{"slug": "gsd", "name": "GSD", "category": "ai-coding", "category_name": "AI coding tools", "description": "", "recommenders": 4, "commenters": 9, "warners": 1, "score": 3.137, "rising": 1.35, "first": "2026-04-06", "latest": "2026-10-28", "why": "in the Claude Code realm I use GSD and it manages all that and keeps token use low.", "why_is_quote": true, "has_verdict": false, "sentiment": {"recommend": 4, "neutral": 2, "compare": 2, "warn": 2}, "spark": [0, 0, 0, 0, 0, 1, 0, 1, 0, 1, 1, 0], "listed": true, "loved": [], "caveat": "", "short_quote": "in the Claude Code realm I use GSD and it manages all that and keeps token use low.", "icon": true, "domain": null, "github_repo": "github.com/open-gsd/gsd-core", "official_url": "https://github.com/open-gsd/gsd-core", "pricing": "", "aliases": ["GSD"], "verdict": null, "praise": [{"label": "", "summary": "", "quotes": [{"id": 796397251, "item_id": 49774828, "url": "https://news.ycombinator.com/item?id=49774828", "by": "JoyenBenitto", "date": "2026-09-20", "stance": "recommend", "quote": "plugins like GSD and superpower which I am accustomed too", "excerpt": "Yeah I have been using it to automate almost everything, even my gitlab ci's sometimes when those ci fails I just ask claude to use glab cli to figure things out on it's own. I have used codex and antigravity but not a huge fan of them. I feel my I am too much in favour of claude also because of plugins like GSD and superpower which I am accustomed too.", "context": "", "use_case": "Claude Code plugin", "switched_from": "", "story": "Ask HN: What happens when Claude Code goes away?"}, {"id": 792127186, "item_id": 49507949, "url": "https://news.ycombinator.com/item?id=49507949", "by": "mstaoru", "date": "2026-08-31", "stance": "recommend", "quote": "one shot GSD in autonomous mode usually nails it", "excerpt": "It is very difficult. I consider myself reasonably skilled in AI usage (multiple harnesses, skills, MCP, etc). I use only the latest models: Opus 5, GPT 5.6 Sol. I experiment with different plan-build-evaluate frameworks like GSD, OpenSpec, Superpowers. I have a reasonable AGENTS.md without much cruft: test coverage ~80%, ASD-STE100 English, use uv - things like that. I can churn out single-use scripts and micro-proj", "context": "experienced AI user", "use_case": "small scripts and micro-projects", "switched_from": "", "story": "Why do I lose my passion and want to do nothing?"}, {"id": 778218368, "item_id": 48638648, "url": "https://news.ycombinator.com/item?id=48638648", "by": "zachmorrison", "date": "2026-06-22", "stance": "recommend", "quote": "I have very much enjoyed GSD as a framework within claude code", "excerpt": "I have very much enjoyed GSD as a framework within claude code https://github.com/open-gsd/gsd-core", "context": "", "use_case": "generating good code with LLMs", "switched_from": "", "story": "Ask HN: How do you make the LLM generate good code?"}, {"id": 762604048, "item_id": 47662753, "url": "https://news.ycombinator.com/item?id=47662753", "by": "nitroedge", "date": "2026-04-06", "stance": "recommend", "quote": "in the Claude Code realm I use GSD and it manages all that and keeps token use low.", "excerpt": "in the Claude Code realm I use GSD and it manages all that and keeps token use low. Plus it writes to a file so memory is stored so I can type /clear and the token count resets yet it still can remember where I left off for the next work. Check it out here: https://github.com/gsd-build/get-shit-done", "context": "", "use_case": "token management and memory in Claude Code", "switched_from": "", "story": "I stopped hitting Claude's usage limits \u2013 things I changed"}]}], "caveats": [{"label": "", "summary": "", "quotes": [{"id": 774761041, "item_id": 48422565, "url": "https://news.ycombinator.com/item?id=48422565", "by": "sermakarevich", "date": "2026-06-06", "stance": "warn", "quote": "Over time GSD grown into beast which is suitable for huge + size projects only producing gigantic specs and burning too many tokens", "excerpt": "I looked at most of those, including kiro and tessl. Was early user of GSD when it was suitable for mid+ size projects. Over time GSD grown into beast which is suitable for huge + size projects only producing gigantic specs and burning too many tokens for most of the tasks. So I decided to created my own, with set of steps I need and specs I want. After few presentations of sddw to different companies, most important", "context": "", "use_case": "spec-driven development", "switched_from": "", "story": "Ask HN: What is your (AI) dev tech stack / workflow? (June 2026)"}, {"id": 767051904, "item_id": 47940744, "url": "https://news.ycombinator.com/item?id=47940744", "by": "bushido", "date": "2026-04-28", "stance": "warn", "quote": "Oh, I use GSD or I use Superpowers and my results have gotten worse", "excerpt": "I think the main thing which a lot of these articles miss is it's not just your Agents.md which can give you a model upgrade or the inverse. But everything your harness looks at could be this. So the skills in your code base, the commands that you've added, the memories that were auto created, they all work towards improving or completely destroying your productivity. And most of it is hidden. You hear people talk ab", "context": "", "use_case": "AI coding agent workflow", "switched_from": "", "story": "A good AGENTS.md is a model upgrade. A bad one is worse than no docs at all"}]}], "who": [{"by": "mstaoru", "context": "works on a large software project at work", "url": "https://news.ycombinator.com/item?id=49723780", "date": "2026-09-16"}], "tags": [], "use_cases": ["spec-driven development", "spec-driven agentic development", "agent project context management", "claude code plugin", "managing ai coding projects", "ai coding workflow"], "compared": [{"slug": "superpowers", "name": "Superpowers", "co": 3, "switched_from": 0, "switched_to": 0}, {"slug": "claude-code", "name": "Claude Code", "co": 3, "switched_from": 0, "switched_to": 0}, {"slug": "openspec", "name": "OpenSpec", "co": 2, "switched_from": 0, "switched_to": 0}, {"slug": "gpt-sol", "name": "GPT Sol", "co": 2, "switched_from": 0, "switched_to": 0}], "makers": [], "threads": [{"url": "https://news.ycombinator.com/item?id=50260571", "title": "Show HN: Specification First Agentic Development Plugin and Prove", "mentions": 1}, {"url": "https://news.ycombinator.com/item?id=49945933", "title": "Agents don't need memory, they need documentation", "mentions": 1}, {"url": "https://news.ycombinator.com/item?id=49755575", "title": "Ask HN: What happens when Claude Code goes away?", "mentions": 1}, {"url": "https://news.ycombinator.com/item?id=49734264", "title": "OpenSpec \u2013 A lightweight and configurable AI spec framework", "mentions": 1}, {"url": "https://news.ycombinator.com/item?id=49715361", "title": "Ask HN: Where is all of the AI coded software?", "mentions": 1}, {"url": "https://news.ycombinator.com/item?id=49505014", "title": "Why do I lose my passion and want to do nothing?", "mentions": 1}], "sentiment_by_month": {"2025-11": {}, "2025-12": {}, "2026-01": {}, "2026-02": {}, "2026-03": {}, "2026-04": {"recommend": 1, "warn": 1}, "2026-05": {}, "2026-06": {"warn": 1, "recommend": 1}, "2026-07": {}, "2026-08": {"recommend": 1}, "2026-09": {"neutral": 2, "recommend": 1}, "2026-10": {"compare": 2}}, "quotes": [{"id": 804370096, "item_id": 50273131, "url": "https://news.ycombinator.com/item?id=50273131", "by": "megool", "date": "2026-10-28", "stance": "compare", "quote": "How does it compare with GSD?", "excerpt": "Seems straight forward and easy to use. How does it compare with GSD? https://github.com/open-gsd/gsd-core", "context": "", "use_case": "spec-driven agentic development", "switched_from": "", "story": "Show HN: Specification First Agentic Development Plugin and Prove"}, {"id": 799298160, "item_id": 49956135, "url": "https://news.ycombinator.com/item?id=49956135", "by": "MaurizioFratell", "date": "2026-10-04", "stance": "compare", "quote": "how is this different or better than existing context and info-about-the-project management systems like for example GSD (formerly get shit done)", "excerpt": "I love it! Genuine question: how is this different or better than existing context and info-about-the-project management systems like for example GSD (formerly get shit done) and others?", "context": "", "use_case": "agent project context management", "switched_from": "", "story": "Agents don't need memory, they need documentation"}, {"id": 796397251, "item_id": 49774828, "url": "https://news.ycombinator.com/item?id=49774828", "by": "JoyenBenitto", "date": "2026-09-20", "stance": "recommend", "quote": "plugins like GSD and superpower which I am accustomed too", "excerpt": "Yeah I have been using it to automate almost everything, even my gitlab ci's sometimes when those ci fails I just ask claude to use glab cli to figure things out on it's own. I have used codex and antigravity but not a huge fan of them. I feel my I am too much in favour of claude also because of plugins like GSD and superpower which I am accustomed too.", "context": "", "use_case": "Claude Code plugin", "switched_from": "", "story": "Ask HN: What happens when Claude Code goes away?"}, {"id": 795873505, "item_id": 49742094, "url": "https://news.ycombinator.com/item?id=49742094", "by": "_blk", "date": "2026-09-17", "stance": "neutral", "quote": "GSD is quite OK but very token hungry", "excerpt": "Interesting project. How does it compare to GSD (opengsd.net)? Just from the command set it seems a lot lighter but also less expressive. GSD is quite OK but very token hungry (~4x but it buys traceability and has quite a powerful autonomous mode) I use gsd-meta-manager to manage multiple GSD projects in parallel without having to use a skill to query each project individually to see where they're at. Does openspec h", "context": "", "use_case": "managing AI coding projects", "switched_from": "", "story": "OpenSpec \u2013 A lightweight and configurable AI spec framework"}, {"id": 795580481, "item_id": 49723780, "url": "https://news.ycombinator.com/item?id=49723780", "by": "mstaoru", "date": "2026-09-16", "stance": "neutral", "quote": "Yes I use GSD and code graph etc.", "excerpt": "> If coding is a nearly solved problem, if AI is making it so easy to make anything AI is very optimized to producing code, but not there (yet? ever?) in making products. Show me a serious software made entirely with AI. There's no AI SolidWorks, AutoCAD, MacOS. And there lies a contradiction: AI is making it easy to start and produce copious amounts of code that looks okay-ish. We start releasing a product and notic", "context": "works on a large software project at work", "use_case": "AI coding workflow", "switched_from": "", "story": "Ask HN: Where is all of the AI coded software?"}, {"id": 792127186, "item_id": 49507949, "url": "https://news.ycombinator.com/item?id=49507949", "by": "mstaoru", "date": "2026-08-31", "stance": "recommend", "quote": "one shot GSD in autonomous mode usually nails it", "excerpt": "It is very difficult. I consider myself reasonably skilled in AI usage (multiple harnesses, skills, MCP, etc). I use only the latest models: Opus 5, GPT 5.6 Sol. I experiment with different plan-build-evaluate frameworks like GSD, OpenSpec, Superpowers. I have a reasonable AGENTS.md without much cruft: test coverage ~80%, ASD-STE100 English, use uv - things like that. I can churn out single-use scripts and micro-proj", "context": "experienced AI user", "use_case": "small scripts and micro-projects", "switched_from": "", "story": "Why do I lose my passion and want to do nothing?"}, {"id": 778218368, "item_id": 48638648, "url": "https://news.ycombinator.com/item?id=48638648", "by": "zachmorrison", "date": "2026-06-22", "stance": "recommend", "quote": "I have very much enjoyed GSD as a framework within claude code", "excerpt": "I have very much enjoyed GSD as a framework within claude code https://github.com/open-gsd/gsd-core", "context": "", "use_case": "generating good code with LLMs", "switched_from": "", "story": "Ask HN: How do you make the LLM generate good code?"}, {"id": 776289152, "item_id": 48518072, "url": "https://news.ycombinator.com/item?id=48518072", "by": "sermakarevich", "date": "2026-06-13", "stance": "neutral", "quote": "Started with GSD and later implemented my own", "excerpt": "I use SDD since Feb for all my mid+ size projects. This works great for me from many angles: - two levels of task decomposition - first is multiple steps in workflow, second is task decomposition into multiple subtasks - help to keep session context clean and focused, thus improving adherence, reducing cost - multiple levels of model understanding verification - you verify first requirements step, then design step an", "context": "", "use_case": "spec-driven development", "switched_from": "GSD", "story": "Ask HN: Are you using Spec Driven Development?"}, {"id": 774761041, "item_id": 48422565, "url": "https://news.ycombinator.com/item?id=48422565", "by": "sermakarevich", "date": "2026-06-06", "stance": "warn", "quote": "Over time GSD grown into beast which is suitable for huge + size projects only producing gigantic specs and burning too many tokens", "excerpt": "I looked at most of those, including kiro and tessl. Was early user of GSD when it was suitable for mid+ size projects. Over time GSD grown into beast which is suitable for huge + size projects only producing gigantic specs and burning too many tokens for most of the tasks. So I decided to created my own, with set of steps I need and specs I want. After few presentations of sddw to different companies, most important", "context": "", "use_case": "spec-driven development", "switched_from": "", "story": "Ask HN: What is your (AI) dev tech stack / workflow? (June 2026)"}, {"id": 767051904, "item_id": 47940744, "url": "https://news.ycombinator.com/item?id=47940744", "by": "bushido", "date": "2026-04-28", "stance": "warn", "quote": "Oh, I use GSD or I use Superpowers and my results have gotten worse", "excerpt": "I think the main thing which a lot of these articles miss is it's not just your Agents.md which can give you a model upgrade or the inverse. But everything your harness looks at could be this. So the skills in your code base, the commands that you've added, the memories that were auto created, they all work towards improving or completely destroying your productivity. And most of it is hidden. You hear people talk ab", "context": "", "use_case": "AI coding agent workflow", "switched_from": "", "story": "A good AGENTS.md is a model upgrade. A bad one is worse than no docs at all"}, {"id": 762604048, "item_id": 47662753, "url": "https://news.ycombinator.com/item?id=47662753", "by": "nitroedge", "date": "2026-04-06", "stance": "recommend", "quote": "in the Claude Code realm I use GSD and it manages all that and keeps token use low.", "excerpt": "in the Claude Code realm I use GSD and it manages all that and keeps token use low. Plus it writes to a file so memory is stored so I can type /clear and the token count resets yet it still can remember where I left off for the next work. Check it out here: https://github.com/gsd-build/get-shit-done", "context": "", "use_case": "token management and memory in Claude Code", "switched_from": "", "story": "I stopped hitting Claude's usage limits \u2013 things I changed"}]}