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 agentmods add skills/opendcai/dataflow-loopai/configernpx skills add OpenDCAI/Dataflow-LoopAI --skill configergit clone --depth 1 https://github.com/OpenDCAI/Dataflow-LoopAIWhat 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 | $0.00000 | $0.02930 |
| Opus 5 | $0.00000 | $0.01465 |
| Sonnet 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 2d 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.
- 2d ago First seen · 362 lines · 0 tokens per session scan A cd04bf627aad
Configer is a skill published in the GitHub repository OpenDCAI/Dataflow-LoopAI (22 stars, last pushed 2d 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
loopx-project
Use when connecting a repository or project goal document to LoopX, maintaining project-local goal state, refreshing stale dashboard status, syncing local projects into the shared global registry, or diagnosing LoopX CLI/PATH/status/history issues across multiple repos. For registering durable project materials such…
loopx-auto-research
Use when a LoopX worker is operating an auto-research lane, demo pane, frontier item, evidence packet, promotion/retirement decision, or visible tmux/Codex auto-research rehearsal. Identity must come from the LoopX role profile and quota/frontier packet; this skill only provides role-specific execution checklists…
loopx-change-quality
Qualify the exact final diff for a LoopX-managed goal. Use when goal policy enables changequalityqualification, before a non-trivial delivery or merge, and when producing or repairing an exact-scope quality receipt. The workflow is language-neutral, permits at most one policy-authorized safe-fix pass, and never grants…
loopx-material
Operate an explicitly activated LoopX Material Lifecycle for a connected project. Use for material-store inventory, lossless migration, candidate/archive transitions, exact-read-backed ranking, ranked-entry rebuilds, bounded Explore intake, owner-gated apply, rollback, and audit. Do not use for ordinary one-off…
loopx-pr-program
Use when LoopX must manage a multi-PR or multi-MR delivery program across one or more repositories: inventory current change requests, reconcile new/merged/closed or retargeted work, preserve requirement and dependency priorities, maintain a roadmap document, or monitor material lifecycle/check/review changes over…
loopx-self-repair
Diagnose and repair LoopX control-plane drift or agent behavior drift. Use when a LoopX task makes unexpectedly small progress, follows a stale or contradictory recommendedaction, ignores a higher-priority blocked item while doing fallback work, reports vague owner/user gates, loses todo projection, misaligns…