{"passport":{"unfragile":{"@version":"1.0","version":"2026-05","artifact":{"id":"github-mindfold-ai--trellis","slug":"mindfold-ai--trellis","name":"Trellis","type":"agent","url":"https://docs.trytrellis.app","page_url":"https://unfragile.ai/mindfold-ai--trellis","categories":["ai-agents"],"tags":["agentic-coding","ai-workflow","claudecode","codex","harness"],"pricing":{"model":"open_source","free":true,"starting_price":null},"status":"active","verified":false},"capabilities":[{"id":"github-mindfold-ai--trellis__cap_0","uri":"capability://tool.use.integration.multi.platform.ai.agent.harness.with.unified.context.injection","name":"multi-platform ai agent harness with unified context injection","description":"Trellis acts as a bridge between a codebase and multiple AI coding platforms (Claude Code, Cursor, OpenCode, Gemini CLI) by maintaining a .trellis/ directory as a Single Source of Truth. The framework auto-injects project-specific specs, task context, and coding guidelines into each AI session via platform-specific integration layers (.claude/, .cursor/, etc.), ensuring every agent operates within consistent project conventions and historical context without manual context setup per session.","intents":["I want AI agents to understand my project's coding standards and conventions automatically across different platforms","I need to maintain continuity across multiple AI-assisted coding sessions without re-explaining project context","I want to switch between Claude Code, Cursor, and other AI platforms while keeping the same project structure and guidelines"],"best_for":["teams using multiple AI coding platforms who need unified project context","developers building agentic workflows that require disciplined, project-aware AI assistance","organizations standardizing AI-assisted development across heterogeneous tooling"],"limitations":["Requires TypeScript CLI setup and .trellis/ directory initialization — not zero-config","Platform integration depends on each AI platform's support for custom hooks/entry points; not all platforms equally supported","Context injection latency scales with spec system size; large codebases with extensive guidelines may add session startup overhead"],"requires":["Node.js 18+ for CLI (@mindfoldhq/trellis)","Git repository with write access to root directory","At least one supported AI platform (Claude Code, Cursor, OpenCode, Gemini CLI)","Python 3.9+ for task.py and backend scripts"],"input_types":["project directory structure","coding guidelines (markdown specs)","task definitions (JSON task.json)","developer journals (markdown)"],"output_types":["platform-specific configuration files (.claude/, .cursor/ directories)","injected context for AI sessions","task state tracking (task.json)"],"categories":["tool-use-integration","automation-workflow"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"github-mindfold-ai--trellis__cap_1","uri":"capability://planning.reasoning.task.centered.workflow.management.with.structured.prds.and.state.tracking","name":"task-centered workflow management with structured prds and state tracking","description":"Trellis provides a task management system (.trellis/tasks/) that structures AI-assisted work around discrete tasks, each with a PRD (product requirements document), context files, and a task.json state file. Tasks follow a defined lifecycle tracked in task.json, enabling AI agents to understand task scope, dependencies, and completion criteria. The system supports task archival (tasks/archive/) and integrates with the multi-agent pipeline to decompose high-level developer intent into concrete coding work.","intents":["I want to break down large features into discrete AI-assisted tasks with clear scope and success criteria","I need to track task state and progress across multiple AI sessions without manual status updates","I want AI agents to understand task dependencies and context from structured PRDs rather than natural language descriptions"],"best_for":["teams managing complex features across multiple AI coding sessions","developers using agentic workflows that require task decomposition and state management","projects needing audit trails of AI-assisted work with clear task boundaries"],"limitations":["Task state is stored in task.json; no built-in persistence layer or database — requires external systems for cross-project task aggregation","Task lifecycle is project-specific; no standardized task schema across Trellis instances without custom spec definitions","Manual task creation and PRD writing required; no automatic task generation from issue trackers or feature requests"],"requires":[".trellis/ directory initialized via CLI","task.json schema defined in project specs","Python 3.9+ for task.py lifecycle scripts"],"input_types":["PRD markdown files","task.json state objects","context files (code snippets, design docs)"],"output_types":["task.json with updated state","archived task records","task completion artifacts (code, tests)"],"categories":["planning-reasoning","automation-workflow"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"github-mindfold-ai--trellis__cap_10","uri":"capability://automation.workflow.developer.workflow.commands.for.task.creation.and.state.management","name":"developer workflow commands for task creation and state management","description":"Trellis provides developer workflow commands (e.g., via CLI or platform-specific slash commands) that enable developers to create tasks, update task state, and manage project context without leaving their AI platform. Commands like 'create task', 'update task status', and 'add to journal' interact with the task management system and workspace, enabling seamless integration of developer actions into the Trellis workflow. These commands are routed through the CLIAdapter and executed as backend scripts.","intents":["I want to create and manage tasks from within my AI platform without switching tools","I need to update task state and progress as I work with AI agents","I want to add notes and decisions to my workspace journal without manual file editing"],"best_for":["developers using AI platforms for extended coding sessions","teams managing tasks and context within AI-assisted workflows","projects where task management should be integrated into the development environment"],"limitations":["Commands are platform-specific; not all AI platforms support custom commands equally","Command execution is asynchronous; no real-time feedback on task state changes","Commands are text-based; no rich UI for task creation or state management"],"requires":["platform-specific command definitions","backend scripts for command implementation","task.json schema for state management"],"input_types":["command text (e.g., '/create-task Feature X')","task parameters (name, description, dependencies)","journal entries"],"output_types":["created task.json files","updated task state","journal entries"],"categories":["automation-workflow","tool-use-integration"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"github-mindfold-ai--trellis__cap_11","uri":"capability://automation.workflow.marketplace.and.template.registry.for.community.contributed.configurations","name":"marketplace and template registry for community-contributed configurations","description":"Trellis includes a marketplace and template registry that enables teams to discover, share, and reuse project configurations, specs, and task templates contributed by the community. The registry is indexed and searchable, allowing developers to find templates for common project types (microservices, libraries, web apps, etc.) and integrate them into their projects. Registry entries include metadata (name, version, description, tags) and are version-controlled, enabling reproducible template usage.","intents":["I want to discover proven project configurations and specs from the community","I want to share my project's configuration with other teams or the community","I want to quickly set up a new project using a community-contributed template"],"best_for":["teams adopting Trellis and looking for best practices and templates","communities sharing project configurations and coding standards","organizations building on top of Trellis and contributing back to the ecosystem"],"limitations":["Registry is community-driven; no quality assurance or curation of contributed templates","Templates may become outdated as projects evolve; no automatic update mechanism","Registry discovery is manual; no recommendation system or popularity ranking"],"requires":["marketplace/registry infrastructure (web service or GitHub-based)","template metadata schema","community contribution guidelines"],"input_types":["template files and metadata","search queries","community contributions"],"output_types":["template listings","downloaded templates","integrated project configurations"],"categories":["automation-workflow","search-retrieval"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"github-mindfold-ai--trellis__cap_12","uri":"capability://automation.workflow.backend.script.execution.with.python.and.shell.support","name":"backend script execution with python and shell support","description":"Trellis supports backend script execution via Python and shell scripts (.trellis/scripts/) that implement task logic, command handlers, and platform integrations. Scripts can access project context (specs, tasks, workspace) via environment variables and file system APIs, and can update task state by modifying task.json files. The script execution layer abstracts platform differences and provides a unified interface for implementing Trellis workflows in Python or shell.","intents":["I want to implement custom task logic that runs as part of the Trellis workflow","I need to execute platform-specific initialization or setup scripts before AI sessions","I want to implement command handlers that interact with Trellis state and context"],"best_for":["teams implementing custom Trellis extensions and workflows","projects with complex initialization or setup requirements","developers building platform-specific integrations"],"limitations":["Scripts are executed synchronously; long-running scripts may block AI sessions","Script execution environment is sandboxed; limited access to system resources","Error handling is basic; script failures may not provide clear feedback to users"],"requires":["Python 3.9+ for Python scripts","shell interpreter for shell scripts",".trellis/scripts/ directory structure","script execution permissions"],"input_types":["Python or shell script files","environment variables with context","task.json files","command parameters"],"output_types":["script execution results","updated task.json files","generated artifacts"],"categories":["automation-workflow","code-generation-editing"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"github-mindfold-ai--trellis__cap_13","uri":"capability://code.generation.editing.unit.test.conventions.and.thinking.guides.for.ai.generated.code.quality","name":"unit test conventions and thinking guides for ai-generated code quality","description":"Trellis defines unit test conventions and thinking guides in the spec system that establish standards for test coverage, test structure, and code quality expectations. These conventions are auto-injected into AI sessions, guiding agents to generate code with appropriate test coverage and following project-specific testing patterns. The system includes golden tests (reference implementations) that agents can learn from, and integrates with CI/CD to validate generated code against test conventions.","intents":["I want AI agents to generate code with appropriate test coverage following my project's standards","I need to enforce consistent test structure and naming conventions across AI-generated code","I want to provide examples (golden tests) that guide AI agents toward high-quality implementations"],"best_for":["teams requiring high test coverage and code quality from AI-assisted development","projects with strict testing standards or compliance requirements","organizations using AI agents for production code generation"],"limitations":["Test conventions are guidelines; no automatic enforcement during code generation","Golden tests are static examples; no dynamic learning from test results","Test coverage validation is post-hoc (via CI/CD); no real-time feedback during generation"],"requires":["test convention specs in .trellis/spec/","golden test examples in project codebase","CI/CD integration for test validation"],"input_types":["test convention markdown specs","golden test examples","generated code"],"output_types":["injected test conventions in AI sessions","generated code with tests","test validation results"],"categories":["code-generation-editing","automation-workflow"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"github-mindfold-ai--trellis__cap_14","uri":"capability://automation.workflow.monorepo.structure.support.with.build.pipeline.and.release.management","name":"monorepo structure support with build pipeline and release management","description":"Trellis supports monorepo structures with a build pipeline and release management system that coordinates builds, tests, and releases across multiple packages. The system uses a TypeScript-based build pipeline (scripts in packages/cli/src/) that orchestrates package builds, test execution, and versioning. Release versioning is managed via .trellis/.version and migration manifests, enabling coordinated releases across the Trellis framework and community templates.","intents":["I want to manage a monorepo with multiple packages using Trellis","I need to coordinate builds and releases across multiple packages","I want to track versions and manage migrations across the monorepo"],"best_for":["organizations maintaining monorepos with multiple packages or services","projects with complex build and release pipelines","teams needing coordinated versioning across multiple packages"],"limitations":["Monorepo support is framework-specific; no generic monorepo abstraction","Build pipeline is TypeScript-based; limited support for other languages","Release management is manual; no automatic version bumping or changelog generation"],"requires":["monorepo structure (packages/ directory)","TypeScript build scripts","version management in .trellis/.version"],"input_types":["package definitions","build scripts","version metadata"],"output_types":["built packages","test results","release artifacts"],"categories":["automation-workflow","tool-use-integration"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"github-mindfold-ai--trellis__cap_2","uri":"capability://memory.knowledge.spec.system.with.auto.injected.coding.guidelines.and.project.standards","name":"spec system with auto-injected coding guidelines and project standards","description":"Trellis maintains a .trellis/spec/ directory containing project standards, patterns, coding guidelines, and architectural decisions in markdown format. These specs are automatically injected into AI agent sessions via the context injection layer, ensuring every coding task adheres to project conventions without manual specification per session. The spec system supports hierarchical organization (e.g., spec/cli/backend/) and integrates with the platform integration layer to customize injections per platform.","intents":["I want my project's coding standards and architectural patterns auto-injected into every AI session","I need to maintain consistency across AI-generated code without manually reviewing and correcting style violations","I want to evolve project guidelines over time and have new AI sessions automatically use updated standards"],"best_for":["teams with strict coding standards or architectural patterns that must be enforced across AI-assisted work","large projects where manual code review for style/pattern violations is expensive","organizations standardizing on specific frameworks, libraries, or design patterns"],"limitations":["Spec injection is one-way (specs → AI session); no feedback loop for AI agents to suggest spec updates based on generated code","Large spec systems (100+ markdown files) may exceed context windows of some AI models, requiring selective injection logic","Specs are markdown-based; no structured schema validation — inconsistent or outdated specs may confuse agents"],"requires":[".trellis/spec/ directory structure","markdown files documenting standards and patterns","platform integration layer configured to inject specs"],"input_types":["markdown specification files","architectural decision records","code style guides","pattern examples"],"output_types":["injected context in AI sessions","spec-compliant generated code"],"categories":["memory-knowledge","automation-workflow"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"github-mindfold-ai--trellis__cap_3","uri":"capability://tool.use.integration.context.injection.and.session.script.execution.for.ai.platforms","name":"context injection and session script execution for ai platforms","description":"Trellis implements a context injection layer that automatically loads and injects project context (specs, task details, workspace journals) into AI agent sessions before code generation begins. Session scripts (Python/shell) are executed to prepare the environment, set up state, and configure platform-specific hooks. The CLIAdapter pattern detects the active AI platform and routes context appropriately, supporting Claude Code, Cursor, OpenCode, and other platforms with platform-specific entry points.","intents":["I want project context automatically loaded into AI sessions without manual setup","I need to run initialization scripts before AI agents start coding (e.g., environment setup, state preparation)","I want different context injected depending on which AI platform I'm using"],"best_for":["developers using multiple AI platforms who need consistent context setup","teams with complex initialization requirements (environment variables, state files, database connections)","projects where session setup overhead is significant and should be automated"],"limitations":["Context injection timing depends on platform hooks; some platforms may not support pre-session initialization","Session scripts are platform-specific; scripts written for Claude Code may not work in Cursor without adaptation","Context injection adds latency to session startup; large context payloads may exceed platform limits or slow down agent responsiveness"],"requires":["platform-specific integration layer (.claude/, .cursor/, etc.)","session scripts in .trellis/scripts/ or platform directories","Python 3.9+ for Python-based session scripts"],"input_types":["specs from .trellis/spec/","task context from .trellis/tasks/","workspace journals from .trellis/workspace/","session scripts (Python, shell)"],"output_types":["injected context in AI session","initialized environment state","platform-specific configuration"],"categories":["tool-use-integration","automation-workflow"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"github-mindfold-ai--trellis__cap_4","uri":"capability://memory.knowledge.developer.workspace.journals.for.project.memory.and.continuity","name":"developer workspace journals for project memory and continuity","description":"Trellis maintains developer-specific workspace journals (.trellis/workspace/<developer>/) as markdown files (e.g., journal-4.md) that preserve project memory, design decisions, and session notes across AI-assisted work. Journals are version-controlled and can be injected into AI sessions as context, enabling agents to understand the project's evolution and previous decisions. The workspace system supports multiple developers with isolated journal spaces while maintaining shared project context via specs and tasks.","intents":["I want to preserve my understanding of project decisions and design rationale across multiple AI sessions","I need AI agents to understand the project's evolution and previous attempts at solving problems","I want to maintain a personal knowledge base of project-specific insights without cluttering shared documentation"],"best_for":["individual developers or small teams using AI agents for extended projects","projects where design decisions and rationale need to be preserved for future reference","teams onboarding new developers who need to understand project history and context"],"limitations":["Journals are developer-specific; no automatic synchronization or conflict resolution across team members","Journal content is unstructured markdown; no schema validation or consistency checks","Large journals may exceed context windows if injected in full; selective injection logic required for large projects"],"requires":[".trellis/workspace/<developer>/ directory","markdown journal files","developer identification for workspace isolation"],"input_types":["markdown journal entries","design notes","session summaries","decision records"],"output_types":["injected journal context in AI sessions","updated journal files with new entries"],"categories":["memory-knowledge","automation-workflow"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"github-mindfold-ai--trellis__cap_5","uri":"capability://planning.reasoning.multi.agent.pipeline.for.task.decomposition.and.orchestration","name":"multi-agent pipeline for task decomposition and orchestration","description":"Trellis implements a multi-agent pipeline that decomposes high-level developer intent into discrete tasks and coordinates multiple AI agents across those tasks. The pipeline uses the task management system to track decomposition, dependencies, and state, enabling sequential or parallel execution of AI-assisted work. Agents communicate via task.json state files and context injection, creating a workflow where each agent understands its role, dependencies, and success criteria.","intents":["I want to break down a large feature into subtasks that multiple AI agents can work on in parallel","I need to coordinate AI agents across multiple tasks with clear dependencies and handoff points","I want to track progress and state across a multi-agent workflow without manual coordination"],"best_for":["teams using multiple AI agents (Claude, Cursor, etc.) on the same project","large features that naturally decompose into independent subtasks","projects where parallel AI-assisted work can accelerate development"],"limitations":["Multi-agent coordination relies on task.json state files; no built-in distributed locking or conflict resolution","Agent communication is asynchronous via state files; no real-time coordination or message passing","Dependency tracking is manual; no automatic deadlock detection or circular dependency prevention"],"requires":["task management system (.trellis/tasks/)","task.json schema with dependency tracking","multiple AI agents configured with Trellis integration"],"input_types":["high-level feature description","task decomposition (task.json files)","dependency graph"],"output_types":["task state updates","completed subtasks","integrated feature code"],"categories":["planning-reasoning","automation-workflow"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"github-mindfold-ai--trellis__cap_6","uri":"capability://tool.use.integration.platform.specific.integration.layer.with.cliadapter.pattern","name":"platform-specific integration layer with cliadapter pattern","description":"Trellis provides a platform integration layer that abstracts differences between AI coding platforms (Claude Code, Cursor, OpenCode, Gemini CLI) via a CLIAdapter pattern. The adapter detects the active platform, routes context injection appropriately, and executes platform-specific hooks and entry points. Platform configurators generate platform-specific configuration files (.claude/, .cursor/, etc.) during initialization, enabling seamless switching between tools while maintaining consistent project context.","intents":["I want to use different AI platforms without reconfiguring my project context","I need platform-specific customizations (e.g., Claude Code skills vs Cursor commands) to work transparently","I want to add support for new AI platforms without modifying core Trellis logic"],"best_for":["teams using multiple AI coding platforms and needing unified project structure","developers experimenting with different AI tools without project reconfiguration","organizations building custom AI platform integrations on top of Trellis"],"limitations":["Platform support depends on each tool's API and hook system; not all platforms equally supported","Platform-specific features (e.g., Claude Code skills) require custom implementation per platform","CLIAdapter adds abstraction overhead; platform-specific optimizations may be lost"],"requires":["TypeScript CLI with platform configurators","platform-specific integration modules (.claude/, .cursor/, etc.)","platform detection logic (environment variables, file markers)"],"input_types":["platform detection signals","platform-specific configuration","context for injection"],"output_types":["platform-specific entry points","platform configuration files","routed context injection"],"categories":["tool-use-integration","automation-workflow"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"github-mindfold-ai--trellis__cap_7","uri":"capability://automation.workflow.template.system.for.project.scaffolding.and.spec.generation","name":"template system for project scaffolding and spec generation","description":"Trellis provides a template system (.trellis/templates/) that scaffolds new projects with pre-configured specs, task structures, and integration layers. Templates are extracted and customized during initialization via the Init command, enabling teams to standardize project structure across multiple repositories. The template registry supports community-contributed templates, enabling reuse of proven project configurations and coding guidelines.","intents":["I want to quickly set up a new project with standard specs, task structure, and AI platform integration","I want to enforce consistent project structure across multiple repositories in my organization","I want to share proven project configurations with my team or the community"],"best_for":["organizations standardizing project structure across multiple repositories","teams creating many similar projects (microservices, libraries, etc.)","communities sharing best practices and project configurations"],"limitations":["Templates are static; no dynamic customization based on project type or team preferences during initialization","Template versioning and updates require manual management; no automatic template updates for existing projects","Template registry is community-driven; no quality assurance or curation of contributed templates"],"requires":["template files in .trellis/templates/ or registry","TypeScript CLI with template extraction logic","template.json or similar manifest for template metadata"],"input_types":["template files (specs, tasks, scripts)","template metadata (name, version, description)","customization parameters"],"output_types":["scaffolded .trellis/ directory","project-specific specs and tasks","platform integration files"],"categories":["automation-workflow","code-generation-editing"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"github-mindfold-ai--trellis__cap_8","uri":"capability://automation.workflow.cli.driven.initialization.and.migration.system.with.version.management","name":"cli-driven initialization and migration system with version management","description":"Trellis provides a TypeScript-based CLI (@mindfoldhq/trellis) that initializes new projects via the Init command, creating the .trellis/ directory structure and platform-specific integration files. The CLI includes an Update command with a migration system that manages version upgrades, schema changes, and breaking changes via migration manifests (e.g., 0.4.0.json). Version tracking in .trellis/.version enables automatic migration detection and execution, ensuring projects stay synchronized with CLI updates.","intents":["I want to quickly initialize a new project with Trellis structure and platform integration","I need to upgrade my project to a new Trellis version without manual reconfiguration","I want to track which Trellis version my project is using and detect when updates are available"],"best_for":["teams adopting Trellis across multiple projects","organizations managing Trellis versions across a fleet of repositories","developers needing reproducible project initialization"],"limitations":["CLI is TypeScript-only; no Python or other language implementations","Migration system is declarative (manifests); complex migrations may require custom scripts","Version tracking is per-project; no centralized version management across multiple repositories"],"requires":["Node.js 18+","@mindfoldhq/trellis CLI installed globally or via npx","Git repository with write access"],"input_types":["project directory","platform selection (Claude Code, Cursor, etc.)","template selection"],"output_types":[".trellis/ directory structure","platform-specific integration files",".trellis/.version file"],"categories":["automation-workflow","tool-use-integration"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"github-mindfold-ai--trellis__cap_9","uri":"capability://tool.use.integration.skills.and.slash.commands.for.ai.platform.specific.workflows","name":"skills and slash commands for ai platform-specific workflows","description":"Trellis supports skills (Claude Code) and slash commands (Cursor, OpenCode) as platform-specific extensions that enable AI agents to perform specialized tasks within their native environments. Skills and commands are defined in platform-specific configuration files and can invoke backend scripts, access project context, or trigger Trellis workflows. The system enables teams to extend AI platform capabilities with project-specific logic without modifying the core Trellis framework.","intents":["I want to add custom commands to my AI platform that integrate with Trellis workflows","I need AI agents to access project-specific tools or scripts via platform-native commands","I want to standardize custom commands across my team's AI platform usage"],"best_for":["teams with custom workflows or tools that should be accessible to AI agents","projects needing platform-specific optimizations or integrations","organizations building AI platform extensions on top of Trellis"],"limitations":["Skills and commands are platform-specific; code written for Claude Code skills may not work in Cursor commands","Command definitions are manual; no automatic generation from project structure or codebase","Command execution is asynchronous; no real-time feedback or streaming output"],"requires":["platform-specific configuration files (.claude/skills.json, .cursor/commands.json, etc.)","backend scripts to implement command logic","platform API documentation for skill/command definitions"],"input_types":["skill/command definitions (JSON)","backend script implementations","command parameters"],"output_types":["command execution results","project context or artifacts"],"categories":["tool-use-integration","automation-workflow"],"confidence":0.5,"matches":0,"success_rate":0}],"trust":{"score":45,"verified":false,"data_access_risk":"high","permissions":["Node.js 18+ for CLI (@mindfoldhq/trellis)","Git repository with write access to root directory","At least one supported AI platform (Claude Code, Cursor, OpenCode, Gemini CLI)","Python 3.9+ for task.py and backend scripts",".trellis/ directory initialized via CLI","task.json schema defined in project specs","Python 3.9+ for task.py lifecycle scripts","platform-specific command definitions","backend scripts for command implementation","task.json schema for state management"],"failure_modes":["Requires TypeScript CLI setup and .trellis/ directory initialization — not zero-config","Platform integration depends on each AI platform's support for custom hooks/entry points; not all platforms equally supported","Context injection latency scales with spec system size; large codebases with extensive guidelines may add session startup overhead","Task state is stored in task.json; no built-in persistence layer or database — requires external systems for cross-project task aggregation","Task lifecycle is project-specific; no standardized task schema across Trellis instances without custom spec definitions","Manual task creation and PRD writing required; no automatic task generation from issue trackers or feature requests","Commands are platform-specific; not all AI platforms support custom commands equally","Command execution is asynchronous; no real-time feedback on task state changes","Commands are text-based; no rich UI for task creation or state management","Registry is community-driven; no quality assurance or curation of contributed templates","builder identity is not verified yet","no observed match outcomes yet"],"rank_breakdown":{"adoption":0.6059773591359205,"quality":0.35,"ecosystem":0.55,"match_graph":0.25,"freshness":0.75,"weights":{"adoption":0.25,"quality":0.25,"ecosystem":0.1,"match_graph":0.28,"freshness":0.12}},"observed_outcomes":{"matches":0,"success_rate":0,"avg_confidence":0,"top_intents":[],"last_matched_at":null},"maintenance":{"status":"active","updated_at":"2026-05-24T12:16:22.062Z","last_scraped_at":"2026-05-03T13:59:55.148Z","last_commit":"2026-05-03T13:10:46Z"},"community":{"stars":7069,"forks":394,"weekly_downloads":null,"model_downloads":null,"model_likes":null}},"distribution":{"claim_url":"https://unfragile.ai/submit?claim=mindfold-ai--trellis","compare_url":"https://unfragile.ai/compare?artifact=mindfold-ai--trellis"}},"signature":"HWXWjFV+QaICD1T0QYXZv7NJrmVyljtFEnLk2KL7n+ZGtakU9jkyGyJB02BRGf77f3/z8xWdmFv6pfiVcx9dBA==","signedAt":"2026-06-22T01:37:33.804Z","signedBy":"unfragile.ai","version":1},"_links":{"self":"https://unfragile.ai/api/v1/passport/mindfold-ai--trellis","artifact":"https://unfragile.ai/mindfold-ai--trellis","verify":"https://unfragile.ai/api/v1/verify?slug=mindfold-ai--trellis","publicKey":"https://unfragile.ai/api/v1/trust-passport-public-key","spec":"https://unfragile.ai/trust","schema":"https://unfragile.ai/schema.json","docs":"https://unfragile.ai/docs"}}