parcadei/Continuous-Claude-v3

AST-Grep Find performs syntax-aware code search and refactoring using ast-grep patterns. Use it to find function calls, imports, and class definitions, or rename and replace code across a codebase.

Agent Context Isolation prevents agent output from polluting the main context window by using background agents with file-based coordination instead of reading full transcripts. Use it when you need to preserve conversation context while delegating work to subagents.

Agent Orchestration defines rules for delegating implementation tasks to subagents so the main context stays lean. Use it when planning multi-file features or following a plan phase to avoid burning context in the main chat.

Agentic Workflow defines a multi-agent pipeline for implementation tasks in Claude Code, using background agents, file-based handoffs, and TDD. Use it to orchestrate research, planning, validation, implementation, and review without flooding the main context.

Agentica Claude Proxy connects Agentica SDK to Claude Code CLI through a local proxy so agents can use Read, Write, Edit, and Bash tools. Use it when setting up or debugging agent integrations, fixing permission errors, or preventing hallucinations.

Agentica Infrastructure documents the Agentica multi-agent coordination APIs, including 11 pattern classes, primitives, and the coordination database schema. Use it when building multi-agent workflows, implementing custom patterns, or debugging agent tracking.

Agentica Prompts provides templates and patterns for writing reliable prompts for Agentica/REPL agents, reducing instruction ambiguity and improving multi-agent orchestration reliability.

Agentica SDK builds Python agents using the Agentica framework with @agentic decorator, spawn(), persistence, and MCP integration. Use it to add agentic capabilities to Python code or orchestrate multiple agents.

Agentica Server configures and runs the Agentica SDK with a local Claude proxy so Python agents can use Claude CLI as their inference backend. Use it when setting up a fresh environment, debugging connection issues, or troubleshooting tool access and hallucinations.

Agentica Spawn executes multi-agent patterns such as swarms, hierarchical coordination, generator/critic loops, and juries after a pattern is selected. Use it to implement parallel research, coordinated building, iterative refinement, or high-stakes validation with spawned agents.

Async REPL Protocol defines rules for using Agentica's async REPL harness during testing: await Future-returning tools and compute and return results in a single code block.

Background Agent Pings instructs Claude Code agents to trust system reminders for background task progress rather than polling. Use it when you want to avoid wasted tokens and context flooding while background agents run.

Braintrust Analysis inspects Claude Code session tracing data in Braintrust to surface tool usage, agent and skill activity, token trends, and repeated loops. Use it for post-task retrospectives, debugging stuck sessions, and weekly productivity reviews.

Braintrust Tracing explains how to capture Claude Code session traces in Braintrust, including hook event flow, state management, and sub-agent correlation. Use it to debug agent runs, inspect token usage, or link sub-agent traces to parent sessions.

Build orchestrates existing skills into feature development workflows, chaining discovery, planning, implementation, and post-implementation phases with human checkpoints at boundaries.

CLI Reference documents the Claude Code command-line interface, covering commands, flags, headless mode, session control, subagents, and automation patterns. Use it when configuring CLI automation, CI/CD, or agent spawning.

Commit Changes plans and creates git commits for changes made during a coding session, only after user approval, and without Claude attribution. It groups related files, asks for confirmation, and saves reasoning notes for future sessions.

Completion Check verifies that infrastructure code is actually connected and invoked before marking work complete. Use it to trace execution paths, confirm hooks and database backends are registered, and run end-to-end tests.

Compound Learnings analyzes session learning files to extract recurring patterns, then proposes and creates permanent capabilities such as rules, skills, hooks, and agent updates. Use it when asked to improve setup, compound learnings, or turn session patterns into reusable artifacts.

Continuity Ledger creates or updates a YAML handoff document that preserves session state across context clears. Use it before /clear, when context approaches 70%, or for multi-day implementations.

Create Handoff generates a YAML handoff document that summarizes a Claude Code session's goal, completed work, decisions, blockers, and next steps, so another agent can pick up where it left off. Use it when ending a session or transferring context to a new session.

Dead Code Detection finds unused functions and dead code in the codebase using TLDR static analysis. Use it to identify and remove dead code to keep the codebase clean.

Debug investigates logs, database state, and git history to help identify issues during manual testing or implementation without editing files. Use it to bootstrap a debugging session when something goes wrong and you need to gather evidence.

Debug Hooks is a systematic workflow for diagnosing Claude Code hooks that aren't firing, producing wrong output, or behaving unexpectedly. Use it to check outputs, verify registration, test hooks manually, and catch silent failures.

E2E Testing validates the entire persistence pipeline end-to-end. Use it when you need to verify that data flows correctly through the full stack.