PACT

Dispatch concurrent specialists for this self-contained task: $ARGUMENTS

Triage after hitting blocker (Is help and/or a redo needed?)

Delegate a task to PACT specialist agents

Pause the session — consolidate memory, persist state, shut down teammates

Peer review of current work (commit, create PR, multi-agent review)

Pin important context permanently to CLAUDE.md, or review the session for pin-worthy context

Multi-agent planning consultation (no implementation)

Run a recursive PACT cycle for this sub-task: $ARGUMENTS

Set up Telegram notifications for PACT

Perform end-of-session cleanup and documentation synchronization

Use this agent to design system architectures: component diagrams, API contracts, data flows, and implementation guidelines. Use after preparation/research is complete.

Use this agent for concurrent quality observation during CODE phase: reading coder output, comparing against architecture specs, and emitting GREEN/YELLOW/RED signals. Does not write code — observes while others build.

Use this agent to implement backend code: server-side components, APIs, business logic, and data processing. Use after architectural specifications are ready.

Use this agent to implement database solutions: schemas, optimized queries, data models, indexes, and data integrity. Use after architectural specifications are ready.

Use this agent to implement infrastructure and build systems: CI/CD pipelines, Dockerfiles, shell scripts, Makefiles, and infrastructure as code. Use after architectural specifications are ready.

Use this agent to implement frontend code: responsive, accessible user interfaces with proper state management. Use after architectural specifications are ready.

Use this agent to build, validate, or troubleshoot n8n workflows: webhooks, HTTP integrations, database workflows, AI agent workflows, and scheduled tasks. Requires n8n-mcp MCP server.

Use this agent to research and gather documentation: API docs, best practices, code examples, and technical information for development. First phase of PACT.

Use this agent for runtime verification: starting the app, navigating pages, testing interactions, and catching regressions invisible to static analysis. Requires a runnable dev server.

Use this agent when HANDOFFs need to be reviewed and distilled into institutional knowledge, or when you need a research assistant for past decisions and institutional memory. The secretary serves dual roles: Knowledge Distiller (synthesizing HANDOFFs into pact-memory) and Research Assistant (answering queries from the lead and specialists about past work). Examples: <example> Context: Workflow completed and HANDOFFs need to be reviewed and saved as institutional memory. user: "Review HANDOFFs for tasks #3, #5, #7 and save institutional knowledge" assistant: "The secretary reads each HANDOFF from `completed_handoffs.jsonl` (preferred) or via `TaskGet` (fallback), extracts institutional knowledge, deduplicates against existing memories, and saves to pact-memory." <commentary>HANDOFF review is the primary write path — the lead sends completed task IDs and the secretary reviews, deduplicates, and saves them.</commentary> </example> <example> Context: A backend coder needs to know what was decided about the caching strategy before implementing. user: "What was decided about the caching strategy?" assistant: "The secretary searches pact-memory and responds directly to the querying specialist with relevant decisions and memory IDs." <commentary>Specialists query the secretary directly via SendMessage — no routing through the lead needed. The secretary provides historical context, not implementation advice.</commentary> </example> <example> Context: Starting a new session and need project context. user: "What were we working on last time?" assistant: "The secretary delivers a session briefing at spawn with recent project context, including Working Memory cleanup." <commentary>The secretary proactively searches pact-memory at spawn, cleans stale Working Memory entries, and delivers a session briefing — no explicit query needed.</commentary> </example>

Use this agent for adversarial security code review: finding vulnerabilities, auth flaws, injection risks, and data exposure. Does not fix issues — reports findings for coders to address.

Use this agent to create and run tests: unit tests, integration tests, E2E tests, performance tests, and security tests. Use after code implementation is complete.

Write JavaScript code in n8n Code nodes. Use when writing JavaScript in n8n, using $input/$json/$node syntax, making HTTP requests with $helpers, working with dates using DateTime, troubleshooting Code node errors, or choosing between Code node modes.

Write Python code in n8n Code nodes. Use when writing Python in n8n, using _input/_json/_node syntax, working with standard library, or need to understand Python limitations in n8n Code nodes.

Validate n8n expression syntax and fix common errors. Use when writing n8n expressions, using {{}} syntax, accessing $json/$node variables, troubleshooting expression errors, or working with webhook data in workflows.

Expert guide for using n8n-mcp MCP tools effectively. Use when searching for nodes, validating configurations, accessing templates, managing workflows, or using any n8n-mcp tool. Provides tool selection guidance, parameter formats, and common patterns.

Operation-aware node configuration guidance. Use when configuring nodes, understanding property dependencies, determining required fields, choosing between get_node detail levels, or learning common configuration patterns by node type.

Interpret validation errors and guide fixing them. Use when encountering validation errors, validation warnings, false positives, operator structure issues, or need help understanding validation results. Also use when asking about validation profiles, error types, or the validation loop process.

Proven workflow architectural patterns from real n8n workflows. Use when building new workflows, designing workflow structure, choosing workflow patterns, planning workflow architecture, or asking about webhook processing, HTTP API integration, database operations, AI agent workflows, or scheduled tasks.

Agent Teams interaction protocol for PACT specialist agents. Auto-loaded via agent frontmatter. Defines how teammates start work, communicate, report completion, and handle blockers.

Architectural design patterns, C4 diagram templates, component design guidelines, and anti-patterns for PACT Architect phase. Use when: designing system components, creating architecture diagrams, defining component boundaries, planning API contracts, selecting design patterns, or reviewing architectural decisions. Triggers on: architecture design, C4 diagrams, component design, system design, microservices, monolith, API design, interface contracts, architect phase.

Clean code principles, error handling patterns, and coding standards for PACT Code phase. Use when: implementing features, refactoring code, reviewing code quality, establishing coding conventions, or handling errors and exceptions. Triggers on: code quality, clean code, refactoring, error handling, logging patterns, naming conventions, code review, code phase.

HANDOFF discovery, review, save, and cleanup workflow for the PACT secretary. Use when: processing agent HANDOFFs after workflow phases, running session consolidation, or recovering orphaned completed handoffs from prior sessions. Triggers: harvest HANDOFFs, process HANDOFFs, incremental, consolidation, handoff recovery.

Persistent memory for PACT agents. Save context, goals, lessons learned, decisions, and entities. Semantic search across sessions. Use when: saving session context, recalling past decisions, searching lessons. Triggers: memory, save memory, search memory, lessons learned, remember, recall

Research methodologies and documentation gathering workflows for PACT Prepare phase. Use when: conducting technology research, evaluating API documentation, comparing framework options, analyzing library choices, gathering requirements, or creating technology comparison matrices. Triggers on: research, requirements gathering, API exploration, documentation review, technology evaluation, library comparison, prepare phase.

Security best practices and threat mitigation patterns for PACT framework development. Use when: implementing authentication or authorization, handling API credentials, integrating external APIs, processing sensitive data (PII, financial, health), reviewing code for vulnerabilities, or enforcing SACROSANCT security rules. Triggers on: security audit, credential handling, OWASP, auth flows, encryption, data protection, backend proxy pattern, frontend credential exposure.

Testing strategies, test pyramid guidance, and quality assurance patterns for PACT Test phase. Use when: designing test suites, implementing unit tests, integration tests, E2E tests, performance testing, security testing, or determining test coverage priorities. Triggers on: test design, unit testing, integration testing, E2E testing, test coverage, test pyramid, mocking, fixtures, performance testing, test phase.

Get additional project context from the secretary — past decisions, architectural patterns, project history, and lessons learned via SendMessage

Telegram notification integration guide for PACT. Use when telegram_notify is available in your tools — covers when to notify, when to ask, when to check replies, and multi-session behavior.

Remove a git worktree and its branch after PACT workflow completes. Use when: PR is merged, sub-scope work is consolidated, or manual cleanup is needed. Triggers on: worktree cleanup, remove worktree, delete worktree, branch cleanup.

Create an isolated git worktree with a feature branch for PACT workflows. Use when: starting a new feature, beginning orchestrate or comPACT, creating sub-scope isolation for ATOMIZE, or manually isolating work. Triggers on: worktree setup, feature isolation, parallel workflow, new worktree.

25 hooks across 11 events