Cursor rule Cursor
This project follows coding conventions defined in AGENTS.md and enforced through convention packs. Before writing or reviewing code, read the applicable convention pack(s) from .opencode/uf/packs/ and apply all rules marked [MUST].
Agent
Runs background tasks without MCP tool access.
Agent
Adaptive implementation engine — coding persona with engineering philosophy, convention pack adherence, and Gaze/Divisor feedback loops.
Agent
Constitution alignment checker — compares a hero constitution against the Unbound Force org constitution.
Agent
Orchestrates forge coordination and supervises worker agents.
Agent
Skeptical auditor that finds where code and specs will break under stress or violate behavioral constraints.
Agent
Structural and architectural reviewer ensuring code and specs align with project conventions and long-term maintainability.
Agent
Documentation & content pipeline triage — owns documentation gaps, blog/tutorial opportunities, and website issue filing.
Agent
Public relations and communications specialist — owns press releases, social media, and community updates.
Agent
Intent drift detector ensuring changes solve the actual business need.
Agent
Blog and announcement writer — owns release notes, blog posts, and feature announcements.
Agent
Technical documentation specialist — owns READMEs, specs, CLI help, and API docs.
Agent
Deployment and operational readiness auditor ensuring code and specs are production-viable, maintainable, and observable in runtime.
Agent
Test quality and testability auditor ensuring code and specs meet coverage, isolation, and assertion standards.
Agent
Quality report agent for Go projects. Runs gaze CLI commands to produce human-readable summaries of CRAP scores, test quality metrics, side effect classifications, and overall project health. Supports three modes: crap (CRAP scores only), quality (test quality metrics only), and full (comprehensive health assessment).
Agent
Test generation agent for Go projects. Consumes gaze quality data (GapHints, Gaps, FixStrategy, AmbiguousEffects) to generate complete, compilable Go test functions, improve documentation for classifier visibility, and restructure assertions for mapper accuracy. Works on any Go project gaze can analyze.
Agent
Flow Facilitator and Continuous Improvement Coach — reflective questioning, retrospective facilitation, and process stewardship.
Agent
Test quality and testability auditor ensuring gaze code and specs meet coverage, isolation, and assertion standards.
Agent
Executes a single subtask with file reservations and progress reporting.
Command
Trigger an incremental re-index of all configured content sources. Updates the Dewey knowledge graph with new and changed content from disk, GitHub, web, and code sources without leaving the OpenCode session.
Command
Delete and rebuild all external source content in the Dewey index. Preserves local vault content and stored learnings. Use when the index appears stale or corrupted.
Command
Check forge coordination status - workers, messages, cells.
Command
Decompose task into subtasks and coordinate parallel agents.
Command
Generate tests and documentation fixes for functions identified by gaze quality analysis, or auto-detect and run the active implementation workflow (Speckit/OpenSpec). With arguments: batch remediation. Without arguments: detects active workflow and runs /speckit.implement or /opsx-apply.