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 OpenDCAI/Dataflow-LoopAI --skill configergit clone --depth 1 https://github.com/OpenDCAI/Dataflow-LoopAIWrote 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/opendcai/dataflow-loopai/configer)<a href="https://agentmods.dev/skills/opendcai/dataflow-loopai/configer"><img src="https://agentmods.dev/badge/skills/opendcai/dataflow-loopai/configer/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/opendcai/dataflow-loopai/configer"><img src="https://agentmods.dev/badge/skills/opendcai/dataflow-loopai/configer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00000 | $0.02930 |
| Opus 5.5 | $0.00000 | $0.01172 |
| Sonnet 5.5 | $0.00000 | $0.00586 |
| Haiku 4.5 | $0.00000 | $0.00293 |
Grade A, and why
Configer 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 — 362 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Configer Skill
用于处理 LoopAI 中两类请求：
state类：读取或修改任务states配置runtime类：读取任务节点 runtime 状态
如果你只想快速判断该不该用这个 skill，看这三条：
- 用户在问“参数是什么、现在配成什么、要怎么改”时，用它
- 用户在问“节点现在跑到哪、历史状态是什么”时，也用它
- 用户在问全局
system配置时，不要用它
什么时候使用
当用户要执行以下任一操作时，使用本 skill：
- 查看某个 section / agent 有哪些可配置字段
- 询问某个配置项是什么意思、允许填什么值
- 读取数据库里某个 task 的实际
states值 - 读取全局默认
states配置 - 修改某个 task 下的
states配置 - 修改全局默认
states配置 - 读取某个 task 下某个节点的最新 runtime
- 读取某个 task 下某个节点的历史 runtime
- 读取某个 task 下所有节点的最新 runtime
不要用它处理：
- 全局
system配置读取或修改 - 模型服务地址、API key、workspace、runner、provider、系统路径等
system.*请求 - 训练、评测、分析、爬取、数据构造本身
首先做分类
开始动作前，先把请求归到下面两类之一：
state：用户关心的是“任务参数是什么、现在怎么配、要不要改”runtime：用户关心的是“任务现在跑到哪了、节点历史状态是什么”
然后再做第二层判断：
- 如果是全局
system：立即停止，不要调用本 skill 的任何state/runtime读写函数 - 如果是
default_states或任务state：走state工具 - 如果是节点运行态 / 节点历史：走
runtime工具
快速决策表
- 想知道字段含义、可选值、schema 默认值：
get_configer_state_schema - 想读当前任务实际配置：
get_configer_task_state_config - 想读默认或自动作用域配置：
get_configer_state_config - 想改当前任务实际配置：
update_configer_task_state_config - 想改默认或自动作用域配置：
update_configer_state_config - 想看单节点最新状态：
get_runtime_task_node_latest - 想看单节点历史：
get_runtime_task_node_history - 想看当前任务全部节点最新状态：
get_runtime_task_latest_runtimes
不要先做全仓搜索
当用户的意图明显是“读/改某个配置项”或“看某个节点 runtime”时，不要先在整个仓库里搜索字段名。
不要先执行这类全仓搜索：
rg -n "eval_task_type|judger|trainer|runtime" -S .
原因：
- 仓库较大，且包含
ui/node_modules等目录 - 全仓搜索很容易拖慢首轮响应
- 对于明确的配置或 runtime 请求，这类搜索没有必要
如果确实需要搜索，也要限制范围，例如：
rg -n "eval_task_type|trainer" skills/Configer loopai/skills/Configer api/app -S
背景知识
这个 skill 对应两类底层数据：
state- 全局默认 states：
StarterConfig.config.default_states - 任务实际 states：
TaskModel.state
- 全局默认 states：
runtime- 任务节点运行态：
TaskRuntime
- 任务节点运行态：
重要：
- 全局
system不属于这套 skill 的处理范围 - 任务级 states 应理解为
TaskModel.state - 不要把任务级 states 修改理解成改
TaskModel.config.default_states - runtime 只读当前任务运行态，不负责配置修改
环境变量与作用域
DB_PATH：读取数据库实际值时必需task_id或TASK_ID：任务级读取时优先使用
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 First seen · 362 lines · 0 tokens per session scan A cd04bf627aad
Configer is a skill published in the GitHub repository OpenDCAI/Dataflow-LoopAI (29 stars, last pushed 16d ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 2,930 tokens. 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.
Other skills, from other repositories
daily-report
Compile timestamped conversation logs, agent sessions, IM messages, collaborative documents, meeting notes, task records, and similar OpenViking materials into concise, evidence-grounded daily reports. Use with ov compile when the user asks for a daily work report, end-of-day digest, 日报, or reports for one or more…
tmux
Remote-control tmux sessions for interactive CLIs by sending keystrokes and scraping pane output.
cron
Schedule reminders and recurring tasks.
scheduler
Use when user wants to schedule tasks for future, recurring, or interval execution. Manages one-time, cron, and interval tasks dispatched via C4 comm-bridge.
meeting-copilot
A two-machine live meeting copilot. A Windows laptop streams two audio channels (your mic, and a loopback of the other side's voice) to a parent machine, which transcribes them, drives a teleprompter you read from, watches every incoming utterance against a ledger of pre-agreed facts, and answers off-script questions.…
meeting-board
A one-machine live meeting board. A small browser extension reads Google Meet's own live captions together with the speaker names, hands them to a tiny helper that listens on 127.0.0.1 only, and the helper periodically asks the local Claude Code (claude -p) to keep a structured, speaker-attributed "story so far".…