{"passport":{"unfragile":{"@version":"1.0","version":"2026-05","artifact":{"id":"github-fjb040911--ai-rules","slug":"fjb040911--ai-rules","name":"ai-rules","type":"repo","url":"https://github.com/fjb040911/ai-rules","page_url":"https://unfragile.ai/fjb040911--ai-rules","categories":["frameworks-sdks","code-editors","app-builders"],"tags":["ai-code-review","ai-coding","code-review","code-rules","repair-prompt"],"pricing":{"model":"open_source","free":true,"starting_price":null},"status":"active","verified":false},"capabilities":[{"id":"github-fjb040911--ai-rules__cap_0","uri":"capability://safety.moderation.project.boundary.enforcement.via.rule.files","name":"project-boundary-enforcement-via-rule-files","description":"Enforces architectural constraints by parsing declarative rule files (likely YAML or JSON format) that define project boundaries, forbidden patterns, and allowed libraries. These rules are injected into AI agent prompts or used to validate generated code against a project's governance model, preventing agents from violating established architectural decisions. The system likely maintains a rule registry that can be version-controlled and shared across team members.","intents":["I want to prevent Cursor/Windsurf from importing unauthorized libraries or breaking my design system","I need to enforce consistent architectural patterns across AI-generated code without manual review","I want to codify my project's constraints so AI agents respect them automatically"],"best_for":["teams using AI code editors (Cursor, Windsurf, Copilot) who want guardrails","projects with strict architectural requirements or design system compliance","organizations scaling AI-assisted development across multiple codebases"],"limitations":["Requires explicit rule definition — no automatic pattern detection from existing codebase","Rule enforcement depends on AI agent's ability to parse and respect injected constraints; some agents may ignore or misinterpret rules","No built-in conflict resolution when rules contradict each other or clash with agent training"],"requires":["AI code editor integration (Cursor, Windsurf, or Copilot with plugin/extension support)","Rule file format support (YAML, JSON, or custom DSL)","JavaScript/Node.js 14+ for rule parsing and validation engine"],"input_types":["rule definition files (YAML/JSON)","generated code from AI agents","project metadata (dependencies, file structure)"],"output_types":["validation results (pass/fail with violation details)","prompt injections for AI agents","rule violation reports"],"categories":["safety-moderation","code-generation-editing"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"github-fjb040911--ai-rules__cap_1","uri":"capability://code.generation.editing.ui.library.and.design.system.enforcement","name":"ui-library-and-design-system-enforcement","description":"Enforces usage of specific UI libraries and design system components by defining allowed component registries and patterns in rule files. When AI agents generate code, the system validates that only approved components are used and that they follow design system conventions (naming, props, composition patterns). This prevents agents from creating custom components or using incompatible libraries that break visual consistency.","intents":["I want AI to only use components from my design system, not create custom divs or unstyled elements","I need to ensure all AI-generated UI code follows my component library's API and naming conventions","I want to prevent AI from mixing multiple UI frameworks in the same project"],"best_for":["design-system-heavy teams (Material-UI, Chakra, Tailwind, custom systems)","enterprises with strict visual consistency requirements","product teams where UI coherence is critical to brand"],"limitations":["Requires maintaining an up-to-date component registry as design system evolves","Cannot validate visual correctness — only structural/API compliance","May over-constrain AI agents, leading to suboptimal or verbose component usage patterns"],"requires":["Design system component registry (JSON or TypeScript definitions)","Rule file defining allowed components and their valid prop combinations","Integration with AI agent's code generation pipeline"],"input_types":["component registry definitions","design system documentation","generated component code"],"output_types":["component usage validation results","violation reports (e.g., 'CustomButton used instead of Button from @company/ui')","corrected code suggestions"],"categories":["code-generation-editing","safety-moderation"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"github-fjb040911--ai-rules__cap_2","uri":"capability://code.generation.editing.architectural.pattern.validation.and.repair","name":"architectural-pattern-validation-and-repair","description":"Validates generated code against defined architectural patterns (e.g., MVC, layered architecture, dependency injection) and provides repair suggestions when violations are detected. The system likely uses pattern matching or AST analysis to identify violations and can either block generation or suggest corrections. This prevents architectural drift caused by AI agents that don't understand project structure.","intents":["I want to ensure AI-generated code follows my project's layered architecture (controllers, services, models)","I need to catch when AI puts business logic in the wrong layer before it gets committed","I want AI to automatically suggest the correct file location and structure for new code"],"best_for":["teams with well-defined architectural patterns (layered, hexagonal, microservices)","large codebases where architectural consistency is critical","projects with strict separation of concerns requirements"],"limitations":["Requires explicit pattern definition — cannot infer architecture from codebase automatically","Pattern matching may produce false positives for legitimate architectural variations","Repair suggestions are heuristic-based and may not match team's preferred refactoring style"],"requires":["Architectural pattern definitions (rules file with layer/module structure)","AST parser or code analysis engine to detect violations","Integration point in AI agent workflow (pre-generation or post-generation validation)"],"input_types":["architectural pattern rules","generated code","project structure metadata"],"output_types":["pattern violation reports with location and severity","repair suggestions (refactored code or file relocation)","architectural compliance score"],"categories":["code-generation-editing","planning-reasoning"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"github-fjb040911--ai-rules__cap_3","uri":"capability://tool.use.integration.ai.agent.prompt.injection.and.constraint.embedding","name":"ai-agent-prompt-injection-and-constraint-embedding","description":"Injects project rules and constraints directly into AI agent prompts (system prompts or context windows) so agents generate code that respects boundaries from the start. The system likely formats rules into natural language instructions that agents can understand and follow, reducing the need for post-generation validation. This works by intercepting or augmenting the prompts sent to AI models before code generation.","intents":["I want to embed my project rules into Cursor/Windsurf's system prompt so it generates compliant code immediately","I need to provide context about my architecture to AI agents without manual explanation each time","I want to reduce iteration cycles by having AI understand constraints upfront"],"best_for":["teams using AI code editors with prompt customization support","projects where preventing violations is cheaper than fixing them post-generation","workflows where AI agents need deep context about project constraints"],"limitations":["Prompt injection effectiveness depends on AI model's instruction-following capability; some models may ignore or misinterpret injected rules","Large rule sets can consume significant context window, reducing space for actual code generation","No guarantee that injected constraints will be respected — requires testing and validation"],"requires":["AI editor with prompt customization API (Cursor, Windsurf, or similar)","Rule-to-prompt translation engine (converts rules to natural language instructions)","Integration point to intercept and augment prompts before sending to AI model"],"input_types":["rule definitions","project context (architecture, libraries, patterns)","AI agent system prompt template"],"output_types":["augmented system prompts","constraint-aware code generation","compliance metrics (% of generated code that respects rules)"],"categories":["tool-use-integration","safety-moderation"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"github-fjb040911--ai-rules__cap_4","uri":"capability://automation.workflow.multi.agent.rule.synchronization.and.versioning","name":"multi-agent-rule-synchronization-and-versioning","description":"Manages rule versions and synchronizes them across multiple AI agents and team members, ensuring consistent governance across different tools (Cursor, Windsurf, Copilot). Rules are likely stored in a version-controlled format that can be distributed to team members and integrated into different agent environments. This prevents rule drift where different developers have different constraint sets.","intents":["I want all team members using different AI editors to follow the same rules","I need to update rules once and have them propagate to everyone's AI agent setup","I want to track when rules change and why (audit trail for governance)"],"best_for":["distributed teams using multiple AI code editors","organizations with governance requirements (compliance, audit trails)","projects where rule consistency across team is critical"],"limitations":["Requires team coordination to adopt and maintain rule files","No built-in conflict resolution for rule updates that break existing code","Synchronization is manual or requires CI/CD integration — no real-time push mechanism"],"requires":["Version control system (Git) for rule files","Rule file format that's human-readable and diff-friendly (YAML or JSON)","Distribution mechanism (package manager, shared repository, or CI/CD integration)"],"input_types":["rule definitions","version metadata","team member configurations"],"output_types":["versioned rule files","distribution packages","synchronization status reports"],"categories":["automation-workflow","safety-moderation"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"github-fjb040911--ai-rules__cap_5","uri":"capability://code.generation.editing.code.violation.detection.and.reporting","name":"code-violation-detection-and-reporting","description":"Detects violations of project rules in generated code and produces detailed reports identifying what was violated, where, and why. The system likely uses pattern matching, AST analysis, or semantic analysis to identify violations and generates human-readable reports that developers can act on. Reports may include severity levels, suggested fixes, and links to rule documentation.","intents":["I want to see exactly what rules my AI-generated code violated and why","I need a report format I can share with my team to discuss violations","I want to understand which rules are most frequently violated so I can improve them"],"best_for":["teams doing code review of AI-generated code","projects tracking architectural compliance metrics","organizations with governance reporting requirements"],"limitations":["Report quality depends on rule specificity — vague rules produce vague violation reports","Cannot explain why AI violated a rule (no insight into agent reasoning)","False positives possible if rules are overly broad or poorly defined"],"requires":["Rule definitions with clear violation criteria","Code analysis engine (AST parser, pattern matcher, or semantic analyzer)","Report generation and formatting engine"],"input_types":["generated code","rule definitions","project context"],"output_types":["violation reports (JSON, HTML, or markdown)","severity-ranked violation lists","compliance metrics and trends"],"categories":["code-generation-editing","safety-moderation"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"github-fjb040911--ai-rules__cap_6","uri":"capability://code.generation.editing.dependency.and.import.governance","name":"dependency-and-import-governance","description":"Enforces rules about which dependencies and imports are allowed in the codebase, preventing AI agents from introducing unauthorized libraries or creating circular dependencies. The system validates import statements against an allowed dependency list and can detect when agents try to import from forbidden modules. This works by analyzing import/require statements and comparing them against a whitelist or blacklist defined in rules.","intents":["I want to prevent AI from importing heavy dependencies that bloat my bundle","I need to ensure all imports come from approved, security-vetted libraries","I want to detect when AI creates circular dependencies or imports from internal modules incorrectly"],"best_for":["projects with strict dependency management policies","teams concerned about supply chain security","monorepos where import boundaries are critical"],"limitations":["Requires maintaining an up-to-date whitelist/blacklist of allowed dependencies","Cannot validate transitive dependencies — only direct imports","May block legitimate imports if whitelist is too restrictive"],"requires":["Dependency whitelist/blacklist rules","Import statement parser (AST-based for accuracy)","Package metadata (to check versions, security status)"],"input_types":["import/require statements","dependency rules","package.json or equivalent"],"output_types":["import validation results","unauthorized import reports","dependency compliance score"],"categories":["code-generation-editing","safety-moderation"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"github-fjb040911--ai-rules__cap_7","uri":"capability://code.generation.editing.code.style.and.naming.convention.enforcement","name":"code-style-and-naming-convention-enforcement","description":"Enforces consistent code style and naming conventions (camelCase, PascalCase, snake_case, etc.) across AI-generated code by validating against rules. The system analyzes variable names, function names, class names, and file names to ensure they match project conventions. This prevents stylistic inconsistencies that arise when AI agents generate code without understanding team preferences.","intents":["I want all AI-generated variables and functions to follow my team's naming convention","I need to ensure file names match my project's structure (e.g., components in PascalCase)","I want to catch style violations before code review"],"best_for":["teams with strict style guides or linting rules","projects where code consistency is important for readability","organizations with coding standards documentation"],"limitations":["Naming convention rules can be subjective and hard to formalize","Cannot validate semantic correctness of names (e.g., 'isFetching' is grammatically correct but semantically wrong)","May conflict with other rules or conventions"],"requires":["Naming convention rules (regex patterns or rule definitions)","AST parser to extract identifiers from code","Integration with code analysis pipeline"],"input_types":["generated code","naming convention rules","style guide definitions"],"output_types":["naming violation reports","suggested renames","style compliance metrics"],"categories":["code-generation-editing","safety-moderation"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"github-fjb040911--ai-rules__cap_8","uri":"capability://code.generation.editing.test.coverage.and.quality.gate.enforcement","name":"test-coverage-and-quality-gate-enforcement","description":"Enforces minimum test coverage and quality standards for AI-generated code by validating that generated functions have corresponding tests and meet coverage thresholds. The system can detect when AI generates code without tests and flag it as a violation. This prevents AI agents from shipping untested code.","intents":["I want to ensure AI-generated code includes tests, not just implementation","I need to enforce minimum coverage thresholds for AI-generated functions","I want to catch untested code before it gets merged"],"best_for":["teams with strict test coverage requirements","projects where code quality is critical (financial, healthcare, security)","organizations using AI for feature development, not just scaffolding"],"limitations":["Requires test files to be generated alongside implementation — adds complexity","Cannot validate test quality, only coverage metrics","May penalize legitimate cases where tests aren't needed (e.g., simple utilities)"],"requires":["Test coverage rules (minimum coverage %, required test types)","Test file detection and parsing","Coverage analysis tool integration (Jest, Vitest, etc.)"],"input_types":["generated code","test files","coverage thresholds"],"output_types":["coverage reports","untested code flags","quality gate pass/fail"],"categories":["code-generation-editing","safety-moderation"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"github-fjb040911--ai-rules__cap_9","uri":"capability://code.generation.editing.documentation.and.comment.requirement.enforcement","name":"documentation-and-comment-requirement-enforcement","description":"Enforces documentation and comment requirements for AI-generated code, ensuring that complex functions, public APIs, and architectural decisions are documented. The system validates that generated code includes JSDoc comments, README updates, or other documentation as defined by rules. This prevents AI from generating undocumented code.","intents":["I want AI to generate JSDoc comments for all public functions","I need to ensure architectural decisions are documented when AI creates new modules","I want to catch undocumented code before it gets merged"],"best_for":["teams with documentation standards","projects with complex architectures that require explanation","organizations maintaining long-lived codebases where documentation is critical"],"limitations":["Cannot validate documentation quality, only presence","Requires defining which code requires documentation (heuristic-based)","May produce verbose or redundant comments if rules are too strict"],"requires":["Documentation rules (which code requires docs, format requirements)","Comment/JSDoc parser","Documentation template definitions"],"input_types":["generated code","documentation rules","comment/JSDoc templates"],"output_types":["undocumented code reports","documentation suggestions","documentation compliance metrics"],"categories":["code-generation-editing","safety-moderation"],"confidence":0.5,"matches":0,"success_rate":0}],"trust":{"score":43,"verified":false,"data_access_risk":"low","permissions":["AI code editor integration (Cursor, Windsurf, or Copilot with plugin/extension support)","Rule file format support (YAML, JSON, or custom DSL)","JavaScript/Node.js 14+ for rule parsing and validation engine","Design system component registry (JSON or TypeScript definitions)","Rule file defining allowed components and their valid prop combinations","Integration with AI agent's code generation pipeline","Architectural pattern definitions (rules file with layer/module structure)","AST parser or code analysis engine to detect violations","Integration point in AI agent workflow (pre-generation or post-generation validation)","AI editor with prompt customization API (Cursor, Windsurf, or similar)"],"failure_modes":["Requires explicit rule definition — no automatic pattern detection from existing codebase","Rule enforcement depends on AI agent's ability to parse and respect injected constraints; some agents may ignore or misinterpret rules","No built-in conflict resolution when rules contradict each other or clash with agent training","Requires maintaining an up-to-date component registry as design system evolves","Cannot validate visual correctness — only structural/API compliance","May over-constrain AI agents, leading to suboptimal or verbose component usage patterns","Requires explicit pattern definition — cannot infer architecture from codebase automatically","Pattern matching may produce false positives for legitimate architectural variations","Repair suggestions are heuristic-based and may not match team's preferred refactoring style","Prompt injection effectiveness depends on AI model's instruction-following capability; some models may ignore or misinterpret injected rules","builder identity is not verified yet","no observed match outcomes yet"],"rank_breakdown":{"adoption":0.3679993725210187,"quality":0.45,"ecosystem":0.75,"match_graph":0.25,"freshness":0.75,"weights":{"adoption":0.3,"quality":0.2,"ecosystem":0.15,"match_graph":0.3,"freshness":0.05}},"observed_outcomes":{"matches":0,"success_rate":0,"avg_confidence":0,"top_intents":[],"last_matched_at":null},"maintenance":{"status":"active","updated_at":"2026-05-24T12:16:21.550Z","last_scraped_at":"2026-04-22T08:03:25.620Z","last_commit":"2026-04-17T06:02:12Z"},"community":{"stars":1011,"forks":18,"weekly_downloads":null,"model_downloads":null,"model_likes":null}},"distribution":{"claim_url":"https://unfragile.ai/submit?claim=fjb040911--ai-rules","compare_url":"https://unfragile.ai/compare?artifact=fjb040911--ai-rules"}},"signature":"KyBnRXqMCrGHOJRrNWSyb8FMMHjyJf3BvpRX/6tdpS15feve4rtMnUjaer1rOY4LbnUCGe7frOm+2qY4peHJBw==","signedAt":"2026-06-22T13:22:38.330Z","signedBy":"unfragile.ai","version":1},"_links":{"self":"https://unfragile.ai/api/v1/passport/fjb040911--ai-rules","artifact":"https://unfragile.ai/fjb040911--ai-rules","verify":"https://unfragile.ai/api/v1/verify?slug=fjb040911--ai-rules","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"}}