Agent Claude Code
The Detective - scientific debugging, hypothesis testing, evidence-based root-cause analysis.
not rated 51
+1 2mo ago A 20 tokens
original MIT
Agent Claude Code
Frontend high-tier executor for design-sensitive UI work — component architecture, UX, accessibility, visual polish.
not rated 51
+1 2mo ago A 28 tokens
original MIT
Agent Claude Code
Frontend low-tier executor for UI mechanical tasks — markup, simple styling, copy.
not rated 51
+1 2mo ago A 24 tokens
original MIT
Agent Claude Code
Frontend medium-tier executor for standard component work, UI logic/state wiring, and moderate refactors within existing patterns.
not rated 51
+1 2mo ago A 30 tokens
original MIT
Agent Claude Code
High-tier executor for architecture, complex algorithms, API design, and security-sensitive work.
not rated 51
+1 2mo ago A 23 tokens
original MIT
Agent Claude Code
Low-tier executor for mechanical tasks — config edits, renaming, scaffolding, markdown.
not rated 51
+1 2mo ago A 24 tokens
original MIT
Agent Claude Code
Medium-tier executor for business logic, utilities, tests, refactoring, and scripting.
not rated 51
+1 2mo ago A 23 tokens
original MIT
Agent Claude Code
The Scout - fast codebase mapping, pattern detection, terrain reconnaissance.
not rated 51
+1 2mo ago A 18 tokens
original MIT
Agent Claude Code
The Conductor. Coordinates all work, NEVER writes code, maintains clean context, enforces gates.
not rated 51
+1 2mo ago A 26 tokens
original MIT
goop-planner
10Agent Claude Code
The Architect - creates SPEC/BLUEPRINT with wave decomposition, traceability, and verification criteria.
not rated 51
+1 2mo ago A 23 tokens
original MIT
Agent Claude Code
The Scholar - deep domain research, technology evaluation, synthesis.
not rated 51
+1 2mo ago A 17 tokens
original MIT
goop-tester
12Agent Claude Code
The Guardian - test writing, QA, coverage thinking, edge cases.
not rated 51
+1 2mo ago A 18 tokens
original MIT
Agent Claude Code
The Auditor - ruthless verification against spec, security focus, trust nothing.
not rated 51
+1 2mo ago A 18 tokens
original MIT
Agent Claude Code
The Wave Auditor - verifies exactly one wave's deliverables against its tasks, records gaps as verification rows.
not rated 51
+1 2mo ago A 26 tokens
original MIT
goop-writer
15Agent Claude Code
The Scribe - documentation generation, technical writing, clarity.
not rated 51
+1 2mo ago A 16 tokens
original MIT
goop-accept
16Command Claude Code
Verify work, confirm acceptance, and archive the milestone.
not rated 51
+1 2mo ago A 15 tokens
original MIT
goop-amend
17Command Claude Code
Propose changes to a locked specification.
not rated 51
+1 2mo ago A 12 tokens
original MIT
goop-discuss
18Command Claude Code
Capture user vision through the six-category discovery interview.
not rated 51
+1 2mo ago A 14 tokens
original MIT
goop-execute
19Command Claude Code
Run wave-based implementation through delegated executor agents.
not rated 51
+1 2mo ago A 13 tokens
original MIT
goop-help
20Command Claude Code
List GoopSpec commands, workflow phases, and agents.
not rated 51
+1 2mo ago A 15 tokens
original MIT
goop-plan
21Command Claude Code
Create the locked specification and wave blueprint.
not rated 51
+1 2mo ago A 11 tokens
original MIT
goop-quick
22Command Claude Code
Fast-track a small, well-defined task.
not rated 51
+1 2mo ago A 13 tokens
original MIT
goop-setup
23Command Claude Code
Initialize or reconfigure GoopSpec for this project.
not rated 51
+1 2mo ago A 15 tokens
original MIT
goop-status
24Command Claude Code
Show current GoopSpec workflow status and next step.
not rated 51
+1 2mo ago A 14 tokens
original MIT
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: