Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/Rheinmir/setupnpx agentmods add skills/rheinmir/setup/dym-ruflo-initWrote 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/rheinmir/setup/dym-ruflo-init)<a href="https://agentmods.dev/skills/rheinmir/setup/dym-ruflo-init"><img src="https://agentmods.dev/badge/skills/rheinmir/setup/dym-ruflo-init/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/rheinmir/setup/dym-ruflo-init"><img src="https://agentmods.dev/badge/skills/rheinmir/setup/dym-ruflo-init.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 | $0.00063 | $0.00908 |
| Opus 5.5 | $0.00025 | $0.00363 |
| Sonnet 5.5 | $0.00013 | $0.00182 |
| Haiku 4.5 | $0.00006 | $0.00091 |
Grade A, and why
dym-ruflo-init 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.
How it starts
The opening of the file, as written. The whole thing — 62 lines — stays where its author put it; the contents beside it link to each section on GitHub.
dym-ruflo-init
When to use
- Trước khi gõ
ruflo initvào bất kỳ dự án đang có.claude/— nhất là dự án dùng overstack. - Cần biết chính xác cái gì bị ghi đè để quyết định có cách ly được không.
Steps
- Luôn init vào dự án RỖNG trong hộp cát trước, không init thẳng dự án thật:
mkdir -p ./scratchpad/ruflo-proj && cd ./scratchpad/ruflo-proj && git init -q .
HOME=<sandbox-home> <prefix>/bin/ruflo init --no-signup
- Đo dấu chân — số đo thật 2026-09-10,
[email protected], dự án git rỗng:
| ghi vào | số lượng |
|---|---|
.claude/ tổng |
241 file · 6.0 MB |
.claude/commands/ |
148 file (slash command) |
.claude/helpers/ |
44 file |
.claude/skills/ |
30 skill |
.claude/agents/ |
18 agent |
.claude-flow/ |
8 file (config.yaml, CAPABILITIES.md, data/logs/sessions) |
.gitignore |
thêm khối "Ruflo local secrets and runtime data" |
- Đo phần CHIẾM
settings.json— đây mới là chỗ đau:
python3 -c "import json;d=json.load(open('.claude/settings.json'));print({k:len(v) for k,v in d['hooks'].items()});print([k for k in d if k!='hooks'])"
Kết quả đo: hook 13 đăng ký trên 10 loại — PreToolUse 2 · PostToolUse 2 ·
UserPromptSubmit 1 · SessionStart 1 · SessionEnd 1 · Stop 1 · PreCompact 2 ·
SubagentStart 1 · SubagentStop 1 · Notification 1. Ngoài hooks còn ghi
statusLine, permissions, model (ghim claude-sonnet-5), env, claudeFlow.
- Muốn chỉ lấy runtime, không đụng
.claude/:--skip-claude.
ruflo init --minimal --skip-claude --no-signup
Đo: .claude/ chỉ còn 4 thư mục RỖNG (0 file), không có settings.json, tổng 108 KB.
Rules
--skip-claudenói dối ở phần thông báo: init vẫn in[INFO] Hooks: 4 hook types enabled in settings.jsontrong khi không cósettings.jsonnào được tạo. Đừng tin dòng đó, đifind/git statusmà kiểm.- Init không hỏi trước khi ghi đè
statusLine/model/permissions. Dự án nào đã có statusline hoặc đã ghim model khác thì mất, không có prompt. - 30 skill của ruflo không trùng tên với 86 skill overstack và 8 skill Orca.app quản
(đã đối chiếu bằng
comm) — rủi ro không nằm ở tên skill mà ởsettings.json. - Luôn
git statusngay sau init:.gitignorebị sửa và 241 file mới là thứ phải quyết commit hay không, đừng để lẫn vào commit khác.
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.
- yesterday First seen · 62 lines · 63 tokens per session scan A 19de31e81867
dym-ruflo-init is a skill published in the GitHub repository Rheinmir/setup (11 stars, last pushed 20d ago), licensed MIT. It adds 63 tokens to every session and 908 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.
dym-ruflo-init compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| dym-ruflo-initRheinmir/setup | Skill | 11 | 20d ago | MIT | A | 63 | Claude Code |
| merge-batchdiegosouzapw/OmniRoute | Skill | 85k | today | MIT | A | 46 | Claude Code |
| prowler-commitprowler-cloud/prowler | Skill | 15k | yesterday | Apache-2.0 | A | 44 | Claude Code, Codex |
| gh-auth-isolationgithub/gh-aw | Skill | 5.6k | today | MIT | A | 20 | Claude Code, Codex |
| comet-githubrpamis/comet | Skill | 3.3k | today | MIT | A | 72 | Claude Code, Codex |
| github-skillzeenie-ai/OpenCompany | Skill | 1.1k | 3d ago | MIT | A | 51 | Claude Code |
| re0-mergeLilMGenius/paperthin | Skill | 1.4k | today | MIT | A | 70 | Claude Code |