LLM: Devise a plan A developer's blog post suggests that appending 'Devise a plan' to prompts is sufficient for large language models to plan before editing, eliminating the need for dedicated plan modes in tools like OpenCode and Claude Code. The post includes a sample session where the model outlines a step-by-step plan to expand blog post connections to include tag-based links, demonstrating the approach's effectiveness. ♠ There’s no need for plan https://opencode.ai/docs/ :~:text=OpenCode%20has%20a%20Plan%20mode%20that%20disables%20its%20ability%20to%20make%20changes%20and%20instead%20suggest%20how%20it%E2%80%99ll%20implement%20the%20feature. mode https://code.claude.com/docs/en/common-workflows plan-before-editing . Sandboxing https://perrotta.dev/2026/02/cco-claude-condom-sandbox/ + prompt engineering is enough. End your prompt with Devise a plan …and let the 2026 Gen AI models flow by themselves. Here’a a sample session: User : some of my blog posts e.g. https://perrotta.dev/2026/07/anki-archive-a-deck/ have "connections" this is great, but it includes only direct links I wanted to expand connections to include a couple of posts that share tags too They should be visually distinct from direct links direct links should stand out better Devise a plan Assistant : ... Current Connections graph reads only backlinks and outlinks. Existing related data mixes links, tags, categories, and title words. It cannot guarantee two tag-based results. Plan: 1. Precompute tag connections - Add tag related to ci/precompute links.py. - Select up to two posts with shared tags. - Exclude current post, backlinks, and outlinks. - Rank by shared-tag count, then newest date. - Store post IDs in data/links.json. 2. Extend mini graph - Read tag related in layouts/partials/mini-graph.html. - Keep incoming links on left. - Keep outgoing links on right. - Place tag connections below current post. - Use no arrows because tag relationships have no direction. - Include shared tag names in each SVG