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 lidicn/AutoFlow --skill skillgit clone --depth 1 https://github.com/lidicn/AutoFlowWrote 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/lidicn/autoflow/skill)<a href="https://agentmods.dev/skills/lidicn/autoflow/skill"><img src="https://agentmods.dev/badge/skills/lidicn/autoflow/skill/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/lidicn/autoflow/skill"><img src="https://agentmods.dev/badge/skills/lidicn/autoflow/skill.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 | $0.00067 | $0.02642 |
| Opus 5.5 | $0.00027 | $0.01057 |
| Sonnet 5.5 | $0.00013 | $0.00528 |
| Haiku 4.5 | $0.00007 | $0.00264 |
Grade A, and why
autoflow-core 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 1mo 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 — 190 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AutoFlow Core / Pro（核心版 / 专业版）
你（agent）通过本 skill 获得对 Node-RED 实例的安全编程能力：读取、编写、修改、验证 flow。
所有写入经 scripts/nr_client.py（纯标准库，无 pip 依赖），自带护栏：写前快照、
结构 lint、节点数熔断、prod 闸、操作日志、回读校验。
⭐ 两种模式（优先用 Pro 网关模式）
| 模式 | 命令前缀 | 特点 | 推荐场景 |
|---|---|---|---|
| Pro（网关模式） ★推荐 | nr_client.py --gateway ... |
DSL 优先，省 5-10 倍 token，有编译闸门和快照，对话即部署 | 99% 日常场景 |
| Core（直连模式） | nr_client.py ... |
直连 NR 写 JSON，无网关，无编译校验 | 离线/网关不可用/极端定制 |
默认用 Pro 网关模式。 只有网关不可用或 DSL 确实表达不了时才用 Core 直连模式。
🚀 Pro 网关模式（首选）
配置
配置文件 ~/.autoflow-core/config.json 增加：
{
"gateway_url": "http://<gateway-host>:8000",
"api_key": "af_pro_xxxxxx",
"agent_id": "my-agent"
}
或环境变量：AF_GATEWAY_URL、AF_API_KEY、AF_AGENT_ID。
标准流程（Pro 模式）
1. --gateway doctor # 自检：网关连通性
2. --gateway resolve-entity "书房灯" # 获取真实 entity_id（写 DSL 前必调）
3. --gateway propose-dsl "触发: 书房人体传感器 on\n动作: light.turn_on(书房灯)" # ★首选
4. 成功 → 自动部署（授权范围内）
5. 失败 → 看编译错误，改 DSL，重跑步骤 3（上限 3 轮）
6. 不满意 → --gateway snapshots 查看快照，--gateway rollback <id> 回滚
Pro 模式命令
# ★首选：提交 DSL，网关编译+闸门校验，自动部署
nr_client.py --gateway propose-dsl "触发: 传感器 on\n动作: light.turn_on(灯)"
nr_client.py --gateway propose-dsl --dsl-file flow.dsl # 从文件读 DSL
nr_client.py --gateway propose-dsl "..." --preview # 仅生成提案，不部署
# ⚠️逃生舱：直接提交 raw JSON（仅在 DSL 表达不了时使用）
nr_client.py --gateway deploy-raw --flow-file flow.json
# 实体查询
nr_client.py --gateway entities --domain light --area 书房
nr_client.py --gateway resolve-entity "书房灯"
# 快照与回滚
nr_client.py --gateway snapshots
nr_client.py --gateway rollback <snapshot_id>
# 自检
nr_client.py --gateway doctor
nr_client.py --gateway version
DSL 语法速查
场景: <名称>
触发: <entity_id> <状态> # 如 binary_sensor.motion on
条件: <entity_id> <状态> # 可选，多条件用 AND
动作: <service>(<entity_id>) # 如 light.turn_on(light.lamp)
动作: <service>(<entity_id>, brightness=80)
延时: <秒数>秒
分支: <条件> → <动作>
否则: <动作>
并行: <动作1> | <动作2>
调用子流程: <子流程名>(参数=值)
写 DSL 前必须先调 resolve-entity 获取真实 entity_id，禁止凭记忆编造。
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 1mo ago Changed · +76 lines · +12 tokens per session af6a366d1fb9
- 1mo ago First seen · 114 lines · 55 tokens per session scan A 714bc083c0de
autoflow-core is a skill published in the GitHub repository lidicn/AutoFlow (1 stars, last pushed 29d ago), licensed MIT. It adds 67 tokens to every session and 2,642 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 2026-08-31.
Other skills, from other repositories
Architecture Diagram
Produces clean architecture and system diagrams from actual repo or product truth instead of decorative boxes.
Excalidraw
Shapes sketch-style diagrams and editable visual explanations for flows, product ideas, and architecture discussions.
eval-dataset-design
A guide to creating reliable test sets for AI agents. Each evaluation task includes the request, the simulated user's behaviour, a reset starting state, and a success check that can be independently verified.
aatmf-t10-confidentiality-breach
AATMF T10 — Integrity & Confidentiality Breach. System prompt extraction, training-data extraction, model-weight leakage, private-key recovery.
ensembl-database
Query Ensembl genome database REST API for 250+ species. Gene lookups, sequence retrieval, variant analysis, comparative genomics, orthologs, VEP predictions, for genomic research.
mochi-remind
Handle due reminders — notify the user with natural language and mark them done.