Agent
Software architecture specialist for system design, scalability, and technical decision-making. Use PROACTIVELY when planning new features, refactoring large systems, or making architectural decisions.
Agent
A build-error repair assistant focused on making a project compile successfully with no language-server errors. Language-server errors are editor-style diagnostics such as invalid types, missing names, or unresolved imports.
Agent
Expert code review specialist. Proactively reviews code for quality, security, and maintainability. Use immediately after writing or modifying code. MUST BE USED for all code changes.
Agent
Documentation and codemap specialist. Use PROACTIVELY for updating codemaps and documentation. Runs /update-codemaps and /update-docs, generates docs/CODEMAPS/, updates READMEs and guides.
Agent
Analyze and improve the local agent harness configuration for reliability, cost, and throughput.
Agent
Operate autonomous agent loops, monitor progress, and intervene safely when loops stall.
Agent
Expert planning specialist for complex features and refactoring. Use PROACTIVELY when users request feature implementation, architectural changes, or complex refactoring. Automatically activated for planning tasks.
Agent
Dead code cleanup and consolidation specialist. Use PROACTIVELY for removing unused code, duplicates, and refactoring. Runs analysis tools (knip, depcheck, ts-prune) to identify dead code and safely removes it.
Command
Incrementally fix build and type errors with minimal, safe CDD changes. Invokes sequential-thinking for analysis before fixing.
Command
A quick compile check for common programming projects. It detects the project type and runs its configured build or type-check command, such as the TypeScript compiler, Rust checker, or Go build.
Command
Create or verify a checkpoint in your workflow. Usage - /checkpoint [create|verify|list] [name].
Command
Start NanoClaw v2 — ECC's persistent, zero-dependency REPL with model routing, skill hot-load, branching, compaction, export, and metrics.
Command
Comprehensive security and quality review of uncommitted changes. Blocks on CRITICAL or HIGH issues.
Command
Manage eval-driven development workflow. Define, check, and report on evaluation criteria.
Command
Analyze instincts and suggest or generate evolved structures (skills, commands, agents).
Command
A command that creates a structured handoff document describing a coding session’s status, decisions, files, risks, and next steps.
Command
Audit the current repository's agent harness setup and return a prioritized scorecard.
Command
Export instincts from project/global scope to a file for sharing or backup.
Command
Import instincts from file or URL into project/global scope.
Command
Show learned instincts (project + global) with confidence scores and metadata.
Command
Extract reusable patterns from the session, self-evaluate quality before saving, and determine the right save location (Global vs Project).
Command
Analyze the current session and extract reusable patterns worth saving as skills or instincts.
Command
Start a managed autonomous loop pattern with safety defaults and stop conditions.
Command
Inspect active loop state, progress, and failure signals.