most-capable-agent-system-prompt
A copy-paste system prompt that has your coding agent (Claude Code, Codex, Cursor) build a self-improving agent system for any computer work.
Automatically checked · GitHub checked 2026-11-14

Overview
Left alone, most agent sessions forget everything between runs, call work done without checking it, and stall once a task is finished. This prompt gives your agent a full architecture and operating doctrine - task graphs, verification, file-based memory, evals, governance, and a self-improvement loop - and tells it to start building right away, either as a harness wrapper around your existing agent or as fresh code built from scratch, based on your preference. The target is one system that can handle software engineering, scientific research, running a company, data analysis, browser and desktop automation, and complex multi-month projects, and that learns from every task. - Inspect your workspace, ask only the questions it cannot answer itself, and write a runtime capability matrix and an implementation contract. - Set up a file-based project operating system (AGENTS.md, plan.md, tasks.md, knowledge.md, FAILURE.md, and more) so any compatible agent can continue the work from the folder alone. - Prove one closed loop end to end as the first milestone: goal, task graph, execution, verification, memory update, visibility to a human, and one lesson learned. - Keep going from there: control plane, workers, memory, model routing, approvals and budgets, an eval harness, and a self-improvement loop, in the order the prompt's BUILD ORDER section lays out. Try a working example: Apps and starter projects · Full portfolio and concepts · Open-source tools. A real website QA check. The demo site’s HTTPS page worked, and its old HTTP URL still served the page. Watch the 30-second redirect walkthrough and run the same free check on your site. For AI crawler access, save the public HTML and robots.txt, then verify any crawler visits in your CDN or server logs. Follow the AI crawler access checklist. If you maintain several client sites, Betterloop Pro gives you daily insight runs across up to five projects for $19 a month plus applicable tax. See Pro pricing and how to start. For AI and ML news, read MyFeed's public topic feed or add it to your RSS reader. - Letta Memory-first stateful agents with durable identity and explicit memory primitives.