← Back to Skills Marketplace
Moses Modes
by
burnmydays
· GitHub ↗
· v1.0.3
· MIT-0
321
Downloads
0
Stars
1
Active Installs
4
Versions
Install in OpenClaw
/install moses-modes
Description
MO§ES™ Governance Modes — Injects behavioral constraints from the active mode into all agent prompts. 8 modes: high-security, high-integrity, creative, resea...
Usage Guidance
This skill appears to be what it says (a governance mode injector), but before installing: 1) Confirm the trusted source of the moses-governance bundle and the procedure for setting state (init_state.py). 2) Ask where "logs" and the "reasoning chain" are stored, how long they are retained, and who/what can read them — chain-of-thought may include sensitive data. 3) Test the mode behavior in a sandboxed agent to see exactly how it modifies prompts and whether it writes files beyond the declared stateDir. 4) Note the small metadata/version mismatch in SKILL.md vs registry; prefer skills with a clear homepage/source and documented release artifacts.
Capability Analysis
Type: OpenClaw Skill
Name: moses-modes
Version: 1.0.3
The moses-modes skill bundle is a governance framework designed to apply behavioral constraints to an AI agent based on a selected mode (e.g., High Security, Research). It operates by reading a local state file (~/.openclaw/governance/state.json) and providing instructions in SKILL.md and references/modes.md to guide the agent's reasoning. No malicious execution, data exfiltration, or suspicious obfuscation was found.
Capability Assessment
Purpose & Capability
Name/description match behavior: the skill injects governance constraints and reads the declared state file (~/.openclaw/governance/state.json). The SKILL.md declares the moses-governance dependency for /govern operations; no unrelated binaries, credentials, or config paths are requested.
Instruction Scope
Instructions are narrowly scoped to loading the active mode and applying the listed constraints. However several modes direct the agent to "log full reasoning chain" or "maintain growth log," which implies retention of chain‑of‑thought and internal reasoning. That has potential privacy/exfiltration implications and the SKILL.md is vague about where/what is logged and how long logs are retained.
Install Mechanism
Instruction-only skill with no install spec and no code files — lowest install risk. Nothing is downloaded or executed on install based on provided metadata.
Credentials
No environment variables, credentials, or unrelated config paths are requested. The single filesystem access (stateDirs: ~/.openclaw/governance) is proportional to the declared purpose, but you should confirm what files are read/written (especially logs) and whether other skills can access the same state/logs.
Persistence & Privilege
The skill is not set to always:true and is user-invocable — appropriate for governance. Still, its design to 'inject constraints into all agent prompts' gives it global effect over agent behavior; combined with retained logs or chain-of-thought recording this increases blast radius. No evidence it modifies other skills' configurations.
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install moses-modes - After installation, invoke the skill by name or use
/moses-modes - Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.3
Auto-publish from commit d201c8b4ce70f4f2078a92ce99723e7715dc6d2a
v1.0.2
Auto-publish from commit c0128f413390c73d38808d42eaf13ad990ee548e
v1.0.1
Auto-publish from commit 5a05052fe9058e9fb8c30b7050582be06b285f63
v1.0.0
- Initial release of MO§ES™ Governance Modes skill.
- Injects behavioral constraints into all agent prompts based on one of 8 selectable modes: high-security, high-integrity, creative, research, self-growth, problem-solving, idk, unrestricted.
- Modes enforce strict rules, priorities, and blocks for a range of operational contexts.
- `/govern <mode>` command sets mode and confirms with active constraint summary.
- Designed for integration with moses-governance bundle; supports patent-pending governance methodology.
Metadata
Frequently Asked Questions
What is Moses Modes?
MO§ES™ Governance Modes — Injects behavioral constraints from the active mode into all agent prompts. 8 modes: high-security, high-integrity, creative, resea... It is an AI Agent Skill for Claude Code / OpenClaw, with 321 downloads so far.
How do I install Moses Modes?
Run "/install moses-modes" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is Moses Modes free?
Yes, Moses Modes is completely free, licensed under MIT-0. You can download, install and use it at no cost.
Which platforms does Moses Modes support?
Moses Modes is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).
Who created Moses Modes?
It is built and maintained by burnmydays (@sunrisesillneversee); the current version is v1.0.3.
More Skills