GSD (Get Shit Done)
Shares rank 11 of 23 agent skills by recommenders
People recommend it for running multi-step AI coding work in phases with fresh context, so the context never needs compacting. Critics say it uses many tokens and suits only large projects.
People recommend it for running multi-step AI coding work in phases with fresh context, so the context never needs compacting. Critics say it uses many tokens and suits only large projects.
26 people gave an opinion
- recommend it
- 15
- criticize it
- 11
- approval share
- 58%
Recommended in 9 of 13 months
- November 2025: not recommended
- December 2025: not recommended
- January 2026: recommended
- February 2026: recommended
- March 2026: recommended
- April 2026: recommended
- May 2026: recommended
- June 2026: recommended
- July 2026: recommended
- August 2026: recommended
- September 2026: recommended
- October 2026: not recommended
- November 2026: not recommended (month in progress)
Why it doesn’t carry the badge
- 15 people recommend itNeeds 10 or more, met.
- 1.3 recommenders for every criticNeeds 2 to 1 or better, not met.
- Recommended in 9 of 13 monthsNeeds 4 or more, met.
The same three rules apply to every product, and the badge can’t be bought. How the badge works
What people say about it
The reasons people give, with the number of comments that give each one. Open a reason to read what they said.
Why people recommend it
Each mark is one comment
Clears context between phases automatically
“i agree that GSD is doing something more complete — full execution orchestration with context rotation”
Comment from 23 May 2026 in “Show HN: I Made a Claude Skill for SDD” “it will launch everything as a phase and steps and clear context for you so you never compact”
Comment from 16 Feb 2026 in “Ask HN: Why is my Claude experience so bad? What am I doing wrong?” Builds large projects into working code
“But it was the difference between "neat demo" and "111,000 lines of working Rust."”
Comment from 17 Feb 2026 in “I Let Opus 4.6 and GSD Build a Programming Language” “one shot GSD in autonomous mode usually nails it”
Comment from 31 Aug 2026 in “Why do I lose my passion and want to do nothing?” Praised as a useful framework
“I do like GSD[1] though, it's been a great addition to the stack.”
Comment from 17 Feb 2026 in “Evaluating AGENTS.md: are they helpful for coding agents?” “I have very much enjoyed GSD as a framework within claude code”
Comment from 23 Jun 2026 in “Ask HN: How do you make the LLM generate good code?” “GSD and spec-kit are great tools.”
Comment from 18 Feb 2026 in “Stop prompting. Let the AI interview you to build specs”
What people warn about
Each mark is one comment
Burns many tokens
“GSD is great for new projects but it burns through tokes at quite the rate.”
Comment from 24 May 2026 in “Show HN: I Made a Claude Skill for SDD” “GSD is quite OK but very token hungry”
Comment from 17 Sep 2026 in “OpenSpec – A lightweight and configurable AI spec framework” “they have too many stages and waste tokens”
Comment from 25 Apr 2026 in “I Cancelled Claude: Token Issues, Declining Quality, and Poor Support” - Comment from 16 Sep 2026 in “OpenSpec – A lightweight and configurable AI spec framework”
Too much process for small projects
“GSD was great but probably for gigantic projects only.”
Comment from 22 May 2026 in “Show HN: Spec-Driven Development Workflow for Claude Code” “this is about 10,000x too much stuff for the equivalent feature set to a markdown file that your agent updates.”
Comment from 11 Oct 2026 in “Show HN: GSD Task Manager – an MCP server that gives your AI agent a task list” “Over time GSD grown into beast which is suitable for huge + size projects only”
Comment from 6 Jun 2026 in “Ask HN: What is your (AI) dev tech stack / workflow? (June 2026)” Loss of control over the agent
“As time went on I felt like the organization was kind of an illusion.”
Comment from 24 Jan 2026 in “Claude Code's new hidden feature: Swarms” “the control I initially felt over the model with all these markdown documents”
Comment from 20 Jan 2026 in “Don't Waste Your Back Pressure”
Other agent skills people recommend
The four most recommended other agent skills, with the same counts for each, so you can compare like for like. The tick on each bar marks the 2 to 1 line the badge needs.
| Product | Recommend | Criticize | Approval | Months | Owned | Badge |
|---|---|---|---|---|---|---|
| Superpowers | 138 | 72 | 66% | 12 | 4 mo7 owners | — |
| Claude Skills | 59 | 26 | 69% | 11 | — | Approved |
| grill-me skill by Matt Pocock | 39 | 2 | 95% | 8 | — | Approved |
| Get Shit Done | 31 | 32 | 49% | 7 | — | — |
| GSD (Get Shit Done)This page | 15 | 11 | 58% | 9 | — | — |
What people said
26 of the 30 comments that mention it, newest first. Each links to the original comment.
“this is about 10,000x too much stuff for the equivalent feature set to a markdown file that your agent updates.”
“plugins like GSD and superpower which I am accustomed too”
“GSD is quite OK but very token hungry”
“mostly they burn more tokens”
“one shot GSD in autonomous mode usually nails it”
“the text in them is useful enough to share”
“I have very much enjoyed GSD as a framework within claude code”
“Over time GSD grown into beast which is suitable for huge + size projects only”
“GSD is great for new projects but it burns through tokes at quite the rate.”
“i agree that GSD is doing something more complete — full execution orchestration with context rotation”
“GSD was great but probably for gigantic projects only.”
“Your results might have gotten worse precisely because you use them”
“they have too many stages and waste tokens”
“using plugins like compound engineering/gsd/superpowers.”
“it manages all that and keeps token use low”
“I wasted like 100$ + so much time trying to debug said crap”
“I recently had a horrible misalignment issue with a 1 agent loop”
“imo these are asking way too much stuff and are just annoying”
“I also advice ignoring any tooling that hides these things from you.”
“There was precious little of what GSD added in terms of value”
“GSD and spec-kit are great tools.”
“I do like GSD[1] though, it's been a great addition to the stack.”
“But it was the difference between "neat demo" and "111,000 lines of working Rust."”
“it will launch everything as a phase and steps and clear context for you so you never compact”
“As time went on I felt like the organization was kind of an illusion.”
“the control I initially felt over the model with all these markdown documents”
Counts come from 1,795,640 Hacker News comments, November 2025 to November 2026. How we count. Report a mistake.