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-plangit 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-plan)<a href="https://agentmods.dev/skills/oai-labs/vibe-flow/vibe-plan"><img src="https://agentmods.dev/badge/skills/oai-labs/vibe-flow/vibe-plan/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-plan"><img src="https://agentmods.dev/badge/skills/oai-labs/vibe-flow/vibe-plan.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 | $0.00083 | $0.02586 |
| Opus 5 | $0.00042 | $0.01293 |
| Sonnet 5 | $0.00017 | $0.00517 |
| Haiku 4.5 | $0.00008 | $0.00259 |
Grade A, and why
vibe-plan 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 — 311 lines — stays where its author put it; the contents beside it link to each section on GitHub.
vibe-plan
Overview
Turn a spec into an executable issue tree in vibe-kanban. Each leaf issue is atomic, testable, and independently dispatchable. Dependencies form the wave structure.
Core principle: Atomic leaves + explicit dependencies = clean parallelization downstream.
Announce at start: "I'm using the vibe-plan skill to decompose the spec."
When to use
- User has a spec, feature doc, or high-level requirement
- User wants multiple related tasks, not just one
- Before
vibe-ship— you need issues to ship
Do NOT use if:
- User wants a single small change (just
create_issuedirectly) - Spec is one paragraph and clearly atomic (one issue is enough)
- User already created issues manually
Required references
references/executor-routing.md— for tier estimationreferences/prompt-templates.md— for T4 brainstorm prompts
The process
Step 1: Understand the spec
Ask user if unclear:
- What's the end goal? (outcome, not output)
- What's in scope? Out of scope?
- Any constraints (tech stack, deadline, compatibility)?
- Which repo(s) does this touch?
- Which vibe-kanban project to put issues in?
Single-issue short-circuit. Skip full planning and just create_issue directly if ANY of these apply:
- Fewer than 2 distinct acceptance criteria can be stated
- Estimated total change ≤ 30 LOC
- Touches only 1 file and no cross-file dependencies are stated
Char count alone is a weak proxy — prefer the criteria above. The goal is to avoid orchestration overhead (workspace setup + review + CI) exceeding the work itself.
Step 2: Decompose into atomic tasks
Apply superpowers:writing-plans principles:
- Each task = one deliverable (2-5 min for T0, scaling up)
- Each task testable independently
- Each task has clear acceptance criteria
Group into:
- Epic (optional, 1 issue): overarching feature
- Stories (1 issue each): independent pieces under the epic
- Sub-tasks (optional): further breakdown if a story is too big
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 · 311 lines · 83 tokens per session scan A e64beaf9a1b1
vibe-plan is a skill published in the GitHub repository OAI-Labs/vibe-flow (1 stars, last pushed 1mo ago), licensed MIT. It adds 83 tokens to every session and 2,586 once invoked, about $0.0004 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.