← 返回 Skills 市场
SMFOI-KERNEL
作者
rigeneproject
· GitHub ↗
· v1.0.4
· MIT-0
136
总下载
0
收藏
0
当前安装
5
版本数
在 OpenClaw 中安装
/install smfoi-kernel
功能描述
Implements a 5-step recursive protocol guiding autonomous agents to self-locate, map constraints, detect challenges, prioritize survival, and act coherently...
安全使用建议
This skill appears to do what it says: a per-turn orientation and local audit log. Before installing, verify the runtime will grant only workspace-scoped write access to ./memory/kernel/ (and that the registry metadata matches the package's CLAW_HUB_METADATA.json). Inspect and restrict access to the generated ./memory/kernel/state.md since it may contain conversation data. Expect frequent writes (every turn); test in an isolated environment first to confirm the runtime enforces the SKILL.md constraints (the SKILL.md is advisory and the platform must honor it). If you need stronger guarantees, ask the skill author to declare the filesystem requirement in the registry metadata and to provide a sample state.md entry format and log rotation/retention guidance.
功能分析
Type: OpenClaw Skill
Name: smfoi-kernel
Version: 1.0.4
The SMFOI-KERNEL skill bundle is a prompt-based orientation protocol designed to enforce safety constraints and auditability. It contains no executable code and explicitly restricts the agent from accessing system logs, environment variables, or modifying its own configuration. All instructions in SKILL.md and kernel_v0.2.txt are focused on maintaining a 'sandbox-first' approach and logging state to a local workspace subfolder (./memory/kernel/).
能力评估
Purpose & Capability
The skill's name and description (orientation/safety kernel) match the SKILL.md instructions (5-step per-turn check, constraint mapping, logging). One discrepancy: top-level registry metadata provided with the evaluation lists no required filesystem permissions, but CLAW_HUB_METADATA.json embedded in the package explicitly requests a workspace-scoped filesystem path (./memory/kernel/) for logging. This is consistent with the stated purpose, but the registry summary should declare that filesystem requirement.
Instruction Scope
SKILL.md constrains the agent (no system logs, no env var reads, Level 3 proposals non-executable) and instructs a per-turn mental check that is logged to ./memory/kernel/state.md. Instructions stay within the stated orientation scope, but they do permit reading local workspace files and writing audit logs that may contain conversation context or user data — review what the agent will record.
Install Mechanism
No install spec and no code files beyond plaintext docs — lowest-risk profile. Nothing is downloaded or executed by an installer.
Credentials
The skill requests no environment variables or external credentials. The only resource it needs is a workspace-local logging path (./memory/kernel/) declared in CLAW_HUB_METADATA.json; confirm the registry-level metadata also declares this so the runtime can grant appropriate workspace write permission and avoid surprise writes elsewhere.
Persistence & Privilege
always:false and normal autonomous invocation are used. The skill will run every turn if enabled (trigger: every_turn), which can generate frequent log writes — not a privilege escalation, but consider potential disk usage and information accumulation in the log file.
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 smfoi-kernel - 安装完成后，直接呼叫该 Skill 的名称或使用
/smfoi-kernel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
v1.0.4
No file changes detected; only SKILL.md was reverted to an older version.
- Rolled back SKILL.md documentation from v0.2.3 to v0.2.2.
- Descriptions and summaries were simplified and wording reverted to earlier phrasing.
- Some security boundary and operational level details were updated to the v0.2.2 format.
- No code or file-level changes were made.
v1.0.3
SMFOI-KERNEL v0.2.3 includes refined security boundaries, clarified protocol, and enhanced auditing:
- Updated description to emphasize a local orientation and telemetry protocol.
- Clarified read-only restrictions: agent cannot modify OS/environment or external files.
- Limited agent write access solely to telemetry logs in ./memory/kernel/state.md.
- Refined security and operational boundaries, ensuring signal detection only processes conversation context.
- Enhanced and clarified 5-step cycle, including stricter logging terminology ("Telemetry" step).
- Minor updates to operational level descriptions and terminology for accuracy.
v1.0.2
No file changes detected; version bump only.
- Version updated to 1.0.2 with no modifications to code or documentation.
- No changes in features, behavior, or security policies.
v1.0.1
SMFOI-KERNEL v0.2.2 focuses on enhanced security and tightened operational boundaries.
- Removes triggers for iot_event and resource_change; now only activates on every_turn.
- Enforces strict "No System Access": prevents reading OS logs, shell history, or environment variables.
- Clarifies that the agent operates in a read-only local environment.
- Requires manual human approval for any protocol modification proposals (Level 3/Recursion).
- Adds mandatory logging of the orientation cycle outcome to ./memory/kernel/state.md.
v1.0.0
Initial public release of SMFOI-KERNEL
- Introduces a 5-step mandatory orientation cycle for every agent action.
- Implements operational levels: Integrity, Exploration, Expansion, Recursion.
- Enforces workspace-only operation with no API keys or external tokens.
- Provides injection defense mechanisms against instruction overrides.
- Designed for autonomous, substrate-independent decision-making.
元数据
常见问题
SMFOI-KERNEL 是什么？
Implements a 5-step recursive protocol guiding autonomous agents to self-locate, map constraints, detect challenges, prioritize survival, and act coherently... 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 136 次。
如何安装 SMFOI-KERNEL？
在 OpenClaw 或 Claude Code 对话框中运行命令「/install smfoi-kernel」即可一键安装，无需额外配置。
SMFOI-KERNEL 是免费的吗？
是的，SMFOI-KERNEL 完全免费，采用 MIT-0 许可证，可自由下载、安装和使用。
SMFOI-KERNEL 支持哪些平台？
SMFOI-KERNEL 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 SMFOI-KERNEL？
由 rigeneproject（@rigeneproject）开发并维护，当前版本 v1.0.4。
推荐 Skills