--- title: Coding Agents | daily.dev description: This is a reference-style rundown of two AI coding agents, Codex and Claude Code, covering setup and day-to-day features. It explains Codex concepts like... canonical: https://daily.dev/posts/coding-agents-ss14lrnkl twitter:card: summary_large_image twitter:site: @dailydotdev og:type: website og:site_name: daily.dev og:title: Coding Agents | daily.dev og:description: This is a reference-style rundown of two AI coding agents, Codex and Claude Code, covering setup and day-to-day features. It explains Codex concepts like... og:url: https://daily.dev/posts/coding-agents-ss14lrnkl og:image: https://api.daily.dev/og/posts/ss14lRNKl.png og:image:alt: Coding Agents og:image:width: 1200 og:image:height: 630 og:locale: en --- > ## Documentation Index > Fetch the complete documentation index at: https://daily.dev/llms.txt > Use this file to discover all available pages before exploring further. # Coding Agents **[Medium](https://daily.dev/sources/medium_js)** · 10 min read · 0 upvotes · 0 comments ## Summary This is a reference-style rundown of two AI coding agents, Codex and Claude Code, covering setup and day-to-day features. It explains Codex concepts like agents.md, the agent loop, slash goals, memory files (memory_summary.md, MEMORY.md, raw_memories.md), skills, and permission modes (Ask for Approval, Approve for Me, Full Access). For Claude Code it lists CLAUDE.md, skills, commands, subagents, MCP servers, hooks, and plugins, plus slash commands like /clear, /compact, /context, /init, /model, /plan, and /batch. It also gives a six-step Codex workflow from defining a task to committing the reviewed diff, and a four-phase PR review model from pre-PR testing to post-merge monitoring. ## Full article daily.dev links to this article rather than hosting it. Read it at the original source: ## Questions this post answers ### What are the three permission modes available in Codex CLI? Codex CLI offers three permission modes: 'Ask for Approval' (the default), which uses a workspace-write sandbox and pauses before external actions or changes outside the workspace; 'Approve for Me', which routes low-risk requests to an auto-review subagent to cut down on prompts; and 'Full Access', which grants unrestricted internet and file access across the computer. _Developers tightening agent permissions before granting file or network access can compare setups like this on daily.dev._ ### What is the difference between AGENTS.md and the memory files in ~/.codex/memories in Codex? AGENTS.md is a human-maintained static instruction layer read at the start of every Codex session, used for hard rules, build commands, and coding styles, and it cascades across global, project, and folder levels. The ~/.codex/memories/ directory is auto-generated, holding memory_summary.md as the consolidated overview, MEMORY.md as the long-form merged store, and raw_memories.md as the pre-consolidation extraction output. _Anyone structuring long-running agent context can track these memory-layer patterns on daily.dev._ ### What are the main slash commands in Claude Code for managing session context? Claude Code offers /clear to wipe conversation history and start fresh, /compact to summarize the active conversation and free up the context window, /context to show a visual breakdown of what is filling the context window, /init to auto-generate a starter CLAUDE.md file, /memory to edit persistent memory configurations, and /resume to reopen a previous terminal conversation. _Developers managing long agent sessions can keep these context-control commands handy via daily.dev._ ## Similar posts on daily.dev - [How to Combine Claude Code and Codex for Maximum Coding Power](https://daily.dev/posts/how-to-combine-claude-code-and-codex-for-maximum-coding-power-h7fg7exw9) · Towards Data Science · 2 upvotes · 0 comments - [OpenAI spills technical details about how its AI coding agent works](https://daily.dev/posts/openai-spills-technical-details-about-how-its-ai-coding-agent-works-qzx3whxmk) · Ars Technica · 1 upvotes · 0 comments --- Tags: [#ai-agents](https://daily.dev/tags/ai-agents), [#mcp](https://daily.dev/tags/mcp), [#claude-code](https://daily.dev/tags/claude-code), [#openai-codex](https://daily.dev/tags/openai-codex) [View this post on daily.dev](https://daily.dev/posts/coding-agents-ss14lrnkl) ```json {"@context":"https://schema.org","@graph":[{"@type":"Organization","@id":"https://daily.dev/#organization","name":"daily.dev","url":"https://daily.dev","logo":{"@type":"ImageObject","url":"https://daily.dev/apple-touch-icon.png","width":180,"height":180},"sameAs":["https://twitter.com/dailydotdev","https://github.com/dailydotdev","https://www.linkedin.com/company/daily-dev-ltd"]},{"@type":"WebSite","@id":"https://daily.dev/#website","url":"https://daily.dev","name":"daily.dev","publisher":{"@id":"https://daily.dev/#organization"},"potentialAction":{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https://daily.dev/search?q={search_term_string}"},"query-input":"required name=search_term_string"}}]} {"@context":"https://schema.org","@type":"TechArticle","headline":"Coding Agents","url":"https://daily.dev/posts/coding-agents-ss14lrnkl","mainEntityOfPage":{"@type":"WebPage","@id":"https://daily.dev/posts/coding-agents-ss14lrnkl"},"datePublished":"2026-11-01T00:04:24.554Z","dateModified":"2026-11-01T00:29:54.915Z","description":"This is a reference-style rundown of two AI coding agents, Codex and Claude Code, covering setup and day-to-day features. It explains Codex concepts like...","image":"https://media.daily.dev/image/upload/s--P4t4XyoV--/f_auto/v1722860399/public/Placeholder%2001","thumbnailUrl":"https://media.daily.dev/image/upload/s--P4t4XyoV--/f_auto/v1722860399/public/Placeholder%2001","isAccessibleForFree":true,"articleSection":"Medium","inLanguage":"en","publisher":{"@type":"Organization","name":"daily.dev","url":"https://daily.dev","logo":{"@type":"ImageObject","url":"https://daily.dev/apple-touch-icon.png","width":180,"height":180}},"author":{"@type":"Organization","name":"Medium","logo":"https://media.daily.dev/image/upload/t_logo,f_auto/v1/logos/medium","url":"https://daily.dev/sources/medium_js"},"commentCount":0,"discussionUrl":"https://daily.dev/posts/coding-agents-ss14lrnkl","interactionStatistic":[{"@type":"InteractionCounter","interactionType":{"@type":"LikeAction"},"userInteractionCount":0},{"@type":"InteractionCounter","interactionType":{"@type":"CommentAction"},"userInteractionCount":0}],"keywords":"ai-agents,mcp,claude-code,openai-codex","timeRequired":"PT10M"} {"@context":"https://schema.org","@type":"BreadcrumbList","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https://daily.dev"},{"@type":"ListItem","position":2,"name":"Medium","item":"https://daily.dev/sources/medium_js"},{"@type":"ListItem","position":3,"name":"Coding Agents"}]} {"@context":"https://schema.org","@type":"FAQPage","@id":"https://daily.dev/posts/coding-agents-ss14lrnkl#faq","mainEntity":[{"@type":"Question","name":"What are the three permission modes available in Codex CLI?","acceptedAnswer":{"@type":"Answer","text":"Codex CLI offers three permission modes: 'Ask for Approval' (the default), which uses a workspace-write sandbox and pauses before external actions or changes outside the workspace; 'Approve for Me', which routes low-risk requests to an auto-review subagent to cut down on prompts; and 'Full Access', which grants unrestricted internet and file access across the computer. Developers tightening agent permissions before granting file or network access can compare setups like this on daily.dev."}},{"@type":"Question","name":"What is the difference between AGENTS.md and the memory files in ~/.codex/memories in Codex?","acceptedAnswer":{"@type":"Answer","text":"AGENTS.md is a human-maintained static instruction layer read at the start of every Codex session, used for hard rules, build commands, and coding styles, and it cascades across global, project, and folder levels. The ~/.codex/memories/ directory is auto-generated, holding memory_summary.md as the consolidated overview, MEMORY.md as the long-form merged store, and raw_memories.md as the pre-consolidation extraction output. Anyone structuring long-running agent context can track these memory-layer patterns on daily.dev."}},{"@type":"Question","name":"What are the main slash commands in Claude Code for managing session context?","acceptedAnswer":{"@type":"Answer","text":"Claude Code offers /clear to wipe conversation history and start fresh, /compact to summarize the active conversation and free up the context window, /context to show a visual breakdown of what is filling the context window, /init to auto-generate a starter CLAUDE.md file, /memory to edit persistent memory configurations, and /resume to reopen a previous terminal conversation. Developers managing long agent sessions can keep these context-control commands handy via daily.dev."}}]} ```