{
  "id": 20302592,
  "title": "My daily.dev plugin was rejected for two bugs. A real test run taught me three more.",
  "url": "https://urgent.news/2026/11/16/my-daily-dev-plugin-was-rejected-for-two-bugs-a-real-test-run-taught",
  "topic": "tech",
  "section": "Tech",
  "published": "2026-11-16T17:18:30.000Z",
  "source": {
    "name": "Dev.to",
    "slug": "dev-to",
    "url": "https://dev.to/dio77799/my-dailydev-plugin-was-rejected-for-two-bugs-a-real-test-run-taught-me-three-more-i5a"
  },
  "original_language": "en",
  "account": "I developed a plugin for the daily.dev marketplace called Agent Stack Radar. This SKILL.md is followed by a coding agent once a week. It analyzes the most-discussed daily.dev posts on Claude Code, MCP, and coding agents, and returns up to five actionable items, each with its source, on what to fix, try, or watch.\n\nInitially, the plugin was rejected by reviewers who pointed out two bugs. The first issue was a wrong parameter over REST, where the tag search used \"?query=\" instead of the correct parameter \"q\". The second issue was the misuse of requests budget. The SKILL.md promised to limit requests, but the developer hadn't verified if the promised limits matched what the agent actually did.\n\nAfter fixing these bugs and adding request budgeting, the developer rewrote the plugin's steps to prevent request drift. The agent now keeps a running count of requests and never exceeds a maximum of 22. The developer also compared every REST path against the official API spec and added tests for both REST and MCP paths separately.\n\nUpon a real test run, the developer discovered three more issues. First, topics with several words return no results. Second, fetching the comments of a post with zero comments wastes a request. Finally, the developer realized that fetching posts only when the summary is missing can save requests.\n\nIn total, a default run uses fewer than 19 requests, saving time and resources. The developer also learned that comments often reveal valuable insights, such as improving security advice based on user feedback.\n\nThe plugin was approved on November 10 and can be found at https://daily.dev/marketplace/XkkaNAkpy. The developer aims to write the brief in Spanish and create a public repository for developers who use skills for agents. They advise checking that what a SKILL.md promises matches the agent's actual behavior, including limits and endpoints.",
  "summary": "I built a plugin for the daily.dev marketplace called Agent Stack Radar. It's a SKILL.md that a coding agent follows once a week. It reads the most discussed daily.dev posts on Claude Code, MCP and coding agents, reads their comments, and gives back up to five things to fix, try or watch, each with its source. The first version was rejected. The reviewers were right on both points, and fixing it…",
  "key_points": [
    "Plugin rejected for two bugs: wrong REST parameter and misuse of requests budget",
    "Developer fixed bugs, added request budgeting and request count limiting"
  ],
  "editors_take": "Rigorous testing and alignment between agent promises and actual API behavior transform initial technical rejections into more efficient, resource-conscious tools for the daily.dev marketplace.",
  "illustration": null,
  "coverage": {
    "outlets": 1,
    "also_reported_by": []
  },
  "ai_generated": true,
  "disclaimer": "Summaries, key points and the editor’s take are written by software from other outlets’ reporting and may contain errors — always check the linked original."
}