Use when the user wants to update Claude settings, hooks, permissions, MCP server toggles, or other JSON config safely and with scope awareness.

This skill appears to be intended for editing Claude JSON config, but it is under-specified about what files and servers it will touch. Before installing or invoking it: (1) Ask the skill author which exact file paths and scopes (user, project, local) the agent will be allowed to read/write. (2) Confirm whether any MCP or server toggles require credentials or network access — if so, require explicit, scope-limited credentials and out-of-band confirmation before changes. (3) Require the agent to produce a diff and get explicit human approval before writing any file. (4) Keep backups of any settings.json you allow it to edit. (5) Because the skill has no homepage and provenance is limited, prefer conservative usage (limit its file permissions, run in a constrained environment) until you can verify the source. These steps reduce the risk that the agent will read or change unrelated or sensitive configuration.

Type: OpenClaw Skill Name: claude-code-claude-settings-editor Version: 1.0.0 The skill is designed to manage Claude configuration files, such as settings.json, hooks, and MCP server toggles. The instructions in SKILL.md and agents/openai.yaml focus on safe JSON editing, scope awareness, and include explicit guardrails to warn users before widening permissions or making broad changes. No malicious code, exfiltration patterns, or harmful prompt-injection instructions were found.