gsd-lite

Name: gsd-lite
Author: sdsrss

bysdsrss· 3 MCP servers

Stars

How to install gsd-lite?

sdsrss/gsd-lite

$git clone https://github.com/sdsrss/gsd-lite

Installs into the current project.

›Prefer a prompt? Paste this to your agent

Install & use

Install gsd-lite by running `git clone https://github.com/sdsrss/gsd-lite`, then use it for the current task and follow its documentation at https://github.com/sdsrss/gsd-lite.

Files · 1

View on GitHub

README.md

1	# GSD-Lite
2
3	> Get Shit Done — AI orchestration for Claude Code
4
5	GSD-Lite is an AI orchestration tool for [Claude Code](https://docs.anthropic.com/en/docs/claude-code). It combines structured project management with built-in quality discipline: TDD enforcement, anti-rationalization guards, multi-level code review, and automatic failure recovery — all driven by a 12-state workflow machine that keeps multi-phase projects on track.
6
7	Discuss thoroughly, execute automatically. Have as many rounds of requirement discussion as needed. Once the plan is approved, GSD-Lite auto-executes: coding, self-review, independent review, verification, and phase advancement — with minimal human intervention.
8
9	## Features
10
11	### Structured Execution Engine
12	- Phase-based project management — Break work into phases with ordered tasks, dependency tracking, and handoff gates
13	- 12-state workflow machine — `planning → executing_task → reviewing_task → reviewing_phase → completed` with precise transitions, persistent to `state.json`
14	- Automatic task scheduling — Gate-aware dependency resolution determines what runs next
15	- Session resilience — Stop anytime, resume exactly where you left off — crash protection via Stop hook auto-saves state markers
16
17	### Quality Discipline (Built-in, Not Optional)
18	- TDD enforcement — "No production code without a failing test first" baked into every executor dispatch
19	- Anti-rationalization guards — Red-flag checklists inline in every agent prompt, blocking common excuses to skip process
20	- Multi-level code review — L0 self-review / L1 phase-batch review / L2 immediate independent review / phase review retry limit
21	- Contract change propagation — When an API contract changes, downstream tasks automatically invalidate
22
23	### Intelligent Failure Recovery
24	- 3-strike retry with debugger escalation — Failed tasks retry up to 3 times, then auto-dispatch a debugger agent
25	- Systematic root cause analysis — Debugger tests hypotheses, finds root cause, feeds fix guidance back to executor
26	- Blocked task handling — Blocked tasks are parked; execution continues with remaining tasks
27	- Rework propagation — Critical review issues cascade invalidation to dependent tasks
28
29	### Adaptive Review & Parallel Execution
30	- Confidence-based review adjustment — Executor self-assesses confidence (high/medium/low); orchestrator auto-adjusts review level with evidence cross-validation
31	- Impact analysis before review — Reviewer runs impact analysis on multi-file changes to catch missed downstream effects
32	- Parallel task scheduling — Independent tasks within the same phase are identified for concurrent dispatch
33	- Auto PR suggestion — Phase/project completion prompts PR creation with evidence summary
34
35	### Context Protection & Monitoring
36	- Subagent isolation — Each task runs in its own agent context, preventing cross-contamination
37	- Real-time context health monitoring — StatusLine tracks context usage and project phase; composite StatusLine support coexists with other plugins
38	- Session lifecycle hooks — Stop hook writes crash marker; SessionStart injects project status into CLAUDE.md; resume detects non-graceful exits
39	- Evidence-based verification — Every claim backed by command output, not assertions
40	- Research with TTL — Research artifacts include volatility ratings and expiration dates
41
42	### Auto-Update & Version Management
43	- Automatic update checks — Checks GitHub Releases every 24 hours with rate-limit backoff
44	- Version drift detection — Server startup compares running version against disk and plugin registry, warns on mismatch
45	- Smart cache management — Keeps latest 3 cached versions, auto-prunes old entries
46	- Idempotent installer — Reinstall anytime without uninstalling; legacy files auto-cleaned
47
48	## Architecture
49
50	```
51	User → discuss + research (confirm requirements) → approve plan → auto-execute
52	↑ ↑ ↑
53	Interaction 1 Interaction 2 Autonomous execution
54	(code→review→verify→advance)
55	```
56
57	### 6 Commands
58
59	\| Command \| Purpose \|
60	\|---------\|---------\|
61	\| `/gsd:start` \| Interactive start — discuss requirements, research, plan, then auto-execute \|
62	\| `/gsd:prd <input>` \| Start from a requirements doc or description text \|
63	\| `/gsd:resume` \| Resume execution from saved state with workspace validation \|
64	\| `/gsd:status` \| View project progress dashboard (derived from canonical state fields) \|
65	\| `/gsd:stop` \| Save state and pause execution \|
66	\| `/gsd:doctor` \| Diagnostic checks on GSD-Lite installation and project health \|
67
68	### 4 Agents
69
70	\| Agent \| Role \| Built-in Discipline \|
71	\|-------\|------\|---------------------\|
72	\| executor \| Execute a single task (TDD + self-review + checkpoint) \| Iron Law + Red Flags + Deviation Rules \|
73	\| reviewer \| Two-stage review (spec check → quality check) \| Independent verification + Hard Gates \|
74	\| **researc

6 picks

Type

gsd-lite

bysdsrss· 3 MCP servers

Stars

How to install gsd-lite?

sdsrss/gsd-lite

$git clone https://github.com/sdsrss/gsd-lite

Installs into the current project.

›Prefer a prompt? Paste this to your agent

Install & use

Install gsd-lite by running `git clone https://github.com/sdsrss/gsd-lite`, then use it for the current task and follow its documentation at https://github.com/sdsrss/gsd-lite.

Files · 1

View on GitHub

README.md

1	# GSD-Lite
2
3	> Get Shit Done — AI orchestration for Claude Code
4
5	GSD-Lite is an AI orchestration tool for [Claude Code](https://docs.anthropic.com/en/docs/claude-code). It combines structured project management with built-in quality discipline: TDD enforcement, anti-rationalization guards, multi-level code review, and automatic failure recovery — all driven by a 12-state workflow machine that keeps multi-phase projects on track.
6
7	Discuss thoroughly, execute automatically. Have as many rounds of requirement discussion as needed. Once the plan is approved, GSD-Lite auto-executes: coding, self-review, independent review, verification, and phase advancement — with minimal human intervention.
8
9	## Features
10
11	### Structured Execution Engine
12	- Phase-based project management — Break work into phases with ordered tasks, dependency tracking, and handoff gates
13	- 12-state workflow machine — `planning → executing_task → reviewing_task → reviewing_phase → completed` with precise transitions, persistent to `state.json`
14	- Automatic task scheduling — Gate-aware dependency resolution determines what runs next
15	- Session resilience — Stop anytime, resume exactly where you left off — crash protection via Stop hook auto-saves state markers
16
17	### Quality Discipline (Built-in, Not Optional)
18	- TDD enforcement — "No production code without a failing test first" baked into every executor dispatch
19	- Anti-rationalization guards — Red-flag checklists inline in every agent prompt, blocking common excuses to skip process
20	- Multi-level code review — L0 self-review / L1 phase-batch review / L2 immediate independent review / phase review retry limit
21	- Contract change propagation — When an API contract changes, downstream tasks automatically invalidate
22
23	### Intelligent Failure Recovery
24	- 3-strike retry with debugger escalation — Failed tasks retry up to 3 times, then auto-dispatch a debugger agent
25	- Systematic root cause analysis — Debugger tests hypotheses, finds root cause, feeds fix guidance back to executor
26	- Blocked task handling — Blocked tasks are parked; execution continues with remaining tasks
27	- Rework propagation — Critical review issues cascade invalidation to dependent tasks
28
29	### Adaptive Review & Parallel Execution
30	- Confidence-based review adjustment — Executor self-assesses confidence (high/medium/low); orchestrator auto-adjusts review level with evidence cross-validation
31	- Impact analysis before review — Reviewer runs impact analysis on multi-file changes to catch missed downstream effects
32	- Parallel task scheduling — Independent tasks within the same phase are identified for concurrent dispatch
33	- Auto PR suggestion — Phase/project completion prompts PR creation with evidence summary
34
35	### Context Protection & Monitoring
36	- Subagent isolation — Each task runs in its own agent context, preventing cross-contamination
37	- Real-time context health monitoring — StatusLine tracks context usage and project phase; composite StatusLine support coexists with other plugins
38	- Session lifecycle hooks — Stop hook writes crash marker; SessionStart injects project status into CLAUDE.md; resume detects non-graceful exits
39	- Evidence-based verification — Every claim backed by command output, not assertions
40	- Research with TTL — Research artifacts include volatility ratings and expiration dates
41
42	### Auto-Update & Version Management
43	- Automatic update checks — Checks GitHub Releases every 24 hours with rate-limit backoff
44	- Version drift detection — Server startup compares running version against disk and plugin registry, warns on mismatch
45	- Smart cache management — Keeps latest 3 cached versions, auto-prunes old entries
46	- Idempotent installer — Reinstall anytime without uninstalling; legacy files auto-cleaned
47
48	## Architecture
49
50	```
51	User → discuss + research (confirm requirements) → approve plan → auto-execute
52	↑ ↑ ↑
53	Interaction 1 Interaction 2 Autonomous execution
54	(code→review→verify→advance)
55	```
56
57	### 6 Commands
58
59	\| Command \| Purpose \|
60	\|---------\|---------\|
61	\| `/gsd:start` \| Interactive start — discuss requirements, research, plan, then auto-execute \|
62	\| `/gsd:prd <input>` \| Start from a requirements doc or description text \|
63	\| `/gsd:resume` \| Resume execution from saved state with workspace validation \|
64	\| `/gsd:status` \| View project progress dashboard (derived from canonical state fields) \|
65	\| `/gsd:stop` \| Save state and pause execution \|
66	\| `/gsd:doctor` \| Diagnostic checks on GSD-Lite installation and project health \|
67
68	### 4 Agents
69
70	\| Agent \| Role \| Built-in Discipline \|
71	\|-------\|------\|---------------------\|
72	\| executor \| Execute a single task (TDD + self-review + checkpoint) \| Iron Law + Red Flags + Deviation Rules \|
73	\| reviewer \| Two-stage review (spec check → quality check) \| Independent verification + Hard Gates \|
74	\| **researc

6 picks

Type

gsd-lite

How to install gsd-lite?

Related

gsd-lite

How to install gsd-lite?

Related