parcadei/Continuous-Claude-v3 - Page 2

implement-plan-micro

Implement technical plans from thoughts/shared/plans with verification

implement-plan

Implement technical plans from thoughts/shared/plans with verification

research

Document codebase as-is with thoughts directory for historical context

sub-agents

Create and configure Claude Code sub-agents with custom prompts, tools, and models

tldr-code

Token-efficient code analysis via 5-layer stack (AST, Call Graph, CFG, DFG, PDG). 95% token savings.

search-router

Choose the right search tool for each query type

completion-check

Completion Check: Verify Infrastructure Is Wired

braintrust-tracing

Braintrust tracing for Claude Code - hook architecture, sub-agent correlation, debugging

git-commits

Git Commit Rules

onboard

Analyze brownfield codebase and create initial continuity ledger

trace-claude-code

Automatically trace Claude Code conversations to Braintrust for observability. Captures sessions, conversation turns, and tool calls as hierarchical traces.

agent-context-isolation

Agent Context Isolation

agent-orchestration

Agent Orchestration Rules

agentic-workflow

Agentic Workflow Pattern

agentica-claude-proxy

Guide for integrating Agentica SDK with Claude Code CLI proxy

agentica-infrastructure

Reference guide for Agentica multi-agent infrastructure APIs

agentica-prompts

Write reliable prompts for Agentica/REPL agents that avoid LLM instruction ambiguity

agentica-sdk

Build Python agents with Agentica SDK - @agentic decorator, spawn(), persistence, MCP integration

agentica-server

Agentica server + Claude proxy setup - architecture, startup sequence, debugging

agentica-spawn

Spawn Agentica multi-agent patterns

async-repl-protocol

Async REPL Protocol

leann-search

Semantic search across codebase using LEANN vector index

router-first-architecture

Router-First Architecture

search-hierarchy

Search Tool Hierarchy

search-tools

Search Tool Hierarchy

ast-grep-find

AST-based code search and refactoring via ast-grep MCP

async-repl-protocol

Async REPL Protocol

background-agent-pings

Background Agent Pings

braintrust-analyze

Analyze Claude Code sessions via Braintrust

complete-skill

A complete skill for E2E testing

compound-learnings

Transform session learnings into permanent capabilities (skills, rules, agents). Use when asked to "improve setup", "learn from sessions", "compound learnings", or "what patterns should become skills".

debug-hooks

Systematic hook debugging workflow. Use when hooks aren't firing, producing wrong output, or behaving unexpectedly.

environment-triage

Environment Triage

explicit-identity

Explicit Identity Across Boundaries

fix

Meta-skill workflow orchestrator for bug investigation and resolution. Routes to debug, implement, test, and commit based on scope.

graceful-degradation

Graceful Degradation with Helpful Messages

hook-developer

Complete Claude Code hooks reference - input/output schemas, registration, testing patterns

hooks

Hook Development Rules

idempotent-redundancy

Idempotent Redundancy

index-at-creation

Index at Creation Time