{
  "id": 5861647,
  "title": "Give Your Coding Agent Eyes",
  "url": "https://urgent.news/2026/09/05/give-your-coding-agent-eyes",
  "topic": "ai",
  "section": "AI",
  "published": "2026-09-05T23:08:58.000Z",
  "source": {
    "name": "Dev.to",
    "slug": "dev-to",
    "url": "https://dev.to/zeflq/give-your-coding-agent-eyes-4mmj"
  },
  "original_language": "en",
  "account": "Coding agents usually start blind when a new session begins, requiring them to rediscover how features work. The AGENTS.md file is typically used to load all relevant information into each session, but it can be too sparse or too resource-intensive. A better approach is to use a catalog system where each feature in the project has a small note associated with it.\n\nAt startup, the agent loads only a table of paths and descriptions for each feature, without loading the actual content. When the agent encounters a task that matches a feature's description, it then reads the corresponding note for more details. The catalog needs to be regenerated periodically, such as every 20 commits or at the end of each sprint, to ensure it remains up-to-date with the current codebase.\n\nThe agent receives contextual information from a pi extension called pi-context, which hooks into the agent's startup routine. This extension walks up from the current working directory to find the project root via AGENTS.md or CLAUDE.md files, recursively scans directories for Markdown files, and keeps only those with a description frontmatter field. The catalog is then formatted and injected into the system prompt.\n\nEach note in the catalog is organized by feature and limited to around 5 KB in size. The description acts as a trigger condition, determining when the agent should load the note based on the task at hand. This approach minimizes the amount of information the agent needs to process and allows for efficient retrieval of relevant information when needed.",
  "summary": "Every coding-agent session starts blind: your agent rediscovers how your features work, and sometimes guesses wrong. AGENTS.md is the usual fix, but it loads every fact into every session — too thin to answer real questions, or too fat to afford. So give the agent a catalog instead. Each feature in your project gets one small note. At startup the agent loads only a table of paths and descriptions…",
  "key_points": [
    "Coding agents begin sessions blind, needing feature rediscovery.",
    "AGENTS.md file loads relevant info, but can be sparse or heavy.",
    "Catalog system improves efficiency by storing feature notes."
  ],
  "editors_take": null,
  "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."
}