claude-flow-novice

Tiered planning orchestrator. Runs the full SPARC+ pipeline (research, spec, decide, pseudo, data, arch, ux, design, test, ops) as a parallel DAG, scaled by build stage (mvp/beta/enterprise) via inclusion profiles. Enforces two gates: every success criterion is executable (verifiable-done) and every step is unambiguous (haiku-executable). Use as the entry point for any non-trivial build instead of cfn-spa-plan.

Post-planning completeness review. Extracts assumptions, traces dependencies, analyzes blast radius, checks alpha-readiness, surfaces gaps before implementation. Use after writing any plan that touches data, APIs, or shared state.

SPARC Specification phase. Make testable acceptance criteria, edge cases, pre/post conditions, invariants BEFORE planning implementation. Use when starting any non-trivial task to lock intent, surface ambiguity early.

Test-strategy phase of cfn-megaplan. Designs test depth properly: fixtures/test-data, the unit/integration/contract/e2e/load split, mocking strategy, and non-functional tests, instead of lumping everything into a vague red phase. Feeds Bar A (verifiable-done): every acceptance criterion becomes a concrete runnable check. Use after cfn-spec, cfn-arch, and (if frontend) cfn-ux.

Pre-edit backup + post-edit validation for safe file edits. Use to capture file state before edits, validate changes after edits, revert files to prior state, or ensure edit safety via auto backup/validation hooks.

Extract complete Redis coordination data from completed CFN Loop tasks and structure into comprehensive JSON analysis files

Coordinates FAST code generation via Z.ai glm-4.6 with CodeSearch pattern learning. Use when agents need rapid test generation, bulk code creation, or repetitive boilerplate. Tracks successful prompts for continuous improvement. Ideal for high-volume, low-complexity code tasks.

FAST code generation via mcp__cerebras-mcp__write tool using Z.ai glm-4.6. Use for rapid test generation, boilerplate creation, and bulk code tasks in main chat. Prompt must be SHORTER than output. Ideal for tests, CRUD, migrations, and repetitive patterns.

FAST code generation via Z.ai glm-4.6 model. Use for rapid test generation, boilerplate code, repetitive patterns, and bulk file creation. Ideal when speed matters more than nuance. Do NOT use for complex architectural decisions or security-critical code.

Docker container orchestration for CFN Loop - spawning, coordination, logging, wave execution. Use when running CFN Loop agents in Docker containers, executing waves of parallel agents, coordinating containerized agents via Redis, or managing Docker-based agent lifecycle.

Manages Google Sheets API calls with rate limiting and quota enforcement

Constructs and validates Google Sheets formulas from templates with syntax checking

Tracks micro-sprint completion state and progress for Google Sheets operations

Validates data integrity and state consistency between Google Sheets operation sprints

Agent selection based on task classification with fallback support

Agent process spawning with provider configuration and execution

Unified agent management selection through completion: spawn, execute, process output. Use when selecting agents for tasks, spawning agents with dependency validation, processing agent outputs, or tracking agent lifecycle events with audit trails.

Generates new agent profiles with consistent structure, automatic validation pattern injection, and test-driven protocols

Enforces validation pattern compliance across all agent profiles with automated detection and fixing

Agent dev tools: template generation, profile validation. Use when creating new agent templates from scaffolding, or validating/linting existing agent profiles for correctness and completeness.

MUST BE USED before any alpha or production release. Do not deploy without passing this check. Alpha readiness analysis plus fix execution: scores 8 readiness areas in parallel, delegates fixes to cfn-parallel-execute. Use when preparing to ship.

Group-based alpha readiness analysis. Use when analyzing all features in one priority group (CRITICAL/HIGH/MEDIUM/LOW) at once; generates consolidated fix lists, marks group complete when done.

MUST BE USED within 10 minutes of any production deployment. Post-deploy health monitoring: polls a URL for 10 minutes checking errors, performance regressions, availability.

PreToolUse hook. Warns before destructive bash commands (rm -rf, DROP TABLE, git push --force, etc). Activates via /careful. Whitelists safe deletions (node_modules, .next, dist).

MANDATORY: Query CodeSearch BEFORE using grep, glob, find, or search. 400x faster semantic/structural code search via SQL on indexed codebase. Use to find functions, classes, patterns, callers, implementations. Agents MUST query CodeSearch first; grep only allowed after CodeSearch returns zero results.

Two-phase Rust/TypeScript compilation error fixer: Cerebras LLM bulk processing + agent cleanup. Use when you have 20+ compilation errors needing fast bulk reduction, or errors are mostly mechanical (type mismatches, missing imports, syntax).

Config management and environment sanitization. Use when managing config files, validating env vars, sanitizing sensitive data, or updating system settings across CFN Loop components.

Sync conversation history from .codex/sessions to .claude.json for context preservation. Use when copying/syncing conversations, importing sessions, or backing up conversation context.

Unified atomic ingestion of CFN dependency manifests (cli-mode, shared)

Task dependency extraction and context ingestion. Use to parse task criteria, identify dependencies, generate execution order, or inject context for complex multi-step tasks.

Automated skill deployment pipeline for CFN Loop integration

Skill Promotion Workflow - Atomic promotion from staging to production

Skill deployment and promotion lifecycle. Use when transitioning skills from APPROVED to DEPLOYED, or promoting skills staging to production with SLA enforcement.

MUST BE USED before merging any PR that adds 3+ new functions or 50+ lines. Run after implementation. Reviews code for DRY violations, modularity, resumable pipeline opportunities. Outputs JSON manifest for cfn-vote-implement.

DEPRECATED. Use cfn-epic-creator-v2 (adds AISP formal contracts, prevents type drift). For full tiered planning use cfn-megaplan. v1 kept for the simpler single-domain prose-epic flow only.

Hybrid AISP epic creation: formal API contracts plus natural language content. Use when epic needs AISP (AI Symbolic Protocol) type definitions and agent binding contracts alongside human-readable descriptions.

Convert markdown epic documents into structured JSON configs for MDAP or CFN Loop execution. Use when parsing epic documents, validating epic structure, or generating execution configs from planning docs.

Error handling, batching, logging for CFN Loop. Use to capture agent errors, batch errors for processing, log structured error data, or categorize/recover from agent failures.

Human intervention detection and orchestration for CFN Loop. Use when automated processes need human oversight, escalation required, or managing intervention workflows and approval gates.

Root-cause debugging: 5-phase protocol, 3-strike escalation, scope lock. Enforces investigation before fixes. Use when diagnosing bugs, system failures, or unexpected behavior.