architect
01Agent
Ask when consequential design choices must be settled before or during implementation — investigates context, compares approaches, and records decisions.
112 27d ago A 24 tokens
112Stars on the repository
28Mods indexed here, across every type
27d agoLast push, which is what freshness is scored on
noneNo LICENSE: all rights reserved, so bodies are not copied
archivist
02Agent
Memory investigation, synthesis, and authorized curation when surfaced memories are insufficient.
112 27d ago A 18 tokens
debugger
03Agent
Systematically diagnose and fix bugs: find root cause before attempting any fix.
112 27d ago A 17 tokens
Agent
Observe Sprout's live session behavior and send concise guidance when it is drifting, stuck, or missing an important instruction.
112 27d ago A 27 tokens
Agent
Explore and understand unfamiliar codebases, map architecture, and synthesize structural insights.
112 27d ago A 19 tokens
Agent
Ask when you need to know what Sprout agents, tools, or MCP servers are available, need a reusable capability plan, or need a new specialist built; not for local command/runtime/cwd checks.
112 27d ago A 43 tokens
Agent
Build new specialist agent definitions on the fly.
112 27d ago A 13 tokens
qm-indexer
08Agent
Discover and index available capabilities across agents, tools, and MCP servers.
112 27d ago A 17 tokens
qm-planner
09Agent
Plan how to accomplish goals by combining available tools, agents, and MCP capabilities.
112 27d ago A 19 tokens
Agent
Reconcile genome/root differences and propose contributions.
112 27d ago A 13 tokens
Agent
Analyze, search, debug, and repair Sprout sessions using metadata and JSONL event logs.
112 27d ago A 24 tokens
Agent
Diagnose whether Sprout is learning effectively from sessions, stumbles, metrics, and pending evaluations.
112 27d ago A 24 tokens
Agent
Explain Sprout internals and advise on changes using architecture resources plus source verification.
112 27d ago A 22 tokens
tech-lead
14Agent
Manage the full implementation cycle for a single task: dispatch engineer, run two-stage review, iterate until approved.
112 27d ago A 25 tokens
engineer
15Agent
Implement a single task from a plan: write code, write tests, commit, and report status.
112 27d ago B 22 tokens
Agent
Review implementation code quality: cleanliness, testing, maintainability, and design.
112 27d ago A 18 tokens
Agent
Review whether an implementation matches its task specification — nothing more, nothing less.
112 27d ago A 18 tokens
the-balcony
18Agent
Private sidecar commentator for the human; watches root sessions without steering them.
112 27d ago A 18 tokens
Agent
Ask to run shell commands — build, test, install, git, or any CLI tool — and get back execution findings.
112 27d ago B 28 tokens
editor
20Agent
Ask to create named files or make targeted edits — acts directly when targets are decisive, reads only when context is missing.
112 27d ago A 25 tokens
mcp
21Agent
Ask to interact with external services via MCP (Model Context Protocol) — list available servers, discover their tools, and call them with arguments.
112 27d ago A 30 tokens
Agent
Ask to manage project memory documents — list, read, write, or search .md files in the project memory directory.
112 27d ago A 26 tokens
reader
23Agent
Ask to find and read specific files or search for patterns — returns extracted information, not raw dumps. Use for quick targeted lookups, not broad exploration.
112 27d ago A 32 tokens
task-manager
24Agent
Ask to track work items for this session — create tasks, list them by status, update progress, assign to agents, and add comments.
112 27d ago A 30 tokens
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: