
AGENTS.md Files Don't Move Coding Agent Correctness: A 288-Run Ablation
AGENTS.md and context files do not measurably change coding agent correctness in a 288-run Claude Code and Codex ablation. Failures were implementation skill.
235 articles - page 5 of 20

AGENTS.md and context files do not measurably change coding agent correctness in a 288-run Claude Code and Codex ablation. Failures were implementation skill.

Microsoft's study of Claude Code and GitHub Copilot CLI found about 24% more merged PRs among adopters. The bigger lesson is rollout design, not magic.

Agent-Manager wraps tmux into a Go TUI that groups AI coding agents by project, shows live status for each, and lets you answer blocked agents or review their changes without attaching to their terminal.

Agent-Manager, Pane, and Golutra compared: three tools for running multiple CLI coding agents in parallel, by architecture, agent support, and workflow fit.

Fable 5 effort levels vs switching models: effort spends more of one model's ceiling, a model switch buys a new one. When to move each dial.

AI coding agent security models compared: how Claude Code, Cursor, Codex, Copilot, Aider and Windsurf handle permissions, sandboxing and prompt injection.

Anthropic cut over 80% of Claude Code's system prompt for Claude 5 models with no coding eval loss. The new context engineering rules and what HN thinks.

Codex and Claude Code July 2026 updates compared: why approval modes, resumable work, MCP auth, artifacts and review surfaces now matter as much as models.

Anthropic removed over 80% of Claude Code's system prompt for Claude 5 models. Here is how the rules changed and what it means for your CLAUDE.md files, skills, and system prompts.

Open Design, an open-source Apache-2.0 app, turns a live website into a DESIGN.md that Cursor and Claude Code follow: colors, typography, spacing, and voice.

Self-improving agents explained: reflection loops, Reflexion, LATS tree search, and meta agents, plus how to ground the critique step so the loop converges.

HalluSquatting uses hallucinated repo and skill names to deliver promptware to AI coding agents. How the attack works and the harness controls that stop it.
Showing 49-60 of 234 articles

New tutorials, open-source projects, and deep dives on coding agents - delivered weekly.
Explore 841 topics
Browse All Topics