agentmods.dev

dym-ruflo-route

dym-ruflo-route is a skill for Claude Code from Rheinmir/setup. It costs 75 tokens per session (801 once invoked), scanned A, original, MIT.

A decision guide for choosing how to run several coding agents. It compares tools for parallel work in one session, across multiple command-line sessions, or through a simple task runner.

In plain words
What is it for?
Use it when deciding whether to use ruflo, herdr, Orca, or a plain task tool for parallel agent work.
Why use it?
It helps avoid installing a large coordinator when a basic task tool or parallel command is enough, and warns about files and settings that a coordinator may overwrite.

Skill for Claude Code

Written for Claude Code: disable-model-invocation in frontmatter. Also seen: mentions CLAUDE.md; mentions subagents; mentions Claude Code.

not rated 11repo 20d ago A scan 75 tokens original MIT

Good fit Use it when deciding whether to use ruflo, herdr, Orca, or a plain task tool for parallel agent work.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/rheinmir/setup/dym-ruflo-route
View source ↗ Rheinmir/setup
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 Rheinmir/setup --skill dym-ruflo-route
Clone the repo
git clone --depth 1 https://github.com/Rheinmir/setup

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.

agentmods badge for dym-ruflo-route

README.md
[![agentmods](https://agentmods.dev/badge/skills/rheinmir/setup/dym-ruflo-route/github.svg)](https://agentmods.dev/skills/rheinmir/setup/dym-ruflo-route)
Your own site
<a href="https://agentmods.dev/skills/rheinmir/setup/dym-ruflo-route"><img src="https://agentmods.dev/badge/skills/rheinmir/setup/dym-ruflo-route/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.

agentmods 80×15 button for dym-ruflo-route

Your own site · 80×15
<a href="https://agentmods.dev/skills/rheinmir/setup/dym-ruflo-route"><img src="https://agentmods.dev/badge/skills/rheinmir/setup/dym-ruflo-route.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 75 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 801 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00075 $0.00801
Opus 5.5 $0.00030 $0.00320
Sonnet 5.5 $0.00015 $0.00160
Haiku 4.5 $0.00007 $0.00080

Measured yesterday against content hash 4d9033da0830, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

dym-ruflo-route 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 yesterday.

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.

.overstack/doyourmagic/ruflo/skills/dym-ruflo-route/SKILL.md · 49 lines

How it starts

The opening of the file, as written. The whole thing — 49 lines — stays where its author put it; the contents beside it link to each section on GitHub.

dym-ruflo-route

When to use

  • Ai đó đề xuất cài ruflo/claude-flow vào dự án dùng overstack.
  • Cần điều phối nhiều agent và không chắc dùng tầng nào.

Steps

  1. Xác định việc thuộc tầng nào — 4 tầng này KHÔNG thay thế nhau:
tầng việc công cụ
trong MỘT phiên Claude Code fan-out subagent, memory chung, hook tự học ruflo (hoặc Task tool trần)
nhiều PHIÊN CLI trên một máy mỗi agent một pane, biết pane nào kẹt/xong herdr
giao việc cho CLI bất kỳ qua Orca, biết lúc xong sentinel shell + poll terminal orca-dispatch.py (của ta)
chỉ cần chạy song song rồi gom không cần gì thêm Task tool / claude -p

  1. Nếu định dùng ruflo, chạy /dym-ruflo init TRƯỚC để biết nó ghi đè gì.

  2. Verdict cho dự án overstack: KHÔNG LẤY nguyên khối.

lý do bằng chứng đo được
Chiếm .claude/ init ghi 241 file, 13 hook / 10 loại, thay statusLine · permissions · model · env — đúng những thứ overstack đang sở hữu
Không phải runtime độc lập "Never use MCP tools alone for execution — Task tool agents do the actual work" (CLAUDE.md của chính nó) — bỏ Claude Code là không còn gì chạy
Chi phí cài 1.5 GB prefix + ghi .claude-flow/ và Library/ vào $HOME
Bề mặt quá rộng để bảo trì 2280 file nguồn, 25 gói workspace, 17 nhóm lệnh, hooks.ts 211 KB · doctor.ts 113 KB

Cái đáng học, không đáng nuốt (mode HÒA TAN, chép Ý không chép code):

  • autopilot — vòng "chưa xong hết task thì đừng dừng", cắm vào Stop hook. Ta đã có Stop hook; đây là một pattern rẻ để thêm.
  • hooks route / hooks explain — định tuyến task→agent bằng pattern đã học, và giải thích được quyết định. Phần explain mới là chỗ hay.
  • swarm compress-message — nén thông điệp giữa agent về một ngân sách token.

Rules

  • Đừng chạy ruflo init trong worktree đang có overstack. Muốn thử thì dựng dự án rỗng riêng, xong xoá.
  • Đừng đọc "60+ agent, consensus, neural, vector memory" như năng lực đã kiểm chứng — lượt đo này chỉ chứng được install · init · doctor · status · help. Phần swarm/neural/ embeddings/ruvector chưa kiểm chứng.
  • Cùng một sản phẩm hai tên: npm ruflo = claude-flow, lỗi vẫn in claude-flow.

Read the full file on GitHub · 49 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.

  1. yesterday First seen · 49 lines · 75 tokens per session scan A 4d9033da0830

Subscribe to this mod's changes

dym-ruflo-route is a skill published in the GitHub repository Rheinmir/setup (11 stars, last pushed 20d ago), licensed MIT. It adds 75 tokens to every session and 801 once invoked, about $0.0003 per session on Opus 5.5. 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 2026-11-07.

Building agentsPlanning
Related

dym-ruflo-route compared with skills from other repositories

dym-ruflo-route next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
dym-ruflo-routeRheinmir/setupSkill1120d agoMITA75Claude Code
imagegenopenai/codexSkill134ktodayApache-2.0A113Codex
local-ai-agentsmicrosoft/ai-agents-for-beginnersSkill79kyesterdayMITA200Claude Code, Codex
playwright-climicrosoft/playwrightSkill100kyesterdayApache-2.0A19Claude Code
browser-automationopenclaw/openclawSkill394ktodayMITA36Claude Code
systematic-debuggingobra/superpowersSkill314k4d agoMITA21Claude Code
next-cache-components-adoptionvercel/next.jsSkill143ktodayMITA95Claude Code