A BlueKiwi tool for finding a running task and continuing it from its current step.

Use it when you want to continue an active task, including by saying “next” or “continue.”

It lets you resume interrupted workflow work without starting over or locating the task manually.

bk-next — Skill for Claude Code by dandacompany

Install

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.

Any agent

npx skills add dandacompany/bluekiwi --skill bk-next

Clone the repo

git clone --depth 1 https://github.com/dandacompany/bluekiwi

Made for: Claude Code.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/dandacompany/bluekiwi/bk-next/github.svg)](https://agentmods.dev/skills/dandacompany/bluekiwi/bk-next)

Your own site

<a href="https://agentmods.dev/skills/dandacompany/bluekiwi/bk-next"><img src="https://agentmods.dev/badge/skills/dandacompany/bluekiwi/bk-next/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/dandacompany/bluekiwi/bk-next"><img src="https://agentmods.dev/badge/skills/dandacompany/bluekiwi/bk-next.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 69 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 2,700 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

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	$0.00069	$0.02700
Opus 5	$0.00034	$0.01350
Sonnet 5	$0.00014	$0.00540
Haiku 4.5	$0.00007	$0.00270

Measured 9d ago against content hash a16d1dc05385, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

bk-next 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.

packages/cli/src/assets/skills/bk-next/SKILL.md · 266 lines

How it starts

The opening of the file, as written. The whole thing — 266 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Asking questions across runtimes: wherever this skill says AskUserQuestion, use your host runtime's native structured-question tool: AskUserQuestion (Claude Code), clarify (Hermes Agent), requestUserInput (Codex CLI), question (opencode). Always present the choices through that tool rather than plain prose. If the runtime has no such tool, list the options as numbered text and wait for the user's reply before proceeding.

BlueKiwi Next Step

Find a running task and resume execution from the current step — designed to absorb natural-language continuation intents ("이어서", "계속", "next", "proceed") without forcing the user to remember the slash command.

Use /bk-next when: there is at least one running task and the user wants to continue it. Use /bk-start when: starting a new workflow, picking from multiple candidates, or resuming a specific task by ID (/bk-start #123).

Core Principles

Shared with bk-start. Summary:

Instructions are internal directives — never echo raw instruction text to the user. Show only results (analysis, questions, suggestions).
Refer to steps as "step". Never expose "node", "node_type", etc.

Natural Language Triggers

If the user says "proceed", "next", "continue", "let's go", "OK", "go ahead", "이어서", "계속" — treat it the same as /bk-next.

Step 0 — Find the Active Task

Call list_tasks(status=running).
If exactly one running task exists → use it directly.
If multiple running tasks exist → ask via AskUserQuestion:
- header: "태스크 선택"
- preview: list of tasks formatted as "Task #{id} — {workflow_name} (Step {current_step}/{total_steps})"
- options: up to 4 task entries (most recent first)
If no running tasks → call list_tasks(status=timed_out) and check for timed-out tasks.
- If found → ask: "이어서 진행할 태스크가 없습니다. 타임아웃된 태스크를 재개할까요?" (options: 가장 최근 재개 / 취소)
- If none → tell the user "실행 중인 태스크가 없습니다. /bk-start로 새 워크플로를 시작하세요."

Read the full file on GitHub · 266 lines

Changes

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 · 266 lines · 69 tokens per session scan A a16d1dc05385

Subscribe to this mod's changes

bk-next is a skill published in the GitHub repository dandacompany/bluekiwi (23 stars, last pushed 1mo ago), licensed MIT. It adds 69 tokens to every session and 2,700 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 2026-08-30.

Productivity

orbit-notion

Open Orbit briefing skill — selected by the Orbit pipeline when Notion is the user's only connected connector, or when the user explicitly scopes their daily digest to Notion. Pulls the past 24 hours of document edits, comments, mentions, and database row changes from the user's authenticated Notion connection and…

nexu-io/open-design · 117 tokens

Cortex

Operate Cortex, the LifeOS memory system — the typed Knowledge Archive (People, Companies, Ideas, Research with typed related: links) plus recall of prior work sessions, ISAs, and conversations. Search, add, harvest, develop, ingest, distill, graph-navigate, recall. USE WHEN cortex, knowledge, knowledge base, search…

danielmiessler/LifeOS · 196 tokens

pinchtab-mcp

Use this skill when a task requires browser automation through PinchTab's MCP server connected to a remote browser instance. Covers navigation, element interaction, data extraction, form filling, multi-step flows, and session management via MCP tools.

pinchtab/pinchtab · 52 tokens

bk-next