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-import-kanbangit 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-import-kanban)<a href="https://agentmods.dev/skills/oai-labs/vibe-flow/vibe-import-kanban"><img src="https://agentmods.dev/badge/skills/oai-labs/vibe-flow/vibe-import-kanban/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-import-kanban"><img src="https://agentmods.dev/badge/skills/oai-labs/vibe-flow/vibe-import-kanban.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 | $0.00065 | $0.01303 |
| Opus 5 | $0.00032 | $0.00651 |
| Sonnet 5 | $0.00013 | $0.00261 |
| Haiku 4.5 | $0.00006 | $0.00130 |
Grade A, and why
vibe-import-kanban 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 — 123 lines — stays where its author put it; the contents beside it link to each section on GitHub.
vibe-import-kanban
Overview
One-way snapshot from vibe-kanban to a local plan file. Does not modify kanban state. The resulting plan-local.json is the input for vibe-ship-fast; the preserved kanban_id / simple_id per issue let vibe-export-kanban post the merge result back to the right issue after the final PR lands.
Core principle: Snapshot, don't subscribe. No polling, no two-way sync, no live updates. If kanban changes mid-flight, the local plan is stale by design — re-import if you need to.
Announce at start: "I'm using the vibe-import-kanban skill to snapshot issues."
When to use
- Issues already exist in vibe-kanban (created by you, a teammate, or
vibe-planwithout--local) - You want
vibe-ship-fast's local workflow (one PR at the end) but still want the kanban board to reflect "done" later - Solo run on a shared project
Do NOT use if:
- Issues don't exist yet →
vibe-plan --local(skip kanban entirely) - You want per-issue PRs and per-PR review on GitHub →
vibe-ship(no import needed) - A
.vibe-flow/plan-local.jsonfrom this run already exists → either resumevibe-ship-fastor delete the file first
The process
Step 1: Resolve scope
Read .vibe-flow.yaml for project_id. If $ARGUMENTS overrides, use that.
Ask the user (or take from $ARGUMENTS) which subset:
- All open issues in the project
- Issues with a specific tag (e.g.,
sprint:q2) - A parent issue's sub-tree
- Explicit list of
simple_ids
Step 2: Pull from kanban
Use MCP:
list_issues(project_id, status_filter, tag_filter)for the candidate set- For each candidate:
get_issue(issue_id)for the full description and tags list_issue_relationships(issue_id)to captureblocks/blocked_byedges
Do NOT issue any write call. This skill is read-only against kanban.
Step 3: Map to local schema
For each kanban issue, build:
{
"id": "L<n>",
"title": "<kanban title>",
"description": "<kanban description, verbatim>",
"tier": "<read from tag tier:t0..t4, fallback T2>",
"depends_on": ["L<m>", "..."],
"tags": ["<kanban tags except tier:* and the internal vibe-flow ones>"],
"brainstorm": "<from tag brainstorm:interactive|autonomous, else null>",
"files_hint": [],
"kanban_id": "<issue_id>",
"simple_id": "<simple_id>"
}
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 · 123 lines · 65 tokens per session scan A f1974271f46d
vibe-import-kanban is a skill published in the GitHub repository OAI-Labs/vibe-flow (1 stars, last pushed 1mo ago), licensed MIT. It adds 65 tokens to every session and 1,303 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
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.