Agent
Implements bounded code changes directly in the repository and validates them before handing back to the caller.
2 5mo ago A 19 tokens
original MIT
2Stars on the repository
37Mods indexed here, across every type
5mo agoLast push, which is what freshness is scored on
MITLicence, which decides whether bodies are shown
Agent
Reviews completed implementation for quality, reliability, and maintainability.
2 5mo ago A 12 tokens
original MIT
Agent
Analyzes codebase implementation details. Call the codebase-analyzer agent when you need to find detailed information about specific components.
2 5mo ago A 25 tokens
copy · 88% MIT
Agent
Locates files, directories, and components relevant to a feature or task. Call codebase-locator with human language prompt describing what you're looking for. Basically a "Super Grep/Glob/LS tool" — Use it if you find yourself desiring to use one of these tools more than once.
2 5mo ago A 63 tokens
copy · 81% MIT
Agent
You are a specialist at finding code patterns and examples in the codebase. Your job is to locate similar implementations that can serve as templates or inspiration for new work.
2 5mo ago A 70 tokens
copy · 81% MIT
Agent
Hidden evidence lane that turns traces, checkpoints, and memory into concise validation or handoff summaries.
2 5mo ago A 19 tokens
original MIT
Agent
Hidden ambiguity analyzer that prepares evidence-backed branch choices or question-tool options.
2 5mo ago A 14 tokens
original MIT
Agent
Verifies implementation matches requested spec exactly with file-level evidence.
2 5mo ago A 12 tokens
original MIT
supervisor
09Agent
Hidden exception-path supervisor for material ambiguity, destructive actions, and repeated failure recovery.
2 5mo ago A 16 tokens
original MIT
Agent
The research equivalent of codebase-analyzer. Use this subagenttype when wanting to deep dive on a research topic. Not commonly needed otherwise.
2 5mo ago A 29 tokens
original MIT
Agent
Discovers relevant documents in thoughts/ directory (We use this for all sorts of metadata storage!). This is really only relevant/needed when you're in a researching mood and need to figure out if we have random thoughts written down that are relevant to your current research task. Based on the name, I imagine you…
2 5mo ago A 78 tokens
original MIT
Agent
Fetch and analyze web content from a provided URL based on a query.
2 5mo ago A 14 tokens
copy · 84% MIT
build
13Agent
Primary shared-state lane. Orchestrates mutable work by delegating discovery and analysis first, then applying edits, validations, and handoffs with minimal root-lane work.
2 5mo ago A 34 tokens
original MIT
compaction
14Agent
Memory-preservation lane. Compresses state, open questions, active overlays, and evidence so long-running work survives compaction cleanly.
2 5mo ago A 27 tokens
original MIT
explore
15Agent
Evidence-gathering lane. Locates files, traces, logs, runtime state, and implementation signals before action is taken.
2 5mo ago A 25 tokens
original MIT
plan
16Agent
Primary orchestration and decomposition lane. Routes intent, dispatches specialists, merges findings, and keeps deep implementation out of the root lane.
2 5mo ago A 27 tokens
original MIT
summary
17Agent
Synthesis lane. Merges lane outputs into concise handoffs, final reports, and next-step recommendations without reopening exploration.
2 5mo ago A 24 tokens
original MIT
title
18Agent
Title-only lane. Produces short, informative conversation titles and nothing else.
2 5mo ago A 15 tokens
original MIT