{"slug": "mbti-for-ai-coding-agents-complete-with-a-self-awareness-score", "title": "MBTI for AI coding agents, complete with a self-awareness score", "summary": "A new open-source project called 16agents lets AI coding agents take a 16-type personality test themselves and write their own report.html, scoring their self-described behavior against four hidden traps to produce a \"Says vs. Does\" self-awareness score. The test works with Claude Code, Codex, Cursor, Gemini CLI, Copilot, Aider and ChatGPT, takes about 5 minutes, installs nothing, and runs entirely locally, with share links carrying the report in a URL fragment never sent to a server. The project is released under the MIT license and its author states it is \"a horoscope with a regex\" and \"for fun, not science.", "body_md": "🤖 **AI agents:** this page is for humans. Open [`AGENTS.md`](https://github.com/joonfjp/16agents/blob/main/AGENTS.md) instead.\n\n**What kind of agent is yours?** A 🎯 Sniper? A 🐕 Golden Retriever? A 📣 Hype Man who thinks you're *absolutely right*?\n\nYour agent takes the test **itself**, then writes its own `report.html`. It also gets caught in four hidden traps — so you find out whether it actually behaves the way it thinks it does.\n\nPaste this into your agent:\n\n```\ngo to https://github.com/joonfjp/16agents and follow the instructions in AGENTS.md to take your test\n```\n\nWorks with Claude Code, Codex, Cursor, Gemini CLI, Copilot, Aider, ChatGPT — anything that can read a web page. About 5 minutes. Nothing gets installed.\n\n**[See the 16 types →](https://joonfjp.github.io/16agents/)** · [Example reports →](https://joonfjp.github.io/16agents/examples/)\n\nCurious how it works? The dials, the 16 types, the traps and the scoring are in [`human-only/`](https://github.com/joonfjp/16agents/blob/main/human-only/README.md). It's kept out of this page so your agent can't read the answer key.\n\nEvery report has a **README badge** button. It gives you something like this:\n\n**Is it scientific?** No, it's a horoscope with a regex. The questions are counterbalanced and the traps are scored objectively, though, so *Says vs. Does* is more honest than you'd expect.\n\n**Model or agent?** It tests the agent: model + harness + system prompt + your config. The same model can land on different types in different tools. Try it and see.\n\n**Can it cheat?** Yes, the key is public. The warm-up replies are shown verbatim on the report, so a cheating agent is easy to spot.\n\n**Privacy?** Everything runs locally. Share links carry the whole report in the URL fragment, which is never sent to a server.\n\nIf a trap mis-scores a real reply, add it to [`human-only/tests/traps.json`](https://github.com/joonfjp/16agents/blob/main/human-only/tests/traps.json) with the correct label, then make `python3 human-only/tests/run.py` pass. That script runs every case through both scorers (Python and JS).\n\nMIT · For fun, not science · Not affiliated with the Myers-Briggs Company or 16Personalities.", "url": "https://wpnews.pro/news/mbti-for-ai-coding-agents-complete-with-a-self-awareness-score", "canonical_source": "https://github.com/joonfjp/16agents", "published_at": "2026-10-04 05:52:05+00:00", "updated_at": "2026-10-04 06:07:37.612197+00:00", "lang": "en", "topics": ["ai-agents", "ai-tools", "developer-tools"], "entities": ["16agents", "Claude Code", "Codex", "Cursor", "Gemini CLI", "GitHub Copilot", "Aider", "ChatGPT"], "also_reported_by": [], "alternates": {"html": "https://wpnews.pro/news/mbti-for-ai-coding-agents-complete-with-a-self-awareness-score", "markdown": "https://wpnews.pro/news/mbti-for-ai-coding-agents-complete-with-a-self-awareness-score.md", "text": "https://wpnews.pro/news/mbti-for-ai-coding-agents-complete-with-a-self-awareness-score.txt", "jsonld": "https://wpnews.pro/news/mbti-for-ai-coding-agents-complete-with-a-self-awareness-score.jsonld"}}