codex-maintenance
Maintains the internal configuration and structural files for Cascade/Codex agents. Use this to modify agent wiring, memory, or observability.
Install
mkdir -p .claude/skills/codex-maintenance && curl -L -o skill.zip "https://agentskills.codes/api/skills/download/17263" && unzip -o skill.zip -d .claude/skills/codex-maintenance && rm skill.zipInstalls to .claude/skills/codex-maintenance
Activation
This is the description your AI agent reads to decide when to run this skill — the better it matches your request, the more reliably it fires.
Use when changing or auditing Cascade surfaces such as skills, agents, AGENTS.md, CODEX.md, .codex/config.toml, hooks, MCP/tool guidance, memory, observability, evals, handoffs, file trees, or validators.Key capabilities
- →Update configuration surfaces like AGENTS.md and CODEX.md
- →Audit Codex surface choices
- →Change Codex-specific surfaces like `.codex/config.toml`
- →Maintain skills under `.codex/skills/`
- →Ensure agent definitions and validation gates are synchronized
How it works
The skill manages and audits Codex-specific surfaces, ensuring that agent definitions, skill configurations, and validation gates are synchronized with repository goals. It follows a defined source order and surface decision rules for changes.
Inputs & outputs
When to use codex-maintenance
- →Updating agent permissions or tool guidance
- →Auditing observability and eval wiring
- →Refactoring Codex file tree structure
- →Changing local role contracts or templates
About codex-maintenance
Updates configuration surfaces like AGENTS.md, CODEX.md, and local skill files. It ensures agent definitions and validation gates remain synchronized with repository goals.
Use when changing or auditing Cascade surfaces such as skills, agents, AGENTS.md, CODEX.md, .codex/config.toml, hooks, MCP/tool guidance, memory, observability, evals, handoffs, file trees, or validators.
When not to use it
- →When patching product/runtime code without explicit redirection through `implement-change`
- →When relying on prompt text for a rule that must always hold
- →When adding a new agent when a skill cleanly owns the repeated workflow
Limitations
- →The skill does not patch product/runtime code unless explicitly redirected.
- →Durable enforcement rules are not to rely on prompt text.
- →New agents should not be added when a skill already owns the workflow.
How it compares
This skill provides a structured and audited approach to maintaining the Codex harness itself, ensuring consistency and adherence to internal standards, unlike ad-hoc modifications to configuration files.
Compared to similar skills
codex-maintenance side by side with the closest alternatives in the catalog.
| Skill | Installs | Updated | Safety | Difficulty |
|---|---|---|---|---|
| codex-maintenance (this skill) | 0 | 2mo | No flags | Advanced |
| skill-builder | 4 | 7mo | Review | Beginner |
| skill-name | 0 | 8mo | Review | Advanced |
| opencode-cli | 14 | 8mo | Review | Advanced |
Try saying
Example prompts that trigger this skill in your AI assistant.
You might also like
skill-builder
ruvnet
Create new Claude Code Skills with proper YAML frontmatter, progressive disclosure structure, and complete directory organization. Use when you need to build custom skills for specific workflows, generate skill templates, or understand the Claude Skills specification.
skill-name
2025Emma
What it does + when to use (activation triggers).
opencode-cli
SpillwaveSolutions
This skill should be used when configuring or using the OpenCode CLI for headless LLM automation. Use when the user asks to "configure opencode", "use opencode cli", "set up opencode", "opencode run command", "opencode model selection", "opencode providers", "opencode vertex ai", "opencode mcp servers", "opencode ollama", "opencode local models", "opencode deepseek", "opencode kimi", "opencode mistral", "fallback cli tool", or "headless llm cli". Covers command syntax, provider configuration, Vertex AI setup, MCP servers, local models, cloud providers, and subprocess integration patterns.
claude-automation-recommender
anthropics
Analyze a codebase and recommend Claude Code automations (hooks, subagents, skills, plugins, MCP servers). Use when user asks for automation recommendations, wants to optimize their Claude Code setup, mentions improving Claude Code workflows, asks how to first set up Claude Code for a project, or wants to know what Claude Code features they should use.
mcp-integration
anthropics
This skill should be used when the user asks to "add MCP server", "integrate MCP", "configure MCP in plugin", "use .mcp.json", "set up Model Context Protocol", "connect external service", mentions "${CLAUDE_PLUGIN_ROOT} with MCP", or discusses MCP server types (SSE, stdio, HTTP, WebSocket). Provides comprehensive guidance for integrating Model Context Protocol servers into Claude Code plugins for external tool and service integration.
hook-development
anthropics
This skill should be used when the user asks to "create a hook", "add a PreToolUse/PostToolUse/Stop hook", "validate tool use", "implement prompt-based hooks", "use ${CLAUDE_PLUGIN_ROOT}", "set up event-driven automation", "block dangerous commands", or mentions hook events (PreToolUse, PostToolUse, Stop, SubagentStop, SessionStart, SessionEnd, UserPromptSubmit, PreCompact, Notification). Provides comprehensive guidance for creating and implementing Claude Code plugin hooks with focus on advanced prompt-based hooks API.