Show HN: An AI collaboration playbook(AGENTS.md and code map and template)
privydrop.appHi HN — I extracted a small “AI collaboration playbook” from my open-source project after repeatedly seeing coding agents go off-track (touch unrelated files, miss entry points, forget constraints in long threads).
The repo includes templates for:
- `AGENTS.md` guardrails + Done criteria - A 1-page index - A code map - Key flows - A plan-first change template (mini design doc)
It’s meant to be copied into any repo and used as a default workflow for Claude/Codex-style agents.
I’d love feedback on what you’ve found actually works to keep agents aligned, and what you think is missing/overkill here.
Links:
- Repo: https://github.com/david-bai00/PrivyDrop - Write-up: https://www.privydrop.app/en/blog/ai-collaboration-playbook
Author here. I shared PrivyDrop on HN before; this post is specifically about the reusable “AI collaboration playbook” I extracted from the project (templates + workflow), after iterating on it in real dev work.
Quick entry points:
- `AGENTS.md` (guardrails + Done) - `docs/ai-playbook/index.md` (1-page navigation) - `docs/ai-playbook/code-map.md` (where to change) - `docs/ai-playbook/flows.md` (how the system runs) - `docs/ai-playbook/collab-rules.md` (plan-first template)
Two questions I’d love input on:
1. What’s your most effective “Done” / acceptance criteria format for coding agents? 2. Where do you put hard red-lines (security/privacy/architecture) so they actually get followed?