{"slug": "get-shit-done", "name": "Get Shit Done", "category": "ai-coding", "category_name": "AI coding tools", "description": "", "recommenders": 3, "commenters": 6, "warners": 2, "score": 1.132, "rising": -0.98, "first": "2026-01-22", "latest": "2026-03-18", "why": "the reliability and almost absence of any error is amazing", "why_is_quote": true, "has_verdict": false, "sentiment": {"recommend": 3, "neutral": 1, "compare": 0, "warn": 2}, "spark": [0, 0, 0, 1, 2, 0, 0, 0, 0, 0, 0, 0], "listed": true, "loved": [], "caveat": "", "short_quote": "the reliability and almost absence of any error is amazing", "icon": true, "domain": null, "github_repo": "github.com/glittercowboy/get-shit-done", "official_url": "https://github.com/glittercowboy/get-shit-done", "pricing": "", "aliases": ["Get Shit Done", "get-shit-done"], "verdict": null, "praise": [{"label": "", "summary": "", "quotes": [{"id": 758887360, "item_id": 47430460, "url": "https://news.ycombinator.com/item?id=47430460", "by": "jdwyah", "date": "2026-03-18", "stance": "recommend", "quote": "But I would recommend it to non coders trying to code.", "excerpt": "I used GSD for a bit. It was helpful for a side project where I constantly forgot where I was in implementation. Helpful to be able to just say \"Do the next thing\" I would imagine that for a non-engineer trying to code it would be quite useful / deliver a better result / less liable to end up in total mess. But for experienced engineers it quickly felt like overkill / claude itself just gets better and better. Partic", "context": "experienced engineer", "use_case": "spec-driven AI development", "switched_from": "", "story": "Get Shit Done: A Meta-Prompting, Context Engineering and Spec-Driven Dev System"}, {"id": 758770176, "item_id": 47423136, "url": "https://news.ycombinator.com/item?id=47423136", "by": "anentropic", "date": "2026-03-18", "stance": "recommend", "quote": "I have been using this a lot lately and ... it's good.", "excerpt": "I have been using this a lot lately and ... it's good. Sometimes annoying - you can't really fire and forget (I tend to regret skipping discussion on any complex tasks). It asks a lot of questions. But I think that's partly why the results are pretty good. The new /gsd:list-phase-assumptions command added recently has been a big help there to avoid needing a Q&A discussion on every phase - you can review and clear up", "context": "", "use_case": "spec-driven development with Claude", "switched_from": "", "story": "Get Shit Done: A Meta-Prompting, Context Engineering and Spec-Driven Dev System"}, {"id": 750558880, "item_id": 46909930, "url": "https://news.ycombinator.com/item?id=46909930", "by": "nitroedge", "date": "2026-02-05", "stance": "recommend", "quote": "the reliability and almost absence of any error is amazing", "excerpt": "You should check out the PAL MCP and then also use this process, its super solid: https://github.com/glittercowboy/get-shit-done The way \"Phases\" are handled is incredible with research then planning, then execution and no context rot because behind the scenes everything is being saved in a State.md file... I'm on Phase 41 of my own project and the reliability and almost absence of any error is amazing. Investigate a", "context": "", "use_case": "phased planning and execution workflow", "switched_from": "", "story": "GPT-5.3-Codex"}]}], "caveats": [{"label": "", "summary": "", "quotes": [{"id": 758782400, "item_id": 47423900, "url": "https://news.ycombinator.com/item?id=47423900", "by": "btiwaree", "date": "2026-03-18", "stance": "warn", "quote": "For what we were trying to build - few small sets of features - using gsd was an overkill.", "excerpt": "I used this for a team hackathon and it took way too much time to build understanding of the codebase, wrote too many agent transcripts and spent way too much token during generation. It also failed multiple times when either generating agent transcript or extracting things from agent transcript - once citing \"The agent transcripts are too complex to extract from\" - quite confounding considering it's the transcript y", "context": "", "use_case": "team hackathon spec-driven development", "switched_from": "", "story": "Get Shit Done: A Meta-Prompting, Context Engineering and Spec-Driven Dev System"}, {"id": 747549520, "item_id": 46721845, "url": "https://news.ycombinator.com/item?id=46721845", "by": "nonethewiser", "date": "2026-01-22", "stance": "warn", "quote": "ultimately I felt like it was all an illusion", "excerpt": "I guess there are probably better worfklows, but I went from raw-dogging it to more structure frameworks like Get Shit Done (GSD) back to raw-dogging it but with lots of use of planning mode. Initially I thought the structure of a framework would be nice. Tracking state, breaking things down into milestones, phases, etc. But ultimately I felt like it was all an illusion. Im not sure it's possible to track and provide", "context": "", "use_case": "structured Claude Code workflow", "switched_from": "", "story": "Ask HN: What is your Claude Code setup? For common or spec projects"}]}], "who": [{"by": "jdwyah", "context": "experienced engineer", "url": "https://news.ycombinator.com/item?id=47430460", "date": "2026-03-18"}], "tags": [], "use_cases": ["spec-driven ai development", "team hackathon spec-driven development", "spec-driven development with claude", "vibe coding workflow", "phased planning and execution workflow", "structured claude code workflow"], "compared": [{"slug": "claude-code", "name": "Claude Code", "co": 1, "switched_from": 0, "switched_to": 1}], "makers": [], "threads": [{"url": "https://news.ycombinator.com/item?id=47417804", "title": "Get Shit Done: A Meta-Prompting, Context Engineering and Spec-Driven Dev System", "mentions": 3}, {"url": "https://news.ycombinator.com/item?id=47309054", "title": "I couldn't figure out Get-Shit-Done, so I let it Vibe Code its own guide", "mentions": 1}, {"url": "https://news.ycombinator.com/item?id=46902638", "title": "GPT-5.3-Codex", "mentions": 1}, {"url": "https://news.ycombinator.com/item?id=46721639", "title": "Ask HN: What is your Claude Code setup? For common or spec projects", "mentions": 1}], "sentiment_by_month": {"2025-11": {}, "2025-12": {}, "2026-01": {"warn": 1}, "2026-02": {"recommend": 1}, "2026-03": {"neutral": 1, "recommend": 2, "warn": 1}, "2026-04": {}, "2026-05": {}, "2026-06": {}, "2026-07": {}, "2026-08": {}, "2026-09": {}, "2026-10": {}}, "quotes": [{"id": 758887360, "item_id": 47430460, "url": "https://news.ycombinator.com/item?id=47430460", "by": "jdwyah", "date": "2026-03-18", "stance": "recommend", "quote": "But I would recommend it to non coders trying to code.", "excerpt": "I used GSD for a bit. It was helpful for a side project where I constantly forgot where I was in implementation. Helpful to be able to just say \"Do the next thing\" I would imagine that for a non-engineer trying to code it would be quite useful / deliver a better result / less liable to end up in total mess. But for experienced engineers it quickly felt like overkill / claude itself just gets better and better. Partic", "context": "experienced engineer", "use_case": "spec-driven AI development", "switched_from": "", "story": "Get Shit Done: A Meta-Prompting, Context Engineering and Spec-Driven Dev System"}, {"id": 758782400, "item_id": 47423900, "url": "https://news.ycombinator.com/item?id=47423900", "by": "btiwaree", "date": "2026-03-18", "stance": "warn", "quote": "For what we were trying to build - few small sets of features - using gsd was an overkill.", "excerpt": "I used this for a team hackathon and it took way too much time to build understanding of the codebase, wrote too many agent transcripts and spent way too much token during generation. It also failed multiple times when either generating agent transcript or extracting things from agent transcript - once citing \"The agent transcripts are too complex to extract from\" - quite confounding considering it's the transcript y", "context": "", "use_case": "team hackathon spec-driven development", "switched_from": "", "story": "Get Shit Done: A Meta-Prompting, Context Engineering and Spec-Driven Dev System"}, {"id": 758770176, "item_id": 47423136, "url": "https://news.ycombinator.com/item?id=47423136", "by": "anentropic", "date": "2026-03-18", "stance": "recommend", "quote": "I have been using this a lot lately and ... it's good.", "excerpt": "I have been using this a lot lately and ... it's good. Sometimes annoying - you can't really fire and forget (I tend to regret skipping discussion on any complex tasks). It asks a lot of questions. But I think that's partly why the results are pretty good. The new /gsd:list-phase-assumptions command added recently has been a big help there to avoid needing a Q&A discussion on every phase - you can review and clear up", "context": "", "use_case": "spec-driven development with Claude", "switched_from": "", "story": "Get Shit Done: A Meta-Prompting, Context Engineering and Spec-Driven Dev System"}, {"id": 756944880, "item_id": 47309055, "url": "https://news.ycombinator.com/item?id=47309055", "by": "dollyxan", "date": "2026-03-09", "stance": "neutral", "quote": "I hit a wall trying to integrate open-code with the get-shit-done (gsd) workflow.", "excerpt": "After years of burnout, stress, and wasting time on tedious, low-challenge tasks, I recently made the switch to Vibe Coding. It\u2019s been a breath of fresh air, but I hit a wall trying to integrate open-code with the get-shit-done (gsd) workflow. The main issue? The project lifecycle, commands, and agents aren't exactly \"beginner-friendly\" documented. I found myself staring at the terminal more than actually shipping. I", "context": "", "use_case": "vibe coding workflow", "switched_from": "", "story": "I couldn't figure out Get-Shit-Done, so I let it Vibe Code its own guide"}, {"id": 750558880, "item_id": 46909930, "url": "https://news.ycombinator.com/item?id=46909930", "by": "nitroedge", "date": "2026-02-05", "stance": "recommend", "quote": "the reliability and almost absence of any error is amazing", "excerpt": "You should check out the PAL MCP and then also use this process, its super solid: https://github.com/glittercowboy/get-shit-done The way \"Phases\" are handled is incredible with research then planning, then execution and no context rot because behind the scenes everything is being saved in a State.md file... I'm on Phase 41 of my own project and the reliability and almost absence of any error is amazing. Investigate a", "context": "", "use_case": "phased planning and execution workflow", "switched_from": "", "story": "GPT-5.3-Codex"}, {"id": 747549520, "item_id": 46721845, "url": "https://news.ycombinator.com/item?id=46721845", "by": "nonethewiser", "date": "2026-01-22", "stance": "warn", "quote": "ultimately I felt like it was all an illusion", "excerpt": "I guess there are probably better worfklows, but I went from raw-dogging it to more structure frameworks like Get Shit Done (GSD) back to raw-dogging it but with lots of use of planning mode. Initially I thought the structure of a framework would be nice. Tracking state, breaking things down into milestones, phases, etc. But ultimately I felt like it was all an illusion. Im not sure it's possible to track and provide", "context": "", "use_case": "structured Claude Code workflow", "switched_from": "", "story": "Ask HN: What is your Claude Code setup? For common or spec projects"}]}