← 返回 Skills 市场
141
总下载
0
收藏
0
当前安装
5
版本数
在 OpenClaw 中安装
/install openclaw-plugin-edicts
功能描述
Ground truth layer for AI agents — provide verified facts in every prompt and expose read/search tools for edict management. Write tools are opt-in. No more...
安全使用建议
This plugin appears to be what it says: a local edict manager that injects curated facts into the system prompt. Before installing/activating it, do the following: 1) Decide whether agents should be allowed to write to the edicts file — safest config is tools.enabled: false and autoSave: false so only your curated file is injected. 2) Set an explicit path in the plugin config (path: './edicts.yaml' or a repo-controlled path) to avoid the plugin walking up the filesystem and picking up unexpected files. 3) If you enable write tools, require a manual review/audit process (or disable autoSave) so agents cannot permanently change system prompts without human oversight. 4) Verify which defaults your OpenClaw install uses (the docs are slightly inconsistent about defaults). 5) Keep the edicts file under version control and review its contents regularly — because anything in that file will influence model behavior. If you want, I can produce a safe default openclaw.json snippet you can paste to minimize risk.
能力评估
Purpose & Capability
The name/description (ground-truth injection) aligns with the shipped code: a local EdictStore that reads/writes YAML/JSON and renders edicts into prompt context. There are small inconsistencies in docs/metadata (Node engine/version strings vary; SKILL.md sometimes says tools are 'opt-in' but other places imply a 'true' default), but nothing that suggests unrelated capabilities (no cloud creds, no unexpected binaries).
Instruction Scope
SKILL.md explicitly instructs the plugin to inject edicts into the system prompt (this is the feature). That is inherently high-impact because it changes model behavior. The docs state write tools are 'opt-in' but elsewhere indicate a default of 'tools.enabled: true' and autoSave defaults to true in the code — this ambiguity matters because enabling write tools + autoSave lets agents persist changes to the file (i.e., mutate the system context). The CLI/store code only reads/writes local files and does not reference environment secrets, but the findEdictsFile routine walks up the directory tree to root which could cause it to pick up edict files outside the immediate workspace unless you set an explicit path.
Install Mechanism
No external download/install spec in the plugin bundle; package is self-contained TypeScript with a single runtime dependency ('yaml'). No network calls, external URLs, or extract-from-URL installs were found in the source. package.json and package-lock list normal dependencies/dev deps.
Credentials
The skill requires no environment variables or external credentials. All storage is file-based. The code accesses filesystem paths (read/write) and computes a file hash for optimistic concurrency — these are proportional to a local edict store.
Persistence & Privilege
The plugin is not always-included (always:false) and model invocation is permitted (normal). The main concern is persistence: EdictStore defaults (and SKILL.md wording) imply runtime mutations may be auto-saved. If you enable write tools and leave autoSave true, an agent could autonomously add/update/remove edicts and thereby alter future system prompts. This is an intended capability but a high-privilege one — confirm settings before enabling.
如何使用
- 确保已安装 OpenClaw（本地或 Docker 部署）
- 在对话框中输入安装命令：
/install openclaw-plugin-edicts - 安装完成后，直接呼叫该 Skill 的名称或使用
/openclaw-plugin-edicts触发 - 根据 Skill 的参数说明提供必要输入，即可获得结构化输出
版本历史
v1.0.6
Excluded CCC planning artifacts (docs/superpowers/, docs/blog/) from package.
v1.0.5
Removed 'inject' trigger words from README and SKILL.md. Emphasized read-only default and opt-in write tools throughout descriptions.
v1.0.4
Removed imperative instruction from README code example that triggered ClawHub prompt-injection scanner.
v1.0.3
Removed CCC helper scripts. Added Security and Trust Model docs.
v1.0.2
Initial ClawHub publish. Same as npm [email protected].
元数据
常见问题
Edicts — Ground Truth for AI Agents 是什么？
Ground truth layer for AI agents — provide verified facts in every prompt and expose read/search tools for edict management. Write tools are opt-in. No more... 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 141 次。
如何安装 Edicts — Ground Truth for AI Agents？
在 OpenClaw 或 Claude Code 对话框中运行命令「/install openclaw-plugin-edicts」即可一键安装，无需额外配置。
Edicts — Ground Truth for AI Agents 是免费的吗？
是的，Edicts — Ground Truth for AI Agents 完全免费，采用 MIT-0 许可证，可自由下载、安装和使用。
Edicts — Ground Truth for AI Agents 支持哪些平台？
Edicts — Ground Truth for AI Agents 跨平台运行，可在任意部署了 OpenClaw / Claude Code 的环境中使用（cross-platform）。
谁开发了 Edicts — Ground Truth for AI Agents？
由 mssteuer（@mssteuer）开发并维护，当前版本 v1.0.6。
推荐 Skills