Articles for people who
ship the stack
Rewrites on React, Node.js, TypeScript and AI. A translated body is shown when it exists. If it does not, you see the English text and a note that says so.
Tagged: agents-md
Rules, Workflow and Sub-Agents: Splitting an AI Agent Plugin for dbt
Why one big instructions file failed, and how AGENTS.md, a spec-driven skill, isolated sub-agents, hooks and Jira MCP each took one job in a dbt workflow.
6 min readAGENTS.md or CLAUDE.md? What 592 Top Repositories Actually Contain
A survey of 592 top GitHub repositories shows CLAUDE.md is mostly a pointer to AGENTS.md, and that hooks, the enforcement layer, are far rarer than the docs.
7 min readWhere Each Instruction Belongs: AGENTS.md, CLAUDE.md and SKILL.md
How the three context files load, why a skill description acts as a gate, what each file should hold, and how to bridge Claude Code and other agents in one repo.
9 min readSpec-Driven Development With AI Coding Agents: A Practical Guide
Spec-driven development with AI coding agents: a four-phase workflow, AGENTS.md and SPEC.md files, multi-agent roles, maturity levels and how to catch drift.
16 min readPrompting OpenAI's Astra Model: Autonomy, Skills, Verification and Stop Rules
Prompting OpenAI's more autonomous Astra model: old habits can hurt. Tune autonomy, instruction priority, style, testing and stop rules, with ready prompts.
14 min readYour AGENTS.md Was Written for a Worse Model: Auditing Prompt Debt
Old AGENTS.md rules outlive the model flaws they patched. Learn to spot prompt debt, trim skills into routers, set permissions and define done before the path.
8 min readCLAUDE.md vs AGENTS.md vs SKILL.md: What Goes Where and Why
CLAUDE.md, AGENTS.md and SKILL.md differ in when they load, their scope and context window cost. A simple way to decide where each rule for Claude Code lives.
7 min read
About these articles
Request a 24h estimate
Need the same stack in a production operator layer? Send the brief — estimate within 24 hours.