Harnesses
The agent runners themselves: what each one does, its configuration, its permission model, and where it breaks.
-
Coding agent security: prompt injection, MCP servers, and secrets
Prompt injection via tool results, MCP server trust, and secrets in config: what the Claude Code, Codex, and Gemini CLI docs commit to, plus an auditor to run.
-
What is a coding-agent harness? The loop, tools, gate, and context
A coding-agent harness is the loop around the model. Here is what each part does, read from three real harnesses, with a 100-line runnable version you can inspect.
-
MCP server tutorial in Python: a stdio server from scratch
What the Model Context Protocol changes for coding agents, the JSON-RPC on the wire, and a dependency-free Python stdio server exercised with a scripted client.
-
Claude Code and Codex headless: running a coding agent in CI safely
The flags for non-interactive Claude Code and Codex CLI runs, the caps that bound a job, the risks the docs name, and a CI wrapper exercised in dry-run mode.
-
CLAUDE.md, AGENTS.md, and .cursor/rules: what goes in a context file
Where each coding agent looks for standing instructions, how the files load and merge, the size limits, and an audit script that finds every context file in a repo.
-
Claude Code vs Codex vs Gemini CLI: what an agent may run
The permission models of Claude Code, Codex CLI, Gemini CLI, the OpenHands SDK, and Omnigent, read from their docs on 2026-09-05, with a working settings file.