Folder structure for coding agents: give your agent context instead of re-explaining
every · x · 2026-09-10
Advice on structuring project folders so agents inherit your way of working instead of re-explaining every chat. Setup: instructions + project knowledge + incident history + specialized skills.
- Put conventions (naming, tests, deploy) in CLAUDE.md, replacing boilerplate with real decisions
- Keep architecture docs in-repo with a reading order for new agents
- Preserve runbooks and incident reports so agents inherit past lessons
- Separate folders by responsibility — feature-building agents need different context than incident-investigation agents
- Run each workflow yourself until predictable before adding task-assignment systems, or you'll multiply stale and duplicate tasks
More from coding & agent
- High-signal evals beat harness tweaks beat post-training: a layered agent methodology — abeirami · 2026-09-10
- Tradooor Mirror mirrors leading traders' consensus positioning into Hyperliquid perps — templecrash · 2026-09-10
- Cognition's Devin agents factor RSA-260, set new record; RSA-1024 cost pegged at ~$30M — StefanoGogioso · 2026-09-10
- Harmonic's Aristotle: an AI agent that proves software correct with machine-checked proofs — satnam6502 · 2026-09-10
- OpenAI Mobilized 250+ People to Build a "Defense Factory" of AI Agents That Find and Fix Vulnerabilities — OpenAI · 2026-09-10
- LangChain NYC meetup to teach voice agent evaluation across execution, outcomes and experience — LangChain · 2026-09-10