🐦 Twitter Post Details

Viewing enriched Twitter post

@omarsar0

Any benefits in using AGENTS dot md files with coding agents? Lots of discussions on this topics lately. Researchers tested OpenAI Codex across 10 repos and 124 PRs, running identical tasks twice (once with AGENTS dot md, once without). The finding is a bit different from what other recent papers report. With AGENTS dot md present, median runtime dropped 28.64% and output tokens fell 16.58%. The agent reached comparable task completion either way, it just got there faster and cheaper with context. One important thing to note: The gains weren't uniform. AGENTS dot md primarily reduced cost in a small number of very high-cost runs rather than uniformly lowering it across all tasks. The file acts more like a guardrail against worst-case thrashing than a universal accelerator. So I guess it depends on the task and requirements. I recommend to not use AGENTS dot md files blindly. If you do, keep them lean. Paper: https://t.co/g2U603Cf8t Learn to build effective AI agents in our academy: https://t.co/U0ZuNA084v

Media 1

📊 Media Metadata

{
  "media": [
    {
      "url": "https://crmoxkoizveukayfjuyo.supabase.co/storage/v1/object/public/media/posts/2028464607753654711/media_0.jpg?",
      "media_url": "https://crmoxkoizveukayfjuyo.supabase.co/storage/v1/object/public/media/posts/2028464607753654711/media_0.jpg?",
      "type": "photo",
      "filename": "media_0.jpg"
    }
  ],
  "processed_at": "2026-03-02T19:01:20.151439",
  "pipeline_version": "2.0"
}

🔧 Raw API Response

{
  "type": "tweet",
  "id": "2028464607753654711",
  "url": "https://x.com/omarsar0/status/2028464607753654711",
  "twitterUrl": "https://twitter.com/omarsar0/status/2028464607753654711",
  "text": "Any benefits in using AGENTS dot md files with coding agents?\n\nLots of discussions on this topics lately.\n\nResearchers tested OpenAI Codex across 10 repos and 124 PRs, running identical tasks twice (once with AGENTS dot md, once without).\n\nThe finding is a bit different from what other recent papers report.\n\nWith AGENTS dot md present, median runtime dropped 28.64% and output tokens fell 16.58%. The agent reached comparable task completion either way, it just got there faster and cheaper with context.\n\nOne important thing to note:\n\nThe gains weren't uniform. AGENTS dot md primarily reduced cost in a small number of very high-cost runs rather than uniformly lowering it across all tasks. The file acts more like a guardrail against worst-case thrashing than a universal accelerator.\n\nSo I guess it depends on the task and requirements. I recommend to not use AGENTS dot md files blindly. If you do, keep them lean.\n\nPaper: https://t.co/g2U603Cf8t\n\nLearn to build effective AI agents in our academy: https://t.co/U0ZuNA084v",
  "source": "Twitter for iPhone",
  "retweetCount": 21,
  "replyCount": 25,
  "likeCount": 133,
  "quoteCount": 5,
  "viewCount": 19624,
  "createdAt": "Mon Mar 02 13:37:04 +0000 2026",
  "lang": "en",
  "bookmarkCount": 125,
  "isReply": false,
  "inReplyToId": null,
  "conversationId": "2028464607753654711",
  "displayTextRange": [
    0,
    280
  ],
  "inReplyToUserId": null,
  "inReplyToUsername": null,
  "author": {
    "type": "user",
    "userName": "omarsar0",
    "url": "https://x.com/omarsar0",
    "twitterUrl": "https://twitter.com/omarsar0",
    "id": "3448284313",
    "name": "elvis",
    "isVerified": false,
    "isBlueVerified": true,
    "verifiedType": null,
    "profilePicture": "https://pbs.twimg.com/profile_images/939313677647282181/vZjFWtAn_normal.jpg",
    "coverPicture": "https://pbs.twimg.com/profile_banners/3448284313/1565974901",
    "description": "",
    "location": "DAIR.AI Academy",
    "followers": 291771,
    "following": 776,
    "status": "",
    "canDm": true,
    "canMediaTag": true,
    "createdAt": "Fri Sep 04 12:59:26 +0000 2015",
    "entities": {
      "description": {
        "urls": []
      },
      "url": {}
    },
    "fastFollowersCount": 0,
    "favouritesCount": 34915,
    "hasCustomTimelines": true,
    "isTranslator": true,
    "mediaCount": 4526,
    "statusesCount": 17382,
    "withheldInCountries": [],
    "affiliatesHighlightedLabel": {},
    "possiblySensitive": false,
    "pinnedTweetIds": [
      "2028464607753654711"
    ],
    "profile_bio": {
      "description": "Building @dair_ai • Prev: Meta AI, Elastic, PhD • New AI learning portal: https://t.co/1e8RZKs4uX",
      "entities": {
        "description": {
          "hashtags": [],
          "symbols": [],
          "urls": [
            {
              "display_url": "academy.dair.ai",
              "expanded_url": "https://academy.dair.ai/",
              "indices": [
                74,
                97
              ],
              "url": "https://t.co/1e8RZKs4uX"
            }
          ],
          "user_mentions": [
            {
              "id_str": "0",
              "indices": [
                9,
                17
              ],
              "name": "",
              "screen_name": "dair_ai"
            }
          ]
        },
        "url": {
          "urls": [
            {
              "display_url": "dair.ai",
              "expanded_url": "https://www.dair.ai/",
              "indices": [
                0,
                23
              ],
              "url": "https://t.co/XQto5ypSIk"
            }
          ]
        }
      }
    },
    "isAutomated": false,
    "automatedBy": null
  },
  "extendedEntities": {
    "media": [
      {
        "display_url": "pic.twitter.com/HXVDA46wFc",
        "expanded_url": "https://twitter.com/omarsar0/status/2028464607753654711/photo/1",
        "ext_media_availability": {
          "status": "Available"
        },
        "features": {
          "large": {
            "faces": []
          },
          "orig": {
            "faces": []
          }
        },
        "id_str": "2028464603815161856",
        "indices": [
          281,
          304
        ],
        "media_key": "3_2028464603815161856",
        "media_results": {
          "id": "QXBpTWVkaWFSZXN1bHRzOgwAAQoAARwmjc9V2zAACgACHCaN0ECb0bcAAA==",
          "result": {
            "__typename": "ApiMedia",
            "id": "QXBpTWVkaWE6DAABCgABHCaNz1XbMAAKAAIcJo3QQJvRtwAA",
            "media_key": "3_2028464603815161856"
          }
        },
        "media_url_https": "https://pbs.twimg.com/media/HCaNz1XbMAAE4-h.png",
        "original_info": {
          "focus_rects": [
            {
              "h": 896,
              "w": 1600,
              "x": 0,
              "y": 0
            },
            {
              "h": 1600,
              "w": 1600,
              "x": 0,
              "y": 0
            },
            {
              "h": 1754,
              "w": 1539,
              "x": 61,
              "y": 0
            },
            {
              "h": 1754,
              "w": 877,
              "x": 394,
              "y": 0
            },
            {
              "h": 1754,
              "w": 1600,
              "x": 0,
              "y": 0
            }
          ],
          "height": 1754,
          "width": 1600
        },
        "sizes": {
          "large": {
            "h": 1754,
            "w": 1600
          }
        },
        "type": "photo",
        "url": "https://t.co/HXVDA46wFc"
      }
    ]
  },
  "card": null,
  "place": {},
  "entities": {
    "hashtags": [],
    "symbols": [],
    "urls": [
      {
        "display_url": "arxiv.org/abs/2601.20404",
        "expanded_url": "https://arxiv.org/abs/2601.20404",
        "indices": [
          930,
          953
        ],
        "url": "https://t.co/g2U603Cf8t"
      },
      {
        "display_url": "academy.dair.ai",
        "expanded_url": "https://academy.dair.ai",
        "indices": [
          1006,
          1029
        ],
        "url": "https://t.co/U0ZuNA084v"
      }
    ],
    "user_mentions": []
  },
  "quoted_tweet": null,
  "retweeted_tweet": null,
  "isLimitedReply": false,
  "article": null
}