AI agent prompts

74 prompts

Prompts for coding agents and agent workflows, from Claude Code, Codex and Cursor to multi-agent pipelines. They read like task briefs: the goal, the scope, the tools allowed and the checks that prove the work is done.

6 results

  • 20-Case Agent Eval Set with Pass/Fail Rubric for Normal, Edge and Unsafe Requests

    Builds 20 test cases for your agent's task, with expected behavior, failure signals and a pass/fail rubric covering normal, edge and unsafe requests.

  • Agent Tool Names, Descriptions and JSON Schemas from API Docs

    Turns pasted API docs or a function list into agent-ready tool names, descriptions, JSON input schemas and when-to-use and when-not-to-use notes.

  • Codebase Tour for a Specific Task

    Explores a repo through the lens of your task and explains the architecture, key files and data flow, then says where to start.

  • Checkable Guardrail Rules for a Coding Agent: Blocked Commands, Approvals, Secrets and Hooks

    Produces a set of testable guardrail rules for your coding agent, covering blocked commands, approval gates, secret handling and hook checks.

  • Subagent Roster Designer for Your Coding Project

    Produces a 3-5 subagent roster with system prompts, minimal tool permissions, model tiers and explicit handoff rules for your project.

  • Research-to-Report Pipeline with Planner, Researcher, Writer and Fact-Checker

    Designs a four-agent pipeline for your report type with each agent's prompt, inputs, outputs and handoff format.

About AI agent prompts

How is an agent prompt different from a chat prompt?

An agent acts: it reads files, runs commands and edits code. So the prompt sets limits and a way to verify the result, not only the answer you want.

Which agents do these prompts work with?

Coding agents such as Claude Code, Codex, Cursor and Copilot's agent mode, plus prompts for designing your own multi-agent pipelines. Each prompt lists its tools.

Should I review what the agent does?

Yes. Run agents in a branch or a sandbox, read the diff and the commands they ran, and keep approval on for anything that deletes data or deploys.