232 docs tagged with "command"

Analyze a task description to determine its complexity level, domains, estimated resources, and recommended agents for execution.

Analyzes API compatibility by comparing current API surface against baseline to detect breaking changes in REST endpoints, GraphQL schemas, and protobuf definitions.

Analyze uncommitted or staged changes for breaking impact on currently deployed production code. Categorizes changes by risk level and identifies API surface violations, schema migrations, config changes, and behavioral shifts.

Control a browser directly from your CODITECT session. Navigate to pages, interact with elements, take screenshots, and extract data using snapshot-based element targeting with 93% token reduction compared to raw HTML.

Extract web page content directly into structured markdown or nested JSON. No screenshot required. Optionally analyze content quality, accessibility, SEO, and compare pages side-by-side.

Agentic browser research that autonomously discovers pages from a starting URL or search query, presents an interactive checklist for selection, extracts content from all selected pages (including PDFs), and assembles everything into a structured research document with summaries and recommendations.

Proactively scan recent commits for likely bugs, logic errors, security issues, and regressions. Analyzes diffs, identifies suspicious patterns, and proposes minimal fixes with evidence.

System Prompt

Start an interactive project building workflow for any analysis type.

Compares canary instance metrics against baseline using statistical tests (Mann-Whitney U, Kolmogorov-Smirnov) to determine whether to advance, hold, or rollback a progressive deployment.

Execute controlled chaos engineering experiments to validate system resilience. Defines steady-state hypotheses, injects faults across network, resource, application, and infrastructure layers, monitors impact, and generates resilience reports.

Create checkpoints for session continuity and autonomous agent handoffs. Supports two modes:

Group CI failures by likely root cause, identify flaky tests, and suggest minimal targeted fixes. Analyzes recent CI runs to distinguish genuine failures from intermittent issues.

Classify documents using the complete 4-phase Mixture of Experts (MoE) pipeline. Supports recursive directory analysis, automatic frontmatter updates, and comprehensive reporting.

Index your project's source code for semantic search, symbol lookup, and call graph analysis.

Search your codebase using natural language queries via codanna's semantic search engine.

Export Codex session data from history.jsonl into per-session JSONL files.

Complete component lifecycle: inventory → register → activate → classify → improve → index → commit.

Resume work after context summarization, interruption, or break. Restores working memory and identifies where to pick up.

Scaffold and configure CopilotKit projects for building AI copilot interfaces.

Execute a multi-agent code review with anonymized peer evaluation, consensus scoring, and structured verdicts.

Identify untested code paths introduced by recent changes and generate focused test cases to close gaps. Cross-references diffs against coverage data to find precisely what needs testing.

Version: 1.0.0

Extract and deduplicate messages from Claude, Codex, and Gemini sessions into a unified store with LLM source identification and automatic indexing for instant searchability. Supports ADR-122 multi-LLM architecture.

Automatically retrieve relevant context from session history to prevent catastrophic forgetting. Combines semantic search with extracted knowledge (decisions, patterns, error solutions).

Search and query the unified message database with full-text search, semantic search, knowledge extraction, and analytics. Part of the CODITECT anti-forgetting system.

Usage

Execute comprehensive dependency vulnerability auditing with CVE reporting, upgrade paths, and license compliance analysis across all package managers.

Purpose: Query CODITECT's component capability index to find the right tool for any task.

Scans project tracks, computes critical path, matches agents to tasks, detects capability gaps, and generates executable multi-agent dispatch plans with parallel wave execution.

Automated build and deployment of the CODITECT documentation site to Cloud Run.

Manage epics within CODITECT projects. Epics are large bodies of work that can be broken down into features.

Execute YAML/JSON workflow definitions as state-machine orchestrated multi-agent tasks with checkpoint/resume capability.

Select an experience pack to optimize skill loading for your specific role. This command uses the CODITECT Experience Framework (CEF) to load only the most relevant skills, reducing context usage by 89%.

Select an experience pack to optimize skill loading for your specific role. This command uses the CODITECT Experience Framework (CEF) to load only the most relevant skills, reducing context usage by 89%.

Manage features within CODITECT epics. Features are discrete pieces of functionality that deliver user value.

Full-featured SaaS financial model engine backed by SQLite (ADR-177). Create scenarios, edit assumptions (pricing, growth, funding, headcount, expenses), build outputs in 4 formats (static XLSX, formula XLSX, JSON, CSV), compare scenarios side-by-side, and maintain a complete audit trail.

Inventories all feature flags, identifies stale/abandoned flags past TTL, flags at 100% rollout needing cleanup, and generates cleanup recommendations with optional ticket creation.

Detect non-deterministic tests from CI run history, classify the root cause of flakiness (timing, order, resource, external, concurrency, data), and propose targeted stabilization fixes.

For Individual Contributors Only

Bottom-up commit and push across all dirty submodules, update parent pointers, and run recursive init.

Monitor autonomous agent health states using the HealthMonitoringService (ADR-110). Shows agent health, heartbeat status, circuit breaker states, and intervention history.

Content-addressable file integrity registry for the CODITECT Zero Trust architecture. Detects unauthorized modifications, tracks changes with cryptographic proof, and maintains an immutable audit trail in org.db.

Activates a CODITECT license key and binds it to this machine for the current user.

Display the current CODITECT license status including tier, validity, expiration, and enabled features.

System Prompt

Version: 1.0.0

Migrate files from various naming conventions (PascalCase, camelCase, SCREAMINGSNAKECASE) to lowercase-kebab-case.

Manually update the migration status of a specific submodule in the queue document.

Show and optionally run the next pending submodule migration from the queue document.

Display migration queue statistics showing pending, completed, and failed submodule counts.

Execute comprehensive multi-agent research using coordinated analyst subagents with explicit certainty scoring, evidence requirements, and logical inference documentation.

Execute a coordinated panel of specialized judge agents to evaluate both outbound prompts (for ambiguity/risk) and inbound responses (for accuracy/grounding) using calibrated, multi-dimensional rubrics.

Pop the next priority task from the V2 project queue and optionally start working on it.

System Prompt

Version: 1.0.0

Version: 1.0.0

5-step session orientation that combines project discovery, context search, agent discovery, invocation creation, and MoE orchestrated execution.

System Prompt

Execute comprehensive performance profiling for applications to identify CPU bottlenecks, memory issues, and I/O constraints with visual flame graph generation.

Orchestrate the complete PILOT project execution workflow with Track-based task management (A-G), MoE methodology, agent discovery, and automated session management.

Generate structured, blameless incident postmortems. Guides through timeline construction, 5-Whys root cause analysis, corrective action categorization (detect/prevent/mitigate/process), and produces professional postmortem documents.

Analyze PR review feedback to extract skill development recommendations. Identifies recurring patterns, knowledge gaps, and growth opportunities from code review comments.

Manage CODITECT projects with hierarchical work item tracking.

Create a new project in ~/PROJECTS/ with full CODITECT integration: symlinks to framework, component inventory registration, activation, and MoE classification.

System Prompt

Validate and review CODITECT components against established standards. Provides automated structural validation (Tier 1) and deep quality review (Tier 2) with scoring, grading, and actionable recommendations.

Generate comprehensive quality metrics report including DORA metrics (deploy frequency, lead time, MTTR, change failure rate), code quality KPIs, defect density, and quality scorecard with trends.

Retrieve relevant prior work context from the CODITECT memory system. Optimizes for signal-to-noise ratio and token efficiency, surfacing decisions, patterns, errors, and work status related to your current task.

Register a project so it appears in the trajectory dashboard. Handles both database registration (projects.db) and UI visibility configuration (dashboard-projects.json).

Analyzes code changes to determine which test suites to run, in what order, and flags flaky tests. Uses impact analysis to optimize test execution time while maintaining coverage.

Aggregate all quality signals into a single GO/NO-GO release decision. Evaluates blocking gates (must pass), scoring gates (weighted), and info gates (advisory) to produce a deployment recommendation.

Generate complete, customer-facing release notes from merged pull requests. Categorizes changes, highlights breaking changes, includes migration instructions, and links to relevant PRs.

Auto-update AGENTS.md, README.md, and other repo documentation with newly discovered workflows, commands, and patterns. Detects undocumented items and stale references.

Triage research manifests to terminal outcomes per ADR-208 Research-to-Product Promotion Lifecycle.

Execute comprehensive security scanning across the codebase including static analysis, dependency auditing, secrets detection, and configuration review.

Launch a project's existing dev server with automatic port conflict resolution, dependency installation, and lifecycle management.

End-of-session workflow that:

Garbage collect dead sessions from the session registry, prune stale task claims, clean file locks from dead PIDs, and trigger a quick vacuum sweep for orphaned tasks.

Append entries to the daily session log with ISO 8601 timestamps (UTC). Supports project-scoped session logs (ADR-155) with automatic project detection. Automatically runs /classify after each update to maintain frontmatter metadata.

Append a CODEX-authored entry that documents how to run /session-log into today's UTC session log.

System Prompt

Generate a Claude Code skill from a documentation website URL

Generate a Claude Code skill from a GitHub repository using C3.x analysis

Version: 1.0.0

Executes post-deployment smoke tests to verify critical paths, health endpoints, and essential functionality. Provides fast feedback on deployment success and can trigger automatic rollback on failure.

Manage time-boxed sprints for CODITECT projects with velocity tracking and burndown metrics.

Start component viewer for: $ARGUMENTS

Generate standardized status reports following CODITECT-STANDARD-STATUS-REPORTING.

Generate McKinsey/BCG/Bain-quality executive strategy briefs with multi-stage research, competitive intelligence, and strategic framework application.

Query conversation summaries extracted from session history. Summaries provide quick overviews of conversations and are automatically extracted from session files.

Export LLM session data to CODITECT Universal Session Format (CUSF) with interactive multi-select capability. Supports Claude, Codex, Gemini, and Kimi. Pairs with /cx for the complete export → extract workflow.

Scan, validate, and fix CODITECT symlinks (.coditect and .claude) across all projects in ~/PROJECTS/.

Zero-interaction, fully automated framework sync.

Manage tasks within CODITECT features. Tasks are the actionable work items that developers complete.

Summarize PR activity grouped by contributor and theme with risk highlights. Provides visibility into who is working on what, review bottlenecks, and areas needing attention.

Visualize and trace conversation threads using UUID parent-child relationships for session continuity and agent conversation tracking. Part of the CODITECT anti-forgetting system.

Normalize transcript TXT files into structured Markdown using the optimal paragraphing rule and consistent naming.

Systematic defect triage workflow. Classifies defects by severity (S1-S4), assigns priority using impact/urgency matrix, performs root cause taxonomy analysis, and generates structured triage reports.

Detect orphaned tasks — work that was started, claimed, or partially completed but abandoned when sessions died, contexts compacted, or projects were parked.

System Prompt

Deploy and manage the CODITECT Web Publishing Platform for: $ARGUMENTS

Synthesize a week's PRs, incidents, deployments, code reviews, and session logs into a structured team digest. Pulls from git, GitHub API, session logs, and CI/CD data.

Universal command for querying and managing any work item type in the CODITECT hierarchy.

Create, manage, and orchestrate isolated worktrees for parallel submodule development with full Git, Docker, and Claude Code session isolation.

System Prompt

Implement working code for: $ARGUMENTS

System Prompt

Analyze user requests, auto-activate deactivated components, and output the correct agent invocation syntax.

System Prompt

Analyze code for: $ARGUMENTS

System Prompt

Analyze meeting notes or transcripts to extract decisions, action items, and strategic context.

System Prompt

System Prompt

Backup context database, unified messages, and Claude global config files to GCS.

Manage staged LLM batch processing pipelines with checkpointing, cost estimation, and parallel execution.

System Prompt

Verify if a component, system, agent, or tool performs a specific behavior or action.

Get best practice recommendations, decision guidance, and tradeoff analysis.

Research individuals: $ARGUMENTS

Surface all blocked tasks across project plans with blocker details and suggested resolutions.

Build a CODITECT website from templates.

Launch a local React-based business intelligence dashboard for real-time project and track analytics.

Generate C4 diagrams for: $ARGUMENTS

Check if Claude, an agent, skill, tool, or system has a specific capability.

Research documentation for: $ARGUMENTS

System Prompt

System Prompt

System Prompt

System Prompt

System Prompt

INSTRUCTIONS FOR CLAUDE: Execute the appropriate backup script command based on arguments.

Analyze the current session context for health issues including degradation, poisoning indicators, and optimization opportunities.

Restore context from: $ARGUMENTS

System Prompt

System Prompt

Create an isolated git worktree for parallel task execution.

Generate comprehensive educational content for: $ARGUMENTS

Analyze database: $ARGUMENTS

System Prompt

Analyze requirements and decompose tasks for: $ARGUMENTS

System Prompt

Deploy a CODITECT website to Google Cloud Platform.

Invoke the documentation-librarian agent to transform scattered documentation into organized, navigable systems with automated quality monitoring.

Generate documentation for: $ARGUMENTS

System Prompt

System Prompt

Evaluate AI responses using professional LLM-as-judge patterns. Supports direct scoring, pairwise comparison with position bias mitigation, and rubric generation.

System Prompt

System Prompt

Setup ticketing for: $ARGUMENTS

System Prompt

Predict outcomes, compatibility impacts, test results, and future states.

Generate PR description for: $ARGUMENTS

Autonomous submodule specification and multi-agent implementation planning system.

System Prompt

System Prompt

Generate comprehensive handoff documentation for team members or future self.

System Prompt

System Prompt

Build production-ready implementation for: $ARGUMENTS

System Prompt

Automates the complete lifecycle of CODITECT install script maintenance - from error report to GCS deployment.

Classify intent for: $ARGUMENTS

Create new CODITECT framework components with proper templates, automatic registration, activation, and MoE classification.

Initialize any folder as a CODITECT-compatible git submodule with automatic GitHub repository creation, symlink chain setup, and parent repository registration.

System Prompt

System Prompt

Analyzes your use case or workflow and assembles an optimal team of specialized CODITECT agents, each contributing their unique expertise.

Orchestrates the complete MoE lifecycle: assembles experts to create deliverables, then judges to evaluate and iterate until quality standards are met.

Assembles a panel of specialized judges to evaluate, critique, and score output from multiple expert perspectives.

Show tasks and areas with recent activity to identify hot spots and work in progress.

System Prompt

Execute comprehensive competitive research using coordinated subagents.

System Prompt

Plan and implement: $ARGUMENTS

Research and plan ticket: $ARGUMENTS

Optimize performance for: $ARGUMENTS

Metadata

Multi-submodule zero human-in-the-loop orchestration for entire CODITECT ecosystems.

Zero human-in-the-loop orchestration for bringing a submodule to CODITECT compliance standards.

Find who owns, wrote, maintains, approved, or should review code, components, and projects.

Execute multiple tasks concurrently in isolated git worktrees.

Process documentation from: $ARGUMENTS

Analyze and process Claude Code native JSONL session files from ~/.claude/projects/ with intelligent chunking, deduplication, and watermark tracking.

Clean repository: $ARGUMENTS

Build rapid prototype for: $ARGUMENTS

System Prompt

System Prompt

Implement ticket: $ARGUMENTS

System Prompt

System Prompt

System Prompt

System Prompt

System Prompt

System Prompt

Verify assumptions and validate technical approach for: $ARGUMENTS

System Prompt

System Prompt

System Prompt

⚠️ DEPRECATION NOTICE (January 2026)

System Prompt

System Prompt

Export Claude Code sessions to text files that are fully compatible with /cx processing. Supports interactive selection from recent sessions or exporting by session ID.

Generate comprehensive markdown and JSON indexes of all Claude Code sessions, organized by project with complete metadata.

Detect, export, and recover hung Claude terminal sessions with automated process identification and LOSSLESS session backup.

System Prompt

View and analyze skill health scores, trends, and optimization recommendations.

System Prompt

System Prompt

Research market intelligence: $ARGUMENTS

System Prompt

Verify current state of systems, services, installations, and configurations.

System Prompt

System Prompt

System Prompt

System Prompt

System Prompt

System Prompt

Metadata

System Prompt

Safely remove the CODITECT installation from your system.

Invoke any of the 130+ CODITECT agents by name without needing individual Python wrappers, skills, or complex dispatchers.

Update your CODITECT installation to the latest version.

System Prompt

System Prompt

Verify codi-watcher health and display time-filtered export activity reports with comprehensive diagnostics.

System Prompt

System Prompt

Log completed work to the context database for future discovery by /work-next, handoffs, and session summaries.

Analyzes multiple data sources to help you understand current project state and interactively decide what work to begin next.