{"slug": "agents-md", "name": "AGENTS.md", "category": "ai-coding", "category_name": "AI coding tools", "description": "", "recommenders": 5, "commenters": 9, "warners": 2, "score": 3.251, "rising": -0.31, "first": "2025-12-09", "latest": "2026-09-19", "why": "I recently switched to using only AGENTS.md and SKILLS.  I appreciate the standardization from this perspective.", "why_is_quote": true, "has_verdict": false, "sentiment": {"recommend": 5, "neutral": 2, "compare": 0, "warn": 2}, "spark": [0, 0, 0, 2, 0, 0, 2, 0, 0, 0, 1, 0], "listed": true, "loved": [], "caveat": "", "short_quote": "I recently switched to using only AGENTS.md and SKILLS.  I appreciate the standardization from this perspective.", "kind": "", "icon": true, "domain": null, "github_repo": "github.com/libretranslate/libretranslate", "official_url": "https://agents.md", "pricing": "", "aliases": ["AGENTS.md"], "verdict": null, "praise": [{"label": "", "summary": "", "quotes": [{"id": 796228257, "item_id": 49764266, "url": "https://news.ycombinator.com/item?id=49764266", "by": "askonomm", "date": "2026-09-19", "stance": "recommend", "quote": "that has been AGENTS.md for a long while now", "excerpt": "Just because something is first, doesn't mean it's the standard. The standard is put in place by how many harnesses use a specific pattern, and that has been AGENTS.md for a long while now. Long enough that Claude Code not supporting it is really just an act of forcing people into a proprietary workflow, because of course it's in their interest to make moving away as painful as possible given how little moat the LLM ", "context": "", "use_case": "agent instructions standard", "switched_from": "", "story": "Claude Code now reads AGENTS.md if there is no Claude.md"}, {"id": 771032720, "item_id": 48189545, "url": "https://news.ycombinator.com/item?id=48189545", "by": "pierotofy", "date": "2026-05-18", "stance": "recommend", "quote": "I stopped most spam with a simple AGENTS.md. It actually seems to work (for now).", "excerpt": "I stopped most spam with a simple AGENTS.md. It actually seems to work (for now). https://github.com/LibreTranslate/LibreTranslate/blob/main/AGENTS.md", "context": "", "use_case": "stop AI bot spam", "switched_from": "", "story": "We stopped AI bot spam in our GitHub repo using Git's \u2013author flag"}, {"id": 767913136, "item_id": 47994571, "url": "https://news.ycombinator.com/item?id=47994571", "by": "arikrahman", "date": "2026-05-03", "stance": "recommend", "quote": "Agents.md actually scales and outperforms alternatives", "excerpt": "Agents.md actually scales and outperforms alternatives so I would be skeptical about overcomplicating the proces https://vercel.com/blog/agents-md-outperforms-skills-in-our-agent-evals", "context": "", "use_case": "", "switched_from": "", "story": "Specsmaxxing \u2013 On overcoming AI psychosis, and why I write specs in YAML"}, {"id": 750011744, "item_id": 46875734, "url": "https://news.ycombinator.com/item?id=46875734", "by": "csummers", "date": "2026-02-03", "stance": "recommend", "quote": "I recently switched to using only AGENTS.md and SKILLS.  I appreciate the standardization from this perspective.", "excerpt": "I'm developing a new programming language, so I have to provide a way for LLMs to know about and generate code for a language they have not seen (i.e., have no training data for). My tooling was previously adding in AI hints with CLAUDE.md, Cursor Rules, Windsurf Rules, AGENTS.md, etc., but I recently switched to using only AGENTS.md and SKILLS. I appreciate the standardization from this perspective.", "context": "developing a new programming language", "use_case": "giving LLMs hints for a new language", "switched_from": "CLAUDE.md", "story": "Agent Skills"}, {"id": 749944273, "item_id": 46871517, "url": "https://news.ycombinator.com/item?id=46871517", "by": "modernerd", "date": "2026-02-03", "stance": "recommend", "quote": "The AGENTS.md approach provides broad, horizontal improvements", "excerpt": "That's also what Vercel found: > In 56% of eval cases, the skill was never invoked. The agent had access to the documentation but didn't use it. Adding the skill produced no improvement over baseline. > \u2026 > Skills aren't useless. The AGENTS.md approach provides broad, horizontal improvements to how agents work with Next.js across all tasks. Skills work better for vertical, action-specific workflows that users explici", "context": "", "use_case": "", "switched_from": "", "story": "Agent Skills"}]}], "caveats": [{"label": "", "summary": "", "quotes": [{"id": 754449569, "item_id": 47153098, "url": "https://news.ycombinator.com/item?id=47153098", "by": "wolfejam", "date": "2026-02-25", "stance": "warn", "quote": "The core issue isn't the idea of context files \u2014 it's that prose is the wrong format for structured facts.", "excerpt": "This paper validates what we've been building toward. The core issue isn't the idea of context files \u2014 it's that prose is the wrong format for structured facts. AI crushes structured data like package.json but struggles with free-form markdown. Two developers describe the same repo completely differently. There's no schema, no validation, no scoring. Our paper on CERN's Zenodo proposes FAF \u2014 a structured YAML format ", "context": "", "use_case": "", "switched_from": "", "story": "Evaluating AGENTS.md: are they helpful for coding agents?"}]}], "who": [{"by": "csummers", "context": "developing a new programming language", "url": "https://news.ycombinator.com/item?id=46875734", "date": "2026-02-03"}], "tags": [], "use_cases": ["agent instructions standard", "stop ai bot spam", "agent configuration", "giving llms hints for a new language"], "compared": [{"slug": "agent-skills", "name": "Agent Skills", "co": 3, "switched_from": 0, "switched_to": 0}, {"slug": "claude-code", "name": "Claude Code", "co": 2, "switched_from": 0, "switched_to": 0}], "makers": [], "threads": [{"url": "https://news.ycombinator.com/item?id=46871173", "title": "Agent Skills", "mentions": 2}, {"url": "https://news.ycombinator.com/item?id=49760187", "title": "Claude Code now reads AGENTS.md if there is no Claude.md", "mentions": 1}, {"url": "https://news.ycombinator.com/item?id=48181125", "title": "We stopped AI bot spam in our GitHub repo using Git's \u2013author flag", "mentions": 1}, {"url": "https://news.ycombinator.com/item?id=48139148", "title": "God Damn AI is making me dumb", "mentions": 1}, {"url": "https://news.ycombinator.com/item?id=47994012", "title": "Specsmaxxing \u2013 On overcoming AI psychosis, and why I write specs in YAML", "mentions": 1}, {"url": "https://news.ycombinator.com/item?id=47280200", "title": "Anthropic, Please Make a New Slack", "mentions": 1}], "sentiment_by_month": {"2025-11": {}, "2025-12": {"neutral": 1}, "2026-01": {}, "2026-02": {"recommend": 2, "warn": 1}, "2026-03": {"warn": 1}, "2026-04": {}, "2026-05": {"recommend": 2, "neutral": 1}, "2026-06": {}, "2026-07": {}, "2026-08": {}, "2026-09": {"recommend": 1}, "2026-10": {}}, "quotes": [{"id": 796228257, "item_id": 49764266, "url": "https://news.ycombinator.com/item?id=49764266", "by": "askonomm", "date": "2026-09-19", "stance": "recommend", "quote": "that has been AGENTS.md for a long while now", "excerpt": "Just because something is first, doesn't mean it's the standard. The standard is put in place by how many harnesses use a specific pattern, and that has been AGENTS.md for a long while now. Long enough that Claude Code not supporting it is really just an act of forcing people into a proprietary workflow, because of course it's in their interest to make moving away as painful as possible given how little moat the LLM ", "context": "", "use_case": "agent instructions standard", "switched_from": "", "story": "Claude Code now reads AGENTS.md if there is no Claude.md"}, {"id": 771032720, "item_id": 48189545, "url": "https://news.ycombinator.com/item?id=48189545", "by": "pierotofy", "date": "2026-05-18", "stance": "recommend", "quote": "I stopped most spam with a simple AGENTS.md. It actually seems to work (for now).", "excerpt": "I stopped most spam with a simple AGENTS.md. It actually seems to work (for now). https://github.com/LibreTranslate/LibreTranslate/blob/main/AGENTS.md", "context": "", "use_case": "stop AI bot spam", "switched_from": "", "story": "We stopped AI bot spam in our GitHub repo using Git's \u2013author flag"}, {"id": 770266256, "item_id": 48141641, "url": "https://news.ycombinator.com/item?id=48141641", "by": "fstepho", "date": "2026-05-14", "stance": "neutral", "quote": "Most of my time goes into AGENTS.md, hooks, sub-agents, verification loops", "excerpt": "Slightly different take here. I'm not coding less, I'm just coding the harness instead of the product. Most of my time goes into AGENTS.md, hooks, sub-agents, verification loops to keep the agent from going off. https://openai.com/index/harness-engineering/ describes pretty much what I do all day now.", "context": "", "use_case": "Agent configuration", "switched_from": "", "story": "God Damn AI is making me dumb"}, {"id": 767913136, "item_id": 47994571, "url": "https://news.ycombinator.com/item?id=47994571", "by": "arikrahman", "date": "2026-05-03", "stance": "recommend", "quote": "Agents.md actually scales and outperforms alternatives", "excerpt": "Agents.md actually scales and outperforms alternatives so I would be skeptical about overcomplicating the proces https://vercel.com/blog/agents-md-outperforms-skills-in-our-agent-evals", "context": "", "use_case": "", "switched_from": "", "story": "Specsmaxxing \u2013 On overcoming AI psychosis, and why I write specs in YAML"}, {"id": 756500225, "item_id": 47281264, "url": "https://news.ycombinator.com/item?id=47281264", "by": "coder543", "date": "2026-03-06", "stance": "warn", "quote": "", "excerpt": "Why on earth would Anthropic commit to interoperability? That is the company that doesn't interoperate with the standard LLM APIs that OpenAI developed, which everyone else in the industry has adopted and uses. Whether OpenAI's APIs are great or perfect or not, they are the standard that the industry has settled on. That is the same company that refuses to add support for AGENTS.md that everyone else in the industry ", "context": "", "use_case": "", "switched_from": "", "story": "Anthropic, Please Make a New Slack"}, {"id": 754449569, "item_id": 47153098, "url": "https://news.ycombinator.com/item?id=47153098", "by": "wolfejam", "date": "2026-02-25", "stance": "warn", "quote": "The core issue isn't the idea of context files \u2014 it's that prose is the wrong format for structured facts.", "excerpt": "This paper validates what we've been building toward. The core issue isn't the idea of context files \u2014 it's that prose is the wrong format for structured facts. AI crushes structured data like package.json but struggles with free-form markdown. Two developers describe the same repo completely differently. There's no schema, no validation, no scoring. Our paper on CERN's Zenodo proposes FAF \u2014 a structured YAML format ", "context": "", "use_case": "", "switched_from": "", "story": "Evaluating AGENTS.md: are they helpful for coding agents?"}, {"id": 750011744, "item_id": 46875734, "url": "https://news.ycombinator.com/item?id=46875734", "by": "csummers", "date": "2026-02-03", "stance": "recommend", "quote": "I recently switched to using only AGENTS.md and SKILLS.  I appreciate the standardization from this perspective.", "excerpt": "I'm developing a new programming language, so I have to provide a way for LLMs to know about and generate code for a language they have not seen (i.e., have no training data for). My tooling was previously adding in AI hints with CLAUDE.md, Cursor Rules, Windsurf Rules, AGENTS.md, etc., but I recently switched to using only AGENTS.md and SKILLS. I appreciate the standardization from this perspective.", "context": "developing a new programming language", "use_case": "giving LLMs hints for a new language", "switched_from": "CLAUDE.md", "story": "Agent Skills"}, {"id": 749944273, "item_id": 46871517, "url": "https://news.ycombinator.com/item?id=46871517", "by": "modernerd", "date": "2026-02-03", "stance": "recommend", "quote": "The AGENTS.md approach provides broad, horizontal improvements", "excerpt": "That's also what Vercel found: > In 56% of eval cases, the skill was never invoked. The agent had access to the documentation but didn't use it. Adding the skill produced no improvement over baseline. > \u2026 > Skills aren't useless. The AGENTS.md approach provides broad, horizontal improvements to how agents work with Next.js across all tasks. Skills work better for vertical, action-specific workflows that users explici", "context": "", "use_case": "", "switched_from": "", "story": "Agent Skills"}, {"id": 739319314, "item_id": 46207457, "url": "https://news.ycombinator.com/item?id=46207457", "by": "evantahler", "date": "2025-12-09", "stance": "neutral", "quote": "- AGENTS.md", "excerpt": "Management of the following projects moves to the Linux Foundation: - MCP - goose - AGENTS.md Learn more @ https://aaif.io/press/linux-foundation-announces-the-formation-of-the-agentic-ai-foundation-aaif-anchored-by-new-project-contributions-including-model-context-protocol-mcp-goose-and-agents-md/", "context": "", "use_case": "", "switched_from": "", "story": "The Linux Foundation Launches the Agentic AI Foundation"}]}