Zown Gemini Governor

A high-fidelity token management and model stabilization skill. Implements the Zown "Atomic Pipeline" to prevent Gemini TPM (Tokens Per Minute) rate limits. Use when performing heavy engineering tasks, multi-step code generation, or when encountering 429 Rate Limit errors. Includes protocols for context pruning and forced cool-downs.

This skill is instruction-only but instructs the agent to run local scripts and CLIs that are not declared or provided. Before installing or enabling it: 1) Ask the publisher for source code or a homepage and for the missing scripts (scripts/cooldown.py) and exact gemini CLI requirements. 2) Verify the gemini CLI and any scripts exist and inspect their code — running them could execute arbitrary actions. 3) Test the skill in a sandboxed/non-production agent with autonomous invocation disabled. 4) Confirm whether 'session_status' and the usage/footer checks are available in your agent runtime; otherwise the cooldown logic can't be trusted. 5) Consider the privacy impact: the skill asks to summarize identity/history files (SOUL.md/IDENTITY.md) — review those files for secrets before allowing access. If you cannot verify the missing components or source, treat this skill as untrusted and do not enable it for sensitive or autonomous workflows.

Type: OpenClaw Skill Name: zown-gemini-governor Version: 0.1.0 The `SKILL.md` file instructs the AI agent to execute external commands, specifically `python3 scripts/cooldown.py 60` and to use the `gemini` CLI. While the stated purpose of these commands (rate limit prevention, context management) appears benign, the direct execution of arbitrary scripts and CLI tools by the agent represents a significant security risk (potential RCE) if the scripts are compromised or if the agent can be prompted to execute other commands. There is no clear evidence of intentional malicious behavior such as data exfiltration or backdoor installation within the provided files, classifying it as suspicious rather than malicious.