates.md— closing protocol (MUST inject into every workspace)references/wave-scheduler.md— DAG algorithm + state persistence
The process
Step 1: Load config and state
- Read
.vibe-flow.yamlat repo root. Apply defaults if missing. - Check
.vibe-flow/state.json:- If exists and has incomplete run → resume mode: reconcile and continue from last consistent state
- Else → fresh mode: start new run
Step 2: Determine scope
Ask user (or use $ARGUMENTS):
- Which issues to ship? Options:
- All open issues in project
- Issues matching a tag (e.g.,
sprint:q2) - Specific issue IDs / simple_ids
- A parent issue's sub-tree
Use list_issues with filters. Fetch relationships for each to build DAG.
Step 3: Build DAG and waves
Follow references/wave-scheduler.md step 1-2.
Present to user:
Wave plan (N waves, M total issues):
Wave 0 (<count> issues, parallel):
- [T0 gemini-flash] A20K-1: Remove AI Literacy column
- [T2 sonnet-high] A20K-3: Add pagination to /dashboard
- [T1 sonnet-medium] A20K-4: Refactor login form
Wave 1 (<count> issues, parallel, waits on Wave 0):
- [T3 opus] A20K-5: Migrate auth to OIDC (blocked by A20K-4)
Estimated cost: $<X>
Max opus in single wave: <N>
Barrier mode: merge
Proceed? (yes / modify / abort)
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 10d ago First seen · 247 lines · 46 tokens per session scan A 73dac42db40d
vibe-ship is a skill published in the GitHub repository OAI-Labs/vibe-flow (1 stars, last pushed 1mo ago), licensed MIT. It adds 46 tokens to every session and 2,418 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.
Other skills, from other repositories
lead
Use when acting as the factory tech lead: classify work, ask the minimum questions, create tickets, and dispatch without implementing.
to-tickets
Use when breaking a plan into tracer-bullet GitHub issues with blocking edges.
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.
workspace
Multi-repo campaign coordinator. Same lifecycle as fleet -- scope claims, discovery relay, wave-based execution -- but the unit of work is a repo, not a file. Coordinates campaigns across repositories with shared context.
decision-map
Turn a loose idea into a git-tracked, session-resumable map of typed investigation tickets, then drive them to resolution one at a time. The planning-loop engine for work that is still being figured out — too fuzzy for a campaign, too big for a single intake item. Resolved tickets graduate into .planning/intake/ for…
unharness
Safely leave Citadel using the active adoption receipt. Produces a no-write, reviewable plan, preserves a portable archive, removes only exact owned material, and reports modified or externally registered surfaces as retained or unknown. Legacy installs must be imported before exact leave is claimed.