gabbe-kit 1.0.0
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- package/LICENSE +25 -0
- package/LICENSE-CODE +202 -0
- package/README.md +817 -0
- package/agents/AGENTS.md +542 -0
- package/agents/CONSTITUTION.md +188 -0
- package/agents/guides/00-index.md +142 -0
- package/agents/guides/ai/a2ui-protocols.md +71 -0
- package/agents/guides/ai/actor-agent-frameworks.md +82 -0
- package/agents/guides/ai/agent-communication.md +146 -0
- package/agents/guides/ai/agent-identity-trust.md +69 -0
- package/agents/guides/ai/agent-only-cognition.md +73 -0
- package/agents/guides/ai/agent-only-swarms.md +70 -0
- package/agents/guides/ai/agent-operating-ergonomics.md +52 -0
- package/agents/guides/ai/agent-ui.md +106 -0
- package/agents/guides/ai/ai-agentic.md +309 -0
- package/agents/guides/ai/beyond-llms.md +60 -0
- package/agents/guides/ai/dynamic-capability-loading.md +121 -0
- package/agents/guides/ai/gabbe-innovations.md +111 -0
- package/agents/guides/ai/model-customization-decisions.md +78 -0
- package/agents/guides/ai/multi-agent-systems.md +85 -0
- package/agents/guides/ai/self-evolving-skills.md +137 -0
- package/agents/guides/ai/self-healing-summary.md +21 -0
- package/agents/guides/ai/visual-mcp-integration.md +106 -0
- package/agents/guides/architecture/api-standards.md +61 -0
- package/agents/guides/architecture/blockchain-dlt.md +36 -0
- package/agents/guides/architecture/critical-systems-arch.md +66 -0
- package/agents/guides/architecture/event-driven-architecture.md +39 -0
- package/agents/guides/architecture/microservices.md +292 -0
- package/agents/guides/architecture/monolith.md +303 -0
- package/agents/guides/architecture/orchestration.md +75 -0
- package/agents/guides/architecture/system-qualities.md +51 -0
- package/agents/guides/architecture/system-scalability.md +47 -0
- package/agents/guides/architecture/systems-architecture.md +506 -0
- package/agents/guides/data/semantic-web.md +23 -0
- package/agents/guides/data/sql-nosql.md +305 -0
- package/agents/guides/industry/engineering-standards.md +36 -0
- package/agents/guides/industry/global-standards.md +24 -0
- package/agents/guides/industry/healthcare-fhir.md +33 -0
- package/agents/guides/industry/industrial-iot.md +33 -0
- package/agents/guides/industry/telecom-networks.md +34 -0
- package/agents/guides/languages/c-sharp.md +66 -0
- package/agents/guides/languages/go-lang.md +251 -0
- package/agents/guides/languages/java.md +73 -0
- package/agents/guides/languages/js-ts-nodejs.md +361 -0
- package/agents/guides/languages/nodejs-advanced.md +56 -0
- package/agents/guides/languages/php-laravel.md +376 -0
- package/agents/guides/languages/python-fastapi-ai.md +257 -0
- package/agents/guides/languages/rust.md +73 -0
- package/agents/guides/ops/compliance-audit.md +177 -0
- package/agents/guides/ops/cost-optimization.md +57 -0
- package/agents/guides/ops/dev-environments.md +67 -0
- package/agents/guides/ops/dev-workflow.md +44 -0
- package/agents/guides/ops/gabbe-cli-workflows.md +252 -0
- package/agents/guides/ops/production-health.md +62 -0
- package/agents/guides/ops/troubleshooting-guide.md +69 -0
- package/agents/guides/patterns/agentic-design-patterns.md +308 -0
- package/agents/guides/patterns/agentic-patterns.md +43 -0
- package/agents/guides/patterns/ai-native-scenarios.md +71 -0
- package/agents/guides/patterns/autonomous-swarm-patterns.md +42 -0
- package/agents/guides/patterns/design-patterns.md +68 -0
- package/agents/guides/patterns/enterprise-migration-scenario.md +58 -0
- package/agents/guides/patterns/enterprise-patterns.md +56 -0
- package/agents/guides/patterns/software-design-patterns.md +106 -0
- package/agents/guides/patterns/time-complexity-analysis.md +116 -0
- package/agents/guides/planning/product-requirements.md +407 -0
- package/agents/guides/planning/strategic-analysis.md +98 -0
- package/agents/guides/planning/visual-product-specs.md +162 -0
- package/agents/guides/principles/clean-code-standards.md +51 -0
- package/agents/guides/principles/computing-foundations.md +87 -0
- package/agents/guides/principles/diagramming-standards.md +568 -0
- package/agents/guides/principles/evaluation-strategy.md +103 -0
- package/agents/guides/principles/future-tech.md +35 -0
- package/agents/guides/principles/human-agent-collaboration.md +54 -0
- package/agents/guides/principles/legacy-tech.md +61 -0
- package/agents/guides/principles/mathematical-foundations.md +103 -0
- package/agents/guides/principles/modeling-methods.md +97 -0
- package/agents/guides/principles/no-code-integration.md +84 -0
- package/agents/guides/principles/testing-strategy.md +97 -0
- package/agents/guides/principles/visual-design-system.md +44 -0
- package/agents/guides/processes/RARV_CYCLE.md +262 -0
- package/agents/guides/processes/extension-protocol.md +183 -0
- package/agents/guides/processes/full-system-lifecycle.md +47 -0
- package/agents/guides/processes/knowledge-integration.md +82 -0
- package/agents/guides/processes/loki-sdlc-phases.md +446 -0
- package/agents/guides/product/green-software.md +38 -0
- package/agents/guides/product/sustainability-checks.md +29 -0
- package/agents/guides/security/ai-risk-standards-map.md +98 -0
- package/agents/guides/security/api-security.md +51 -0
- package/agents/guides/security/cryptography-standards.md +38 -0
- package/agents/guides/security/privacy-data-protection.md +41 -0
- package/agents/guides/security/secure-architecture.md +43 -0
- package/agents/guides/security/threat-modeling.md +46 -0
- package/agents/memory/AUDIT_LOG.md +48 -0
- package/agents/memory/CONTINUITY.md +49 -0
- package/agents/memory/PROJECT_STATE.md +134 -0
- package/agents/memory/RESUME_POINTER.md +15 -0
- package/agents/memory/episodic/DECISION_LOG_TEMPLATE.md +104 -0
- package/agents/memory/semantic/PROJECT_KNOWLEDGE_TEMPLATE.md +194 -0
- package/agents/memory/semantic/VECTOR_DB_CONFIG_TEMPLATE.json +46 -0
- package/agents/personas/00-index.md +148 -0
- package/agents/personas/biz-compliance.md +112 -0
- package/agents/personas/biz-legal.md +131 -0
- package/agents/personas/eng-api.md +110 -0
- package/agents/personas/eng-backend.md +113 -0
- package/agents/personas/eng-data.md +50 -0
- package/agents/personas/eng-database.md +95 -0
- package/agents/personas/eng-frontend.md +75 -0
- package/agents/personas/eng-infra.md +105 -0
- package/agents/personas/eng-messaging.md +50 -0
- package/agents/personas/eng-ml.md +50 -0
- package/agents/personas/eng-mobile.md +75 -0
- package/agents/personas/eng-perf.md +90 -0
- package/agents/personas/eng-qa.md +125 -0
- package/agents/personas/eng-tooling.md +49 -0
- package/agents/personas/ops-compliance.md +109 -0
- package/agents/personas/ops-cost.md +92 -0
- package/agents/personas/ops-devops.md +85 -0
- package/agents/personas/ops-incident.md +123 -0
- package/agents/personas/ops-monitor.md +89 -0
- package/agents/personas/ops-release.md +91 -0
- package/agents/personas/ops-security.md +104 -0
- package/agents/personas/ops-sre.md +85 -0
- package/agents/personas/orch-coordinator.md +140 -0
- package/agents/personas/orch-judge.md +135 -0
- package/agents/personas/orch-planner.md +114 -0
- package/agents/personas/orch-researcher.md +165 -0
- package/agents/personas/prod-architect.md +110 -0
- package/agents/personas/prod-design.md +112 -0
- package/agents/personas/prod-ethicist.md +50 -0
- package/agents/personas/prod-integration.md +120 -0
- package/agents/personas/prod-pm.md +115 -0
- package/agents/personas/prod-product-ops.md +128 -0
- package/agents/personas/prod-research.md +49 -0
- package/agents/personas/prod-safety-engineer.md +28 -0
- package/agents/personas/prod-tech-lead.md +119 -0
- package/agents/personas/ui-design.md +81 -0
- package/agents/scripts/check_skills_docs.py +120 -0
- package/agents/scripts/compile_skills.py +284 -0
- package/agents/scripts/comprehensive_checker.py +187 -0
- package/agents/scripts/dump-context.sh +37 -0
- package/agents/scripts/eval_skills.py +268 -0
- package/agents/scripts/preflight_summary.sh +80 -0
- package/agents/scripts/report_duplicates.py +125 -0
- package/agents/scripts/setup-context.ps1 +250 -0
- package/agents/scripts/setup-context.sh +398 -0
- package/agents/scripts/state_export.sh +84 -0
- package/agents/scripts/state_import.sh +99 -0
- package/agents/scripts/validate_integrity.py +98 -0
- package/agents/scripts/validate_links.py +96 -0
- package/agents/scripts/validate_methodology_graph.py +194 -0
- package/agents/scripts/validate_skills.py +81 -0
- package/agents/scripts/verify_e2e_init_flows.py +246 -0
- package/agents/scripts/verify_setup_simulation.py +104 -0
- package/agents/scripts/verify_triggers_and_mcps.py +159 -0
- package/agents/scripts/verify_use_cases.py +498 -0
- package/agents/skills/00-index.md +322 -0
- package/agents/skills/ai/a2ui-protocols.skill.md +31 -0
- package/agents/skills/ai/actor-agent-frameworks.skill.md +31 -0
- package/agents/skills/ai/agent-communication.skill.md +36 -0
- package/agents/skills/ai/agent-ui.skill.md +31 -0
- package/agents/skills/ai/autonomous-swarm-patterns.skill.md +31 -0
- package/agents/skills/ai/beyond-llms.skill.md +31 -0
- package/agents/skills/ai/context-engineering.skill.md +79 -0
- package/agents/skills/ai/llm-as-judge.skill.md +97 -0
- package/agents/skills/ai/multi-agent-systems.skill.md +31 -0
- package/agents/skills/ai/rag-evaluation.skill.md +93 -0
- package/agents/skills/ai/reasoning-patterns.skill.md +125 -0
- package/agents/skills/architecture/adaptive-architecture.skill.md +51 -0
- package/agents/skills/architecture/api-design.skill.md +92 -0
- package/agents/skills/architecture/api-standards.skill.md +31 -0
- package/agents/skills/architecture/arch-debt.skill.md +180 -0
- package/agents/skills/architecture/arch-design.skill.md +304 -0
- package/agents/skills/architecture/arch-patterns.skill.md +52 -0
- package/agents/skills/architecture/arch-review.skill.md +326 -0
- package/agents/skills/architecture/architecture-governance.skill.md +62 -0
- package/agents/skills/architecture/attribute-driven-design.skill.md +108 -0
- package/agents/skills/architecture/blockchain-dlt.skill.md +28 -0
- package/agents/skills/architecture/compatibility-design.skill.md +51 -0
- package/agents/skills/architecture/critical-systems-arch.skill.md +31 -0
- package/agents/skills/architecture/design-patterns.skill.md +59 -0
- package/agents/skills/architecture/diagramming.skill.md +380 -0
- package/agents/skills/architecture/domain-model.skill.md +294 -0
- package/agents/skills/architecture/enterprise-migration-scenario.skill.md +31 -0
- package/agents/skills/architecture/enterprise-patterns.skill.md +31 -0
- package/agents/skills/architecture/error-handling-strategy.skill.md +58 -0
- package/agents/skills/architecture/event-driven-architecture.skill.md +31 -0
- package/agents/skills/architecture/event-governance.skill.md +55 -0
- package/agents/skills/architecture/fitness-functions.skill.md +111 -0
- package/agents/skills/architecture/graphql-schema.skill.md +64 -0
- package/agents/skills/architecture/legacy-modernization.skill.md +51 -0
- package/agents/skills/architecture/microservices.skill.md +31 -0
- package/agents/skills/architecture/middleware-design.skill.md +59 -0
- package/agents/skills/architecture/monolith.skill.md +31 -0
- package/agents/skills/architecture/realtime-comm.skill.md +52 -0
- package/agents/skills/architecture/state-management.skill.md +72 -0
- package/agents/skills/architecture/system-qualities.skill.md +31 -0
- package/agents/skills/architecture/system-scalability.skill.md +31 -0
- package/agents/skills/architecture/systems-architecture.skill.md +31 -0
- package/agents/skills/architecture/visual-whiteboarding.skill.md +33 -0
- package/agents/skills/brain/README.md +70 -0
- package/agents/skills/brain/active-inference.skill.md +74 -0
- package/agents/skills/brain/brain-mode.skill.md +125 -0
- package/agents/skills/brain/cognitive-architectures.skill.md +53 -0
- package/agents/skills/brain/cognitive-testing.skill.md +62 -0
- package/agents/skills/brain/consciousness-loop.skill.md +68 -0
- package/agents/skills/brain/cost-benefit-router.skill.md +89 -0
- package/agents/skills/brain/episodic-consolidation.skill.md +43 -0
- package/agents/skills/brain/epistemology-knowledge.skill.md +54 -0
- package/agents/skills/brain/global-workspace.skill.md +77 -0
- package/agents/skills/brain/learning-adaptation.skill.md +68 -0
- package/agents/skills/brain/loki-mode.skill.md +267 -0
- package/agents/skills/brain/neuroscience-foundations.skill.md +52 -0
- package/agents/skills/brain/scripts/active_inference_loop.py +92 -0
- package/agents/skills/brain/scripts/cognition_test.py +80 -0
- package/agents/skills/brain/scripts/global_workspace.py +104 -0
- package/agents/skills/brain/self-improvement.skill.md +80 -0
- package/agents/skills/brain/sensory-motor.skill.md +61 -0
- package/agents/skills/brain/sequential-thinking.skill.md +48 -0
- package/agents/skills/brain/working-memory.skill.md +47 -0
- package/agents/skills/coding/agent-trajectory-eval.skill.md +92 -0
- package/agents/skills/coding/artisan-commands.skill.md +52 -0
- package/agents/skills/coding/browser-tdd.skill.md +131 -0
- package/agents/skills/coding/chaos-fault-injection.skill.md +116 -0
- package/agents/skills/coding/ci-autofix.skill.md +53 -0
- package/agents/skills/coding/clean-coder.skill.md +58 -0
- package/agents/skills/coding/code-review.skill.md +100 -0
- package/agents/skills/coding/debug.skill.md +100 -0
- package/agents/skills/coding/documentation.skill.md +149 -0
- package/agents/skills/coding/eval-driven-development.skill.md +107 -0
- package/agents/skills/coding/evals/code-review.eval.yaml +29 -0
- package/agents/skills/coding/excalidraw.skill.md +90 -0
- package/agents/skills/coding/file-processing.skill.md +55 -0
- package/agents/skills/coding/git-workflow.skill.md +153 -0
- package/agents/skills/coding/metamorphic-testing.skill.md +113 -0
- package/agents/skills/coding/mobile-dev.skill.md +41 -0
- package/agents/skills/coding/nodejs-expert.skill.md +23 -0
- package/agents/skills/coding/output-validation.skill.md +57 -0
- package/agents/skills/coding/pbt-strategy.skill.md +117 -0
- package/agents/skills/coding/performant-ai.skill.md +62 -0
- package/agents/skills/coding/performant-go.skill.md +61 -0
- package/agents/skills/coding/performant-laravel.skill.md +70 -0
- package/agents/skills/coding/performant-nodejs.skill.md +67 -0
- package/agents/skills/coding/performant-php.skill.md +53 -0
- package/agents/skills/coding/performant-python.skill.md +62 -0
- package/agents/skills/coding/refactor.skill.md +124 -0
- package/agents/skills/coding/secure-coding.skill.md +57 -0
- package/agents/skills/coding/sketch-to-diagram.skill.md +106 -0
- package/agents/skills/coding/spec-driven-development.skill.md +110 -0
- package/agents/skills/coding/tdd-cycle.skill.md +92 -0
- package/agents/skills/coding/testing-strategy.skill.md +74 -0
- package/agents/skills/coding/time-complexity.skill.md +112 -0
- package/agents/skills/coding/tldraw-canvas.skill.md +109 -0
- package/agents/skills/coding/tool-construction.skill.md +47 -0
- package/agents/skills/coding/ui-gen.skill.md +64 -0
- package/agents/skills/coding/vibe-coding.skill.md +63 -0
- package/agents/skills/coding/visual-design.skill.md +65 -0
- package/agents/skills/coordination/agent-interop.skill.md +72 -0
- package/agents/skills/coordination/agent-protocol.skill.md +62 -0
- package/agents/skills/coordination/agent-workflow-patterns.skill.md +123 -0
- package/agents/skills/coordination/agentic-linter.skill.md +134 -0
- package/agents/skills/coordination/agentic-patterns.skill.md +79 -0
- package/agents/skills/coordination/meta-optimize.skill.md +62 -0
- package/agents/skills/coordination/meta-prompting.skill.md +46 -0
- package/agents/skills/coordination/multi-agent-orch.skill.md +78 -0
- package/agents/skills/coordination/persona-selector.skill.md +78 -0
- package/agents/skills/coordination/self-optimize.skill.md +81 -0
- package/agents/skills/coordination/swarm-consensus.skill.md +52 -0
- package/agents/skills/core/agent-analytics.skill.md +74 -0
- package/agents/skills/core/audit-trail.skill.md +122 -0
- package/agents/skills/core/clarify.skill.md +89 -0
- package/agents/skills/core/emerging-tech.skill.md +52 -0
- package/agents/skills/core/empirical-methods.skill.md +101 -0
- package/agents/skills/core/evals/clarify.eval.yaml +29 -0
- package/agents/skills/core/evals/integrity-check.eval.yaml +23 -0
- package/agents/skills/core/evals/research.eval.yaml +23 -0
- package/agents/skills/core/final-review.skill.md +66 -0
- package/agents/skills/core/integrity-check.skill.md +149 -0
- package/agents/skills/core/knowledge-connect.skill.md +77 -0
- package/agents/skills/core/knowledge-gap.skill.md +123 -0
- package/agents/skills/core/preflight.skill.md +106 -0
- package/agents/skills/core/research.skill.md +107 -0
- package/agents/skills/core/retrospective.skill.md +59 -0
- package/agents/skills/core/sdlc-checkpoint.skill.md +151 -0
- package/agents/skills/core/self-heal.skill.md +163 -0
- package/agents/skills/core/session-resume.skill.md +125 -0
- package/agents/skills/core/skills-registry.skill.md +65 -0
- package/agents/skills/core/state-portability.skill.md +89 -0
- package/agents/skills/core/state-preserve.skill.md +76 -0
- package/agents/skills/core/system-lifecycle.skill.md +51 -0
- package/agents/skills/core/update-scan.skill.md +92 -0
- package/agents/skills/data/data-engineering.skill.md +56 -0
- package/agents/skills/data/data-governance.skill.md +49 -0
- package/agents/skills/data/db-migration.skill.md +136 -0
- package/agents/skills/data/semantic-web.skill.md +28 -0
- package/agents/skills/data/sql-optimization.skill.md +78 -0
- package/agents/skills/industry/engineering-standards.skill.md +31 -0
- package/agents/skills/industry/global-standards.skill.md +30 -0
- package/agents/skills/industry/healthcare-fhir.skill.md +28 -0
- package/agents/skills/industry/industrial-iot.skill.md +30 -0
- package/agents/skills/industry/telecom-networks.skill.md +30 -0
- package/agents/skills/ops/caching-strategy.skill.md +77 -0
- package/agents/skills/ops/capacity-planning.skill.md +67 -0
- package/agents/skills/ops/cloud-deploy.skill.md +55 -0
- package/agents/skills/ops/configuration-management.skill.md +107 -0
- package/agents/skills/ops/cost-optimization.skill.md +39 -0
- package/agents/skills/ops/decommission-sunset.skill.md +64 -0
- package/agents/skills/ops/dependency-lifecycle.skill.md +63 -0
- package/agents/skills/ops/deployment.skill.md +217 -0
- package/agents/skills/ops/dev-environments.skill.md +31 -0
- package/agents/skills/ops/dev-workflow.skill.md +28 -0
- package/agents/skills/ops/docker-dev.skill.md +52 -0
- package/agents/skills/ops/enterprise-integration.skill.md +53 -0
- package/agents/skills/ops/feature-flag-management.skill.md +59 -0
- package/agents/skills/ops/incident-response.skill.md +40 -0
- package/agents/skills/ops/infra-devops.skill.md +53 -0
- package/agents/skills/ops/k8s-dev.skill.md +51 -0
- package/agents/skills/ops/memory-optimization.skill.md +45 -0
- package/agents/skills/ops/observability-stack-setup.skill.md +62 -0
- package/agents/skills/ops/performance-audit.skill.md +178 -0
- package/agents/skills/ops/performance-optimization.skill.md +51 -0
- package/agents/skills/ops/production-health.skill.md +85 -0
- package/agents/skills/ops/production-verifier.skill.md +50 -0
- package/agents/skills/ops/queue-management.skill.md +52 -0
- package/agents/skills/ops/release-management.skill.md +39 -0
- package/agents/skills/ops/release-validation.skill.md +51 -0
- package/agents/skills/ops/reliability-sre.skill.md +51 -0
- package/agents/skills/ops/runbook-authoring.skill.md +64 -0
- package/agents/skills/ops/system-benchmark.skill.md +69 -0
- package/agents/skills/ops/tech-debt.skill.md +143 -0
- package/agents/skills/ops/troubleshooting-guide.skill.md +31 -0
- package/agents/skills/product/accessibility.skill.md +143 -0
- package/agents/skills/product/adr-writer.skill.md +110 -0
- package/agents/skills/product/business-case.skill.md +70 -0
- package/agents/skills/product/change-management.skill.md +90 -0
- package/agents/skills/product/decompose.skill.md +75 -0
- package/agents/skills/product/design-thinking.skill.md +62 -0
- package/agents/skills/product/estimation-sizing.skill.md +87 -0
- package/agents/skills/product/evals/spec-writer.eval.yaml +22 -0
- package/agents/skills/product/financial-governance.skill.md +88 -0
- package/agents/skills/product/green-software.skill.md +46 -0
- package/agents/skills/product/ideation-facilitation.skill.md +87 -0
- package/agents/skills/product/market-analysis.skill.md +56 -0
- package/agents/skills/product/opportunity-assessment.skill.md +89 -0
- package/agents/skills/product/product-analytics.skill.md +92 -0
- package/agents/skills/product/professional-practice.skill.md +105 -0
- package/agents/skills/product/req-elicitation.skill.md +292 -0
- package/agents/skills/product/req-review.skill.md +280 -0
- package/agents/skills/product/spec-analyze.skill.md +98 -0
- package/agents/skills/product/spec-writer.skill.md +114 -0
- package/agents/skills/product/stakeholder-management.skill.md +54 -0
- package/agents/skills/product/sustainability-checks.skill.md +29 -0
- package/agents/skills/product/systems-thinking.skill.md +56 -0
- package/agents/skills/product/user-research-synthesis.skill.md +85 -0
- package/agents/skills/product/user-story-mapping.skill.md +54 -0
- package/agents/skills/product/visual-specs.skill.md +112 -0
- package/agents/skills/security/access-control.skill.md +45 -0
- package/agents/skills/security/agent-sandboxing.skill.md +69 -0
- package/agents/skills/security/ai-ethics-compliance.skill.md +46 -0
- package/agents/skills/security/ai-red-teaming.skill.md +74 -0
- package/agents/skills/security/ai-safety-guardrails.skill.md +60 -0
- package/agents/skills/security/api-security.skill.md +31 -0
- package/agents/skills/security/backup-recovery.skill.md +49 -0
- package/agents/skills/security/compliance-review.skill.md +152 -0
- package/agents/skills/security/cryptography-standards.skill.md +31 -0
- package/agents/skills/security/dependency-security.skill.md +47 -0
- package/agents/skills/security/hazard-analysis.skill.md +53 -0
- package/agents/skills/security/legal-review.skill.md +41 -0
- package/agents/skills/security/log-analysis.skill.md +68 -0
- package/agents/skills/security/network-security.skill.md +64 -0
- package/agents/skills/security/privacy-audit.skill.md +137 -0
- package/agents/skills/security/privacy-data-protection.skill.md +31 -0
- package/agents/skills/security/prompt-injection-defense.skill.md +67 -0
- package/agents/skills/security/reliability-engineering.skill.md +47 -0
- package/agents/skills/security/safety-scan.skill.md +49 -0
- package/agents/skills/security/secrets-management.skill.md +65 -0
- package/agents/skills/security/secure-architecture.skill.md +31 -0
- package/agents/skills/security/security-audit.skill.md +164 -0
- package/agents/skills/security/threat-model.skill.md +120 -0
- package/agents/skills/security/traceability-audit.skill.md +48 -0
- package/agents/templates/00-index.md +162 -0
- package/agents/templates/architecture/ADAPTIVE_SYSTEM_TEMPLATE.md +35 -0
- package/agents/templates/architecture/ADD_WORKBOOK_TEMPLATE.md +81 -0
- package/agents/templates/architecture/ADR_TEMPLATE.md +136 -0
- package/agents/templates/architecture/ARCHITECTURE_DECISION_MATRIX.md +169 -0
- package/agents/templates/architecture/ARCHITECTURE_REVIEW_TEMPLATE.md +241 -0
- package/agents/templates/architecture/ARCHITECTURE_VIEWS_TEMPLATE.md +353 -0
- package/agents/templates/architecture/ARCH_DECISION_FRAMEWORK.md +32 -0
- package/agents/templates/architecture/C4_ARCHITECTURE_TEMPLATE.md +185 -0
- package/agents/templates/architecture/CAPABILITY_MAP_TEMPLATE.md +153 -0
- package/agents/templates/architecture/CONTEXT_MAP_TEMPLATE.md +196 -0
- package/agents/templates/architecture/DESIGN_PATTERN_USAGE.md +24 -0
- package/agents/templates/architecture/DOMAIN_MODEL_TEMPLATE.md +254 -0
- package/agents/templates/architecture/FITNESS_FUNCTION_TEMPLATE.md +59 -0
- package/agents/templates/architecture/INTEGRATION_SPEC_TEMPLATE.md +38 -0
- package/agents/templates/architecture/LEGACY_AUDIT_TEMPLATE.md +34 -0
- package/agents/templates/architecture/QUALITY_ATTRIBUTES_TEMPLATE.md +210 -0
- package/agents/templates/architecture/SCALABILITY_ANALYSIS_TEMPLATE.md +46 -0
- package/agents/templates/architecture/SMART_CONTRACT_TEMPLATE.md +44 -0
- package/agents/templates/architecture/SYSTEM_CONTEXT_TEMPLATE.md +197 -0
- package/agents/templates/brain/ACTIVE_INFERENCE_LOOP_TEMPLATE.md +42 -0
- package/agents/templates/brain/EPISODIC_MEMORY_LOG_TEMPLATE.md +28 -0
- package/agents/templates/brain/GLOBAL_WORKSPACE_CONFIG_TEMPLATE.md +44 -0
- package/agents/templates/brain/KNOWLEDGE_MAP_TEMPLATE.md +53 -0
- package/agents/templates/brain/OODA_LOOP_TRACE_TEMPLATE.md +44 -0
- package/agents/templates/brain/PREDICTION_ERROR_LOG_TEMPLATE.md +33 -0
- package/agents/templates/brain/PROJECT_CONTEXT_TEMPLATE.md +36 -0
- package/agents/templates/brain/SELF_IMPROVEMENT_LOG_TEMPLATE.md +39 -0
- package/agents/templates/brain/WORKING_MEMORY_TEMPLATE.md +34 -0
- package/agents/templates/coding/CLEAN_CODE_CHECKLIST.md +30 -0
- package/agents/templates/coding/DESIGN_TOKENS_TEMPLATE.json +54 -0
- package/agents/templates/coding/DEVCONTAINER_TEMPLATE.json +42 -0
- package/agents/templates/coding/DEV_SPACE_TEMPLATE.yaml +48 -0
- package/agents/templates/coding/E2E_TEST_SUITE_TEMPLATE.md +36 -0
- package/agents/templates/coding/EVAL_PLAN_TEMPLATE.md +85 -0
- package/agents/templates/coding/EVAL_RUBRIC_TEMPLATE.md +57 -0
- package/agents/templates/coding/GOLDEN_DATASET_TEMPLATE.md +73 -0
- package/agents/templates/coding/PROPERTY_TEST_CHECKLIST.md +77 -0
- package/agents/templates/coding/SKETCH_TO_DIAGRAM_TEMPLATE.md +56 -0
- package/agents/templates/coding/TEST_CASE_TEMPLATE.md +28 -0
- package/agents/templates/coding/TEST_PLAN_TEMPLATE.md +36 -0
- package/agents/templates/coding/TIME_COMPLEXITY_REPORT_TEMPLATE.md +61 -0
- package/agents/templates/coordination/AGENTS_TEMPLATE.md +540 -0
- package/agents/templates/coordination/AGENT_HANDSHAKE_TEMPLATE.json +37 -0
- package/agents/templates/coordination/AGENT_PROFILE_TEMPLATE.md +28 -0
- package/agents/templates/coordination/SWARM_ARCHITECTURE_TEMPLATE.md +53 -0
- package/agents/templates/coordination/SWARM_CONFIG_TEMPLATE.json +45 -0
- package/agents/templates/core/AUDIT_LOG_TEMPLATE.md +75 -0
- package/agents/templates/core/BUG_REPORT_TEMPLATE.md +136 -0
- package/agents/templates/core/DEPENDENCY_GRAPH_TEMPLATE.md +63 -0
- package/agents/templates/core/ESTIMATION_TEMPLATE.md +70 -0
- package/agents/templates/core/MCP_CONFIG_TEMPLATE.json +807 -0
- package/agents/templates/core/PLAN_TEMPLATE.md +162 -0
- package/agents/templates/core/PROJECT_RETROSPECTIVE_TEMPLATE.md +67 -0
- package/agents/templates/core/SDLC_TRACKER.md +217 -0
- package/agents/templates/core/SESSION_SNAPSHOT_TEMPLATE.md +168 -0
- package/agents/templates/core/SYSTEM_ANALYSIS_TEMPLATE.md +52 -0
- package/agents/templates/core/TASKS_TEMPLATE.md +104 -0
- package/agents/templates/core/TRACEABILITY_MATRIX_TEMPLATE.md +18 -0
- package/agents/templates/core/WHITEBOARD_DESIGN_TEMPLATE.md +46 -0
- package/agents/templates/data/DATABASE_SCHEMA_TEMPLATE.md +38 -0
- package/agents/templates/data/DATA_PIPELINE_TEMPLATE.md +44 -0
- package/agents/templates/data/ONTOLOGY_TEMPLATE.md +52 -0
- package/agents/templates/industry/ENGINEERING_STANDARDS_REVIEW_TEMPLATE.md +43 -0
- package/agents/templates/industry/FHIR_INTEGRATION_TEMPLATE.md +53 -0
- package/agents/templates/industry/GLOBAL_STANDARDS_AUDIT_TEMPLATE.md +45 -0
- package/agents/templates/industry/IOT_TELEMETRY_TEMPLATE.md +59 -0
- package/agents/templates/industry/TELECOM_API_TEMPLATE.md +50 -0
- package/agents/templates/ops/BENCHMARK_REPORT_TEMPLATE.md +48 -0
- package/agents/templates/ops/CAPACITY_PLAN_TEMPLATE.md +41 -0
- package/agents/templates/ops/COST_OPTIMIZATION_REPORT_TEMPLATE.md +40 -0
- package/agents/templates/ops/DECOMMISSION_PLAN_TEMPLATE.md +102 -0
- package/agents/templates/ops/DEPLOY_CONFIG_TEMPLATE.md +88 -0
- package/agents/templates/ops/INCIDENT_POSTMORTEM_TEMPLATE.md +39 -0
- package/agents/templates/ops/INFRA_PLAN_TEMPLATE.md +37 -0
- package/agents/templates/ops/RELEASE_READINESS_REPORT.md +35 -0
- package/agents/templates/ops/RUNBOOK_TEMPLATE.md +103 -0
- package/agents/templates/ops/TECH_DEBT_TEMPLATE.md +102 -0
- package/agents/templates/product/BUSINESS_CASE_TEMPLATE.md +42 -0
- package/agents/templates/product/CHANGE_MANAGEMENT_PLAN_TEMPLATE.md +68 -0
- package/agents/templates/product/EMPATHY_MAP_TEMPLATE.md +47 -0
- package/agents/templates/product/EXPERIMENT_PLAN_TEMPLATE.md +84 -0
- package/agents/templates/product/GREEN_SOFTWARE_REPORT_TEMPLATE.md +42 -0
- package/agents/templates/product/IDEATION_LOG_TEMPLATE.md +42 -0
- package/agents/templates/product/NFR_TEMPLATE.md +31 -0
- package/agents/templates/product/PRD_TEMPLATE.md +222 -0
- package/agents/templates/product/PROBLEM_STATEMENT_TEMPLATE.md +32 -0
- package/agents/templates/product/REQUIREMENTS_REVIEW_TEMPLATE.md +173 -0
- package/agents/templates/product/SPEC_TEMPLATE.md +259 -0
- package/agents/templates/product/STAKEHOLDER_REGISTER_TEMPLATE.md +127 -0
- package/agents/templates/product/USER_STORY_MAP_TEMPLATE.md +35 -0
- package/agents/templates/product/VISUAL_SPEC_PACKAGE_TEMPLATE.md +207 -0
- package/agents/templates/security/DATASHEET_TEMPLATE.md +95 -0
- package/agents/templates/security/ETHICAL_IMPACT_ASSESSMENT.md +32 -0
- package/agents/templates/security/HAZARD_LOG.md +17 -0
- package/agents/templates/security/MODEL_CARD_TEMPLATE.md +120 -0
- package/agents/templates/security/SAFETY_CASE.md +39 -0
- package/agents/templates/security/SAFETY_POLICY.md +25 -0
- package/agents/templates/security/SECURITY_CHECKLIST.md +157 -0
- package/agents/templates/security/SYSTEM_CARD_TEMPLATE.md +139 -0
- package/agents/templates/security/THREAT_MODEL_TEMPLATE.md +171 -0
- package/bin/install.js +572 -0
- package/docs/CLI_REFERENCE.md +527 -0
- package/docs/INSTALL.md +68 -0
- package/docs/MCP_CONFIGURATIONS.md +1765 -0
- package/docs/PLATFORM_CONTROLS.md +324 -0
- package/docs/POST_INSTALL.md +75 -0
- package/docs/QUICK_COMMANDS.md +131 -0
- package/docs/QUICK_GUIDE.md +914 -0
- package/docs/README_FULL.md +1451 -0
- package/docs/SCHEMA.md +164 -0
- package/docs/V1_RELEASE_CHECKLIST.md +144 -0
- package/docs/VERIFICATION_GUIDE.md +283 -0
- package/docs/adr/0001-record-architecture-decisions.md +26 -0
- package/docs/adr/0002-brain-active-inference-runtime.md +27 -0
- package/docs/adr/0003-additive-only-emitter-schema-evolution.md +33 -0
- package/docs/assets/GABBE.png +0 -0
- package/docs/gabbe.config.example.json +9 -0
- package/docs/reports/duplication-report.md +30 -0
- package/install.ps1 +90 -0
- package/install.sh +89 -0
- package/package.json +49 -0
- package/scripts/init.py +1036 -0
|
@@ -0,0 +1,294 @@
|
|
|
1
|
+
---
|
|
2
|
+
name: domain-model
|
|
3
|
+
description: Create or review a domain model — bounded contexts, entities, value objects, aggregates, domain events, relationships.
|
|
4
|
+
triggers: [domain model, bounded context, ubiquitous language, context map, domain design, domain analysis, domain events, aggregate, entities, DDD analysis]
|
|
5
|
+
tags: [architecture]
|
|
6
|
+
context_cost: medium
|
|
7
|
+
---
|
|
8
|
+
# Domain Model Skill
|
|
9
|
+
|
|
10
|
+
## Goal
|
|
11
|
+
|
|
12
|
+
Produce a clear domain model that captures the business concepts and their relationships.
|
|
13
|
+
This model is the shared language between stakeholders and developers — it drives naming,
|
|
14
|
+
component boundaries, and data design. Technology-agnostic: no database tables, no
|
|
15
|
+
class syntax, no framework artifacts.
|
|
16
|
+
|
|
17
|
+
---
|
|
18
|
+
|
|
19
|
+
## When to Use
|
|
20
|
+
|
|
21
|
+
- **Scenario 1 (New product)**: Before designing architecture. "What are the core business concepts?"
|
|
22
|
+
- **Scenario 2 (Existing system review)**: "Does the current system model correctly reflect the domain?"
|
|
23
|
+
- **Before splitting a monolith**: Identify bounded context boundaries.
|
|
24
|
+
- **When teams disagree on terminology**: Model the language explicitly.
|
|
25
|
+
|
|
26
|
+
---
|
|
27
|
+
|
|
28
|
+
## Step 1 — Discover Ubiquitous Language
|
|
29
|
+
|
|
30
|
+
```
|
|
31
|
+
Ubiquitous language = the vocabulary shared between all stakeholders and code.
|
|
32
|
+
The same term must mean the same thing everywhere.
|
|
33
|
+
|
|
34
|
+
Discovery process:
|
|
35
|
+
1. Extract all nouns from requirements documents
|
|
36
|
+
(These are candidate domain concepts: entities, value objects)
|
|
37
|
+
2. Extract all verbs and verb phrases
|
|
38
|
+
(These are candidate domain events and domain operations)
|
|
39
|
+
3. Interview or analyze stakeholder language
|
|
40
|
+
(What terms do domain experts use naturally?)
|
|
41
|
+
|
|
42
|
+
Build a Glossary:
|
|
43
|
+
| Term | Definition | Context (if term varies by subdomain) |
|
|
44
|
+
|------|-----------|---------------------------------------|
|
|
45
|
+
| Order | A confirmed request to purchase items | Order Management context |
|
|
46
|
+
| Order | The ranked sequence in search results | Search context |
|
|
47
|
+
(Same word, different meaning = CONTEXT BOUNDARY SIGNAL)
|
|
48
|
+
|
|
49
|
+
Glossary rules:
|
|
50
|
+
- One term = one meaning within a context
|
|
51
|
+
- Ambiguous terms signal bounded context boundaries
|
|
52
|
+
- Technical terms forbidden in ubiquitous language
|
|
53
|
+
- Business domain terms only
|
|
54
|
+
```
|
|
55
|
+
|
|
56
|
+
---
|
|
57
|
+
|
|
58
|
+
## Step 2 — Identify Bounded Contexts
|
|
59
|
+
|
|
60
|
+
```
|
|
61
|
+
Bounded context = a section of the domain where a model (ubiquitous language) is consistent.
|
|
62
|
+
Within a bounded context, all terms have unambiguous meaning.
|
|
63
|
+
|
|
64
|
+
Signals of a bounded context boundary:
|
|
65
|
+
- The same word means different things (see glossary step)
|
|
66
|
+
- A team owns this area independently
|
|
67
|
+
- Different data lifecycle (orders have a lifecycle independent of catalog)
|
|
68
|
+
- Different change rate (product catalog changes slower than order status)
|
|
69
|
+
- Legal/compliance boundary
|
|
70
|
+
|
|
71
|
+
Context identification method:
|
|
72
|
+
1. Group related concepts from the glossary
|
|
73
|
+
2. Find where the same word changes meaning → draw a boundary
|
|
74
|
+
3. Name each context using domain language (not technical names)
|
|
75
|
+
|
|
76
|
+
Examples:
|
|
77
|
+
Identity & Access Context: User, Credential, Session, Permission, Role
|
|
78
|
+
Order Management Context: Order, OrderItem, OrderStatus, ShippingAddress
|
|
79
|
+
Product Catalog Context: Product, Category, Attribute, Price, Stock
|
|
80
|
+
Payment Context: Payment, Invoice, Refund, PaymentMethod
|
|
81
|
+
Notification Context: Notification, NotificationChannel, Template
|
|
82
|
+
|
|
83
|
+
Each context gets its own ubiquitous language — models are isolated.
|
|
84
|
+
```
|
|
85
|
+
|
|
86
|
+
---
|
|
87
|
+
|
|
88
|
+
## Step 3 — Classify Domain Objects
|
|
89
|
+
|
|
90
|
+
```
|
|
91
|
+
Within each bounded context, classify concepts:
|
|
92
|
+
|
|
93
|
+
ENTITY: Has a unique identity that persists over time.
|
|
94
|
+
- Identity: identified by ID, not by attributes
|
|
95
|
+
- Mutable: attributes may change, identity does not
|
|
96
|
+
- Lifecycle: has a state machine (created, active, cancelled, etc.)
|
|
97
|
+
Examples: Order, Customer, Invoice, Product
|
|
98
|
+
|
|
99
|
+
VALUE OBJECT: Defined by its attributes, no persistent identity.
|
|
100
|
+
- No identity: two VOs with same attributes are equal
|
|
101
|
+
- Immutable: replace, never modify
|
|
102
|
+
- Descriptive: describes an attribute of an entity
|
|
103
|
+
Examples: Address, Money, DateRange, EmailAddress, PhoneNumber, Color
|
|
104
|
+
|
|
105
|
+
AGGREGATE: Cluster of entities and VOs treated as one unit.
|
|
106
|
+
- One AGGREGATE ROOT: the entity that guards all others
|
|
107
|
+
- Access rule: only the root can be referenced externally
|
|
108
|
+
- Transactional boundary: changes are atomic within one aggregate
|
|
109
|
+
- Keep small: an aggregate that's too large causes contention
|
|
110
|
+
Examples:
|
|
111
|
+
Order aggregate root: Order (root), OrderItems[], ShippingAddress (VO)
|
|
112
|
+
Product aggregate root: Product (root), Variants[], Price (VO)
|
|
113
|
+
|
|
114
|
+
DOMAIN SERVICE: Business logic that doesn't belong to one entity.
|
|
115
|
+
- Stateless
|
|
116
|
+
- Named after an action ("PricingCalculator", "TaxService")
|
|
117
|
+
- Only when logic operates on multiple aggregates
|
|
118
|
+
|
|
119
|
+
DOMAIN EVENT: Something significant that happened in the domain.
|
|
120
|
+
- Past tense: "OrderPlaced", "PaymentFailed", "InventoryDepleted"
|
|
121
|
+
- Immutable fact: events don't change after they happen
|
|
122
|
+
- Used for: decoupling contexts, audit trail, event sourcing
|
|
123
|
+
```
|
|
124
|
+
|
|
125
|
+
---
|
|
126
|
+
|
|
127
|
+
## Step 4 — Design Aggregates
|
|
128
|
+
|
|
129
|
+
```
|
|
130
|
+
For each aggregate:
|
|
131
|
+
|
|
132
|
+
1. Identify the root: "Who owns this cluster of objects?"
|
|
133
|
+
2. Define the boundary: "What objects MUST change together?"
|
|
134
|
+
3. Check invariants: "What business rules must always hold?"
|
|
135
|
+
4. Minimize the aggregate: "Can this be split?"
|
|
136
|
+
|
|
137
|
+
Aggregate design rules:
|
|
138
|
+
□ Reference other aggregates by ID only (no object reference across boundaries)
|
|
139
|
+
□ One transaction = one aggregate (if multiple aggregates, use domain events)
|
|
140
|
+
□ Load whole aggregate or don't load it
|
|
141
|
+
□ Keep aggregates small — large aggregates are a smell
|
|
142
|
+
|
|
143
|
+
Invariant identification:
|
|
144
|
+
An invariant is a business rule that must always be true.
|
|
145
|
+
Example: "An Order must always have at least one OrderItem"
|
|
146
|
+
"Order total must equal sum of OrderItem prices"
|
|
147
|
+
The aggregate root enforces ALL invariants within its boundary.
|
|
148
|
+
|
|
149
|
+
Document each aggregate:
|
|
150
|
+
Aggregate: [Name]
|
|
151
|
+
Root: [Entity name]
|
|
152
|
+
Members: [List of entities and VOs]
|
|
153
|
+
Invariants: [Business rules that must always hold]
|
|
154
|
+
Lifecycle States: [State machine: Created → Confirmed → Shipped → Delivered → Cancelled]
|
|
155
|
+
Domain Events: [Events emitted on state transitions]
|
|
156
|
+
```
|
|
157
|
+
|
|
158
|
+
---
|
|
159
|
+
|
|
160
|
+
## Step 5 — Context Map
|
|
161
|
+
|
|
162
|
+
```
|
|
163
|
+
Context map = the relationships between bounded contexts.
|
|
164
|
+
|
|
165
|
+
Relationship patterns (DDD):
|
|
166
|
+
Partnership:
|
|
167
|
+
Two contexts cooperate equally — changes to one require the other to change.
|
|
168
|
+
Use when: both teams can coordinate easily.
|
|
169
|
+
|
|
170
|
+
Shared Kernel:
|
|
171
|
+
Two contexts share a small model (common entities/VOs).
|
|
172
|
+
Use when: sharing is genuinely valuable and teams coordinate well.
|
|
173
|
+
Caution: creates coupling — avoid where possible.
|
|
174
|
+
|
|
175
|
+
Customer/Supplier (Upstream/Downstream):
|
|
176
|
+
Supplier (upstream) provides an API. Customer (downstream) conforms to it.
|
|
177
|
+
Upstream doesn't know about downstream.
|
|
178
|
+
Use when: one context serves another; clear ownership.
|
|
179
|
+
|
|
180
|
+
Conformist:
|
|
181
|
+
Downstream conforms completely to upstream's model (no translation).
|
|
182
|
+
Use when: upstream cannot be influenced; not worth translating.
|
|
183
|
+
|
|
184
|
+
Anti-Corruption Layer (ACL):
|
|
185
|
+
Downstream translates upstream's model into its own language.
|
|
186
|
+
Use when: upstream model is messy or conflicting with your domain.
|
|
187
|
+
Cost: translation code to maintain.
|
|
188
|
+
|
|
189
|
+
Open Host Service (OHS):
|
|
190
|
+
Context provides a well-defined API for many consumers.
|
|
191
|
+
Use when: many contexts depend on this one.
|
|
192
|
+
|
|
193
|
+
Published Language (PL):
|
|
194
|
+
Formal, shared language (schema, API spec) for communication.
|
|
195
|
+
Often combined with OHS.
|
|
196
|
+
|
|
197
|
+
Separate Ways:
|
|
198
|
+
Contexts have no integration — solve independently.
|
|
199
|
+
Use when: integration is more expensive than duplication.
|
|
200
|
+
|
|
201
|
+
Draw the context map showing:
|
|
202
|
+
- All bounded contexts as boxes
|
|
203
|
+
- All integration relationships as labeled arrows with pattern name
|
|
204
|
+
- U (upstream) / D (downstream) labels on Customer/Supplier relationships
|
|
205
|
+
|
|
206
|
+
Fill: templates/architecture/CONTEXT_MAP_TEMPLATE.md
|
|
207
|
+
```
|
|
208
|
+
|
|
209
|
+
---
|
|
210
|
+
|
|
211
|
+
## Step 6 — Domain Event Catalog
|
|
212
|
+
|
|
213
|
+
```
|
|
214
|
+
For each significant state transition in each aggregate, define a domain event:
|
|
215
|
+
|
|
216
|
+
Domain Event Format:
|
|
217
|
+
Name: [PastTenseVerb][Noun] (e.g., "OrderPlaced", "PaymentFailed")
|
|
218
|
+
Context: [which bounded context emits this]
|
|
219
|
+
Trigger: [what causes this event]
|
|
220
|
+
Payload: [what data is carried — domain language, no tech types]
|
|
221
|
+
Consumers:[which other contexts care about this event]
|
|
222
|
+
Invariant:[any business rule that must hold when this event fires]
|
|
223
|
+
|
|
224
|
+
Event catalog use:
|
|
225
|
+
- Integration events: events crossing context boundaries
|
|
226
|
+
- Internal events: events within one context (optional)
|
|
227
|
+
- Events drive the context map (who listens to whom)
|
|
228
|
+
|
|
229
|
+
Event Storming (optional):
|
|
230
|
+
If modeling a complex domain, use Event Storming notation:
|
|
231
|
+
Orange = Domain Event
|
|
232
|
+
Blue = Command (what causes the event)
|
|
233
|
+
Yellow = Actor (who issues the command)
|
|
234
|
+
Green = External System
|
|
235
|
+
Purple = Policy/Process (automated command in response to event)
|
|
236
|
+
Red = Problem/Hot Spot
|
|
237
|
+
```
|
|
238
|
+
|
|
239
|
+
---
|
|
240
|
+
|
|
241
|
+
## Output Format
|
|
242
|
+
|
|
243
|
+
Produce `docs/domain/DOMAIN_MODEL.md` from `templates/architecture/DOMAIN_MODEL_TEMPLATE.md`:
|
|
244
|
+
|
|
245
|
+
```markdown
|
|
246
|
+
# Domain Model — [System Name]
|
|
247
|
+
|
|
248
|
+
## Ubiquitous Language Glossary
|
|
249
|
+
| Term | Definition | Context |
|
|
250
|
+
|
|
251
|
+
## Bounded Contexts
|
|
252
|
+
[List with description of each]
|
|
253
|
+
|
|
254
|
+
## Context Map
|
|
255
|
+
[Mermaid diagram showing relationships]
|
|
256
|
+
[Relationship explanations]
|
|
257
|
+
|
|
258
|
+
## Aggregate Definitions
|
|
259
|
+
For each aggregate:
|
|
260
|
+
### [Aggregate Name]
|
|
261
|
+
Root | Members | Invariants | Lifecycle | Events
|
|
262
|
+
|
|
263
|
+
## Domain Event Catalog
|
|
264
|
+
| Event Name | Context | Trigger | Payload | Consumers |
|
|
265
|
+
|
|
266
|
+
## Domain Diagram (Mermaid)
|
|
267
|
+
[Class-style diagram showing entities, VOs, and relationships]
|
|
268
|
+
```
|
|
269
|
+
|
|
270
|
+
---
|
|
271
|
+
|
|
272
|
+
## Constraints
|
|
273
|
+
|
|
274
|
+
- Domain model must use business language only — no technical terms
|
|
275
|
+
- Every bounded context boundary must be justified (ambiguous term OR team/lifecycle boundary)
|
|
276
|
+
- Aggregates must be minimal — if an aggregate is complex, split it
|
|
277
|
+
- Context map relationships must be explicit — no implicit coupling between contexts
|
|
278
|
+
- Domain events must have clear, specific payload — "all order data" is not acceptable
|
|
279
|
+
- Model is validated against requirements: every use case must be traceable to domain objects
|
|
280
|
+
|
|
281
|
+
## Security & Guardrails
|
|
282
|
+
|
|
283
|
+
### Steps
|
|
284
|
+
## 1. Skill Security (Domain Modeling)
|
|
285
|
+
- **Invariant Immutability**: The agent must establish that business invariants (e.g., "An account balance cannot be negative") defined within an Aggregate Root are inviolable security boundaries. It must forbid any design that attempts to bypass the Aggregate Root to modify internal Entity state directly, as this breaks the mathematical guarantee of system consistency.
|
|
286
|
+
- **Confidentiality in Ubiquitous Language**: The agent must ensure that the Ubiquitous Language does not establish a precedent for mishandling data. For example, if the business uses the term "RawCreditCardNumber" casually, the agent must intervene in the modeling phase to ensure the domain formally processes "TokenizedPaymentMethod" instead, embedding security into the vocabulary.
|
|
287
|
+
|
|
288
|
+
### 2. System Integration Security
|
|
289
|
+
- **Anti-Corruption Layer (ACL) as a Firewall**: When integrating with a legacy or untrusted external context via an ACL in the Context Map, the agent must define the ACL not just as a data translator, but as a strict validation firewall. The ACL must drop malformed, suspicious, or excessively large payloads from the upstream system before they enter the pristine domain core.
|
|
290
|
+
- **Domain Event Sanitization**: In an Event-Driven architecture, Domain Events are broadcast widely across the Context Map. The agent must explicitly define rules stating that Domain Events must not contain sensitive PII or credentials in their payload (e.g., emitting `UserCreated(Email, HashedPassword)` is a critical violation).
|
|
291
|
+
|
|
292
|
+
### 3. LLM & Agent Guardrails
|
|
293
|
+
- **Tech-Stack Hallucination**: The agent is strictly forbidden from injecting specific database technologies, ORMs, or caching layers (e.g., "Redis", "JPA") into the Domain Model layout. Introducing technical implementation details during the domain phase biases the security architecture prematurely and violates the purity of the DDD process.
|
|
294
|
+
- **Implicit Trust Bias**: The LLM might assume that because two Bounded Contexts are owned by the same company (e.g., "HR Context" and "Billing Context"), they inherently trust each other's data representations. The agent must enforce the "Shared Kernel" or "Customer/Supplier" relationships explicitly, ensuring boundaries are respected mathematically, not merely organizationally.
|
|
@@ -0,0 +1,31 @@
|
|
|
1
|
+
---
|
|
2
|
+
name: enterprise-migration-scenario
|
|
3
|
+
description: Plan and execute complex enterprise-scale legacy migrations
|
|
4
|
+
triggers: [plan enterprise migration, migrate legacy to microservices, architect system migration]
|
|
5
|
+
tags: [architecture]
|
|
6
|
+
context_cost: high
|
|
7
|
+
---
|
|
8
|
+
# enterprise-migration-scenario
|
|
9
|
+
|
|
10
|
+
## Goal
|
|
11
|
+
Design and execute large-scale migrations from legacy systems (mainframe/on-prem) to modern, cloud-native architectures without dropping traffic or data.
|
|
12
|
+
|
|
13
|
+
## Steps
|
|
14
|
+
1. **Audit Legacy**: Parse existing legacy docs using `architecture/LEGACY_AUDIT_TEMPLATE.md`.
|
|
15
|
+
2. **Select Pattern**: Choose migration strategies like Strangler Fig, Anti-Corruption Layer (ACL), or CDC (Change Data Capture).
|
|
16
|
+
3. **Execution Plan**: Output a phased `core/PLAN.md` with incremental rollout checkpoints.
|
|
17
|
+
4. **Verification**: Verify backward-compatibility testing (parallel runs) and automated rollback plans are explicitly documented.
|
|
18
|
+
|
|
19
|
+
## Security & Guardrails
|
|
20
|
+
|
|
21
|
+
### 1. Skill Security
|
|
22
|
+
- **Irreversible Actions**: The agent must NEVER output commands that drop or truncate legacy databases. Migrations must strictly be additive/shadow writes until final approval.
|
|
23
|
+
- **Migration Script Generation**: Enforce strict input sanitization on any LLM-generated SQL or scripting intended for migration execution.
|
|
24
|
+
|
|
25
|
+
### 2. System Integration Security
|
|
26
|
+
- **Data In-Flight**: Assure all synchronization between legacy and new systems runs over encrypted tunnels, even within perceived "safe" corporate boundaries.
|
|
27
|
+
- **Anti-Corruption Layer Hardening**: Implement strict type-checking at the ACL boundary to prevent legacy structural malformations from poisoning the new domains.
|
|
28
|
+
|
|
29
|
+
### 3. LLM & Agent Guardrails
|
|
30
|
+
- **Big-Bang Fallacy**: The LLM might hallucinate that an entire enterprise system can be migrated synchronously over a weekend. Agents must reject Big-Bang migrations and mandate phased, Strangler Fig rollouts.
|
|
31
|
+
- **Knowledge Overreach**: Prevent the LLM from making assumptions about proprietary legacy behaviors (like custom Mainframe DB architectures) without explicit user documentation.
|
|
@@ -0,0 +1,31 @@
|
|
|
1
|
+
---
|
|
2
|
+
name: enterprise-patterns
|
|
3
|
+
description: Implement robust Enterprise Architecture Patterns
|
|
4
|
+
triggers: [implement enterprise pattern, add circuit breaker, design saga pattern]
|
|
5
|
+
tags: [architecture]
|
|
6
|
+
context_cost: medium
|
|
7
|
+
---
|
|
8
|
+
# enterprise-patterns
|
|
9
|
+
|
|
10
|
+
## Goal
|
|
11
|
+
Implement widespread architectural patterns (BFF, API Gateway, Saga Pattern, Circuit Breaker) for scalable and resilient enterprise operations.
|
|
12
|
+
|
|
13
|
+
## Steps
|
|
14
|
+
1. **Identify Constraint**: Select the pattern that solves the specific distributed computing constraint (e.g., Saga for distributed transactions).
|
|
15
|
+
2. **Component Implementation**: Generate the boilerplate (e.g., Spring/Go libraries) for the specific pattern.
|
|
16
|
+
3. **Resilience Engineering**: Define retry counts, timeouts, and fallback protocols.
|
|
17
|
+
4. **Verification**: Enforce Chaos testing or failure simulation tests before marking the task complete.
|
|
18
|
+
|
|
19
|
+
## Security & Guardrails
|
|
20
|
+
|
|
21
|
+
### 1. Skill Security
|
|
22
|
+
- **Pattern Bloat**: Prevent the agent from overly engineering simple CRUD apps with unnecessary Sagaservers or Kafka queues.
|
|
23
|
+
- **Library Vet**: Force the agent to rely only on enterprise-approved libraries (e.g., Resilience4j) rather than attempting to handwrite complex distributed locks.
|
|
24
|
+
|
|
25
|
+
### 2. System Integration Security
|
|
26
|
+
- **Circuit Breaker Fallbacks**: Ensure that when a circuit breaker trips, the fallback mechanism (cached data, default error) does not accidentally leak sensitive placeholder data to the client.
|
|
27
|
+
- **Distributed Logging**: Ensure Saga orchestrators redact PII when logging complex multi-stage rollbacks or compensations.
|
|
28
|
+
|
|
29
|
+
### 3. LLM & Agent Guardrails
|
|
30
|
+
- **Saga Complexity Hallucination**: The LLM must explicitly list all compensatory transactions for every step of a Saga; it cannot gloss over failure states.
|
|
31
|
+
- **Anti-Pattern Prevention**: Agents must explicitly block the use of distributed 2-Phase Commits in favor of Saga patterns across loosely coupled services.
|
|
@@ -0,0 +1,58 @@
|
|
|
1
|
+
---
|
|
2
|
+
name: error-handling-strategy
|
|
3
|
+
description: Centralized error handling (RFC 7807), circuit breakers, and user-facing fallbacks.
|
|
4
|
+
triggers: [error handling strategy]
|
|
5
|
+
tags: [architecture]
|
|
6
|
+
role: prod-architect, eng-backend
|
|
7
|
+
context_cost: low
|
|
8
|
+
---
|
|
9
|
+
# error-handling-strategy Skill
|
|
10
|
+
|
|
11
|
+
## Goal
|
|
12
|
+
Errors are inevitable. Handling them must be consistent, predictable, and safe.
|
|
13
|
+
|
|
14
|
+
## Steps
|
|
15
|
+
## 1. Unified API Error Format (RFC 7807)
|
|
16
|
+
Never return raw stack traces or ad-hoc JSON strings. Use `Problem Details`:
|
|
17
|
+
|
|
18
|
+
```json
|
|
19
|
+
{
|
|
20
|
+
"type": "https://example.com/probs/out-of-credit",
|
|
21
|
+
"title": "You do not have enough credit.",
|
|
22
|
+
"status": 403,
|
|
23
|
+
"detail": "Current balance is 30, but cost is 50.",
|
|
24
|
+
"instance": "/account/12345/msgs/abc",
|
|
25
|
+
"traceId": "00-5c14d5-..."
|
|
26
|
+
}
|
|
27
|
+
```
|
|
28
|
+
|
|
29
|
+
## 2. Centralized Exception Handling
|
|
30
|
+
- **Do Not**: Catch exceptions in every controller method.
|
|
31
|
+
- **Do**: Use a Global Exception Handler (Middleware / Filter).
|
|
32
|
+
- Map `DomainException` → 422 Unprocessable Entity.
|
|
33
|
+
- Map `NotFoundException` → 404 Not Found.
|
|
34
|
+
- Map `SecurityException` → 401/403.
|
|
35
|
+
- Map `CatchAll` → 500 Internal Server Error (and log trace ID).
|
|
36
|
+
|
|
37
|
+
## 3. Resilience Patterns
|
|
38
|
+
- **Circuit Breaker**: Detect cascading failures. If 50% of requests to Service B fail, open the circuit (fail fast) for 30s.
|
|
39
|
+
- **Bulkhead**: Thread pool isolation. Service A crashing shouldn't take down Service B.
|
|
40
|
+
- **Retry**: Only retry *transient* errors (Network, 503). Never retry 4xx errors. Backoff: Exponential + Jitter.
|
|
41
|
+
|
|
42
|
+
## 4. User-Facing Fallbacks
|
|
43
|
+
- **Graceful Degradation**: If the "Recommendations" service is down, don't crash the homepage. Show "Popular Items" (static) instead.
|
|
44
|
+
- **Friendly Messages**: "Something went wrong" is bad. "We couldn't load your cart, but your items are safe. Try refreshing." is better.
|
|
45
|
+
|
|
46
|
+
## Security & Guardrails
|
|
47
|
+
|
|
48
|
+
### 1. Skill Security (Error Handling)
|
|
49
|
+
- **Stack Trace Suppression Guarantee**: The agent must irrevocably mandate that under no circumstances—not even during `beta` or early deployment phases—will raw stack traces, SQL syntax errors, or server environment variables be returned in HTTP 500 responses. This prevents critical Information Disclosure vulnerabilities.
|
|
50
|
+
- **Trace ID Obfuscation**: While `traceId` (RFC 7807) is critical for debugging, the agent must ensure the generated ID does not inadvertently leak internal system state (like sequential database IDs, IP addresses, or readable timestamps). It must mandate the use of opaque UUIDv4 or cryptographic hashes for public-facing tracing identifiers.
|
|
51
|
+
|
|
52
|
+
### 2. System Integration Security
|
|
53
|
+
- **Fail-Closed by Default**: When an unexpected `DomainException` or `SecurityException` occurs, the Global Exception Handler must inherently default to a restrictive posture (401/403 or a generic 500). It must never "fail-open" by ignoring the error and proceeding with the execution flow or granting unverified access.
|
|
54
|
+
- **Circuit Breaker Poisoning Defense**: If a Circuit Breaker is triggered by a sudden spike in errors (often indicative of a DDoS attack or an intentional exploit attempt against a specific service), the system must degrade gracefully (Step 4) without completely locking out valid, authenticated traffic to unaffected areas.
|
|
55
|
+
|
|
56
|
+
### 3. LLM & Agent Guardrails
|
|
57
|
+
- **Excessive Error Verbosity Hallucination**: An overly helpful LLM might suggest returning "user-friendly" error messages that inadvertently leak business logic (e.g., "User account exists but is locked due to 5 failed password attempts"). The agent must rigidly enforce the OWASP standard for generic authentication errors (e.g., "Invalid username or password").
|
|
58
|
+
- **Retry Amplification Attack Mitigation**: The agent must not suggest naive Retry logic without strict bounds. If an LLM proposes "retry failed requests up to 10 times," the agent must intervene, enforcing Exponential Backoff and Jitter. Unbounded retries turn a transient internal network issue into a self-inflicted, devastating Denial of Service.
|
|
@@ -0,0 +1,31 @@
|
|
|
1
|
+
---
|
|
2
|
+
name: event-driven-architecture
|
|
3
|
+
description: Design and implement Event-Driven and Async Architectures
|
|
4
|
+
triggers: [design event-driven system, implement eda, setup message broker topology]
|
|
5
|
+
tags: [architecture]
|
|
6
|
+
context_cost: medium
|
|
7
|
+
---
|
|
8
|
+
# event-driven-architecture
|
|
9
|
+
|
|
10
|
+
## Goal
|
|
11
|
+
Architect distributed, decoupled systems using Event-Driven Architecture (EDA) patterns like Pub/Sub, Event Sourcing, and CQRS.
|
|
12
|
+
|
|
13
|
+
## Steps
|
|
14
|
+
1. **Event Modeling**: Identify domain events and map out producer/consumer relationships.
|
|
15
|
+
2. **Broker Design**: Select the appropriate messaging tech (Kafka, RabbitMQ, SQS) based on throughput and ordering constraints.
|
|
16
|
+
3. **Schema Registry**: Define strongly typed schemas (Avro, Protobuf, JSON Schema) for all events.
|
|
17
|
+
4. **Verification**: Validate that idempotent consumers are implemented to handle at-least-once delivery semantics.
|
|
18
|
+
|
|
19
|
+
## Security & Guardrails
|
|
20
|
+
|
|
21
|
+
### 1. Skill Security
|
|
22
|
+
- **Schema Poisoning**: Prevent the skill from executing dynamic code attached to event payloads when simulating event flows.
|
|
23
|
+
- **Topology Overload**: Limit the visual diagram generation (e.g., Mermaid) to prevent generating massively complex graphs that crash the markdown renderer.
|
|
24
|
+
|
|
25
|
+
### 2. System Integration Security
|
|
26
|
+
- **Event Tampering**: All events traversing untrusted boundaries must be digitally signed to guarantee origin and integrity.
|
|
27
|
+
- **Dead Letter Security**: Ensure sensitive data (PII/PCI) in failed events is masked or encrypted before being dumped into a Dead Letter Queue (DLQ).
|
|
28
|
+
|
|
29
|
+
### 3. LLM & Agent Guardrails
|
|
30
|
+
- **Ordering Hallucination**: The LLM must not assume guaranteed global ordering of events unless explicitly supported by the selected broker (e.g., Kafka partitions).
|
|
31
|
+
- **Consistency Fallacies**: Explicitly warn the user about eventual consistency side-effects; do not falsely claim that distributed EDA systems provide ACID guarantees out-of-the-box.
|
|
@@ -0,0 +1,55 @@
|
|
|
1
|
+
---
|
|
2
|
+
name: event-governance
|
|
3
|
+
description: Schema Registry enforcement (Avro/JSON), CloudEvents standard, and Event Evolution rules.
|
|
4
|
+
triggers: [event governance]
|
|
5
|
+
tags: [architecture]
|
|
6
|
+
role: prod-architect, eng-data
|
|
7
|
+
context_cost: low
|
|
8
|
+
---
|
|
9
|
+
# event-governance Skill
|
|
10
|
+
|
|
11
|
+
## Goal
|
|
12
|
+
Events are Data Contracts. They must be governed as strictly as APIs.
|
|
13
|
+
|
|
14
|
+
## Steps
|
|
15
|
+
## 1. CloudEvents Standard
|
|
16
|
+
Use the standard envelope structure:
|
|
17
|
+
```json
|
|
18
|
+
{
|
|
19
|
+
"specversion": "1.0",
|
|
20
|
+
"type": "com.example.order.created",
|
|
21
|
+
"source": "/service/order",
|
|
22
|
+
"id": "A234-1234-1234",
|
|
23
|
+
"time": "2020-01-01T12:00:00Z",
|
|
24
|
+
"datacontenttype": "application/json",
|
|
25
|
+
"data": { ... }
|
|
26
|
+
}
|
|
27
|
+
```
|
|
28
|
+
|
|
29
|
+
## 2. Schema Registry
|
|
30
|
+
- **Rule**: All event payloads must be validated against a Schema Registry (e.g., Confluent, Glue) *before* publishing.
|
|
31
|
+
- **Formats**: Avro (preferred for compact/evolution), Protobuf, or JSON Schema.
|
|
32
|
+
|
|
33
|
+
## 3. Schema Evolution (Compatibility)
|
|
34
|
+
- **Backward Compatibility**: New consumer can read old data. (Add optional fields).
|
|
35
|
+
- **Forward Compatibility**: Old consumer can read new data. (Ignore unknown fields).
|
|
36
|
+
- **Full Compatibility**: Both.
|
|
37
|
+
- **Breaking Changes**: renaming fields, changing types. **Forbidden** without a new topic version (`orders.v2`).
|
|
38
|
+
|
|
39
|
+
## 4. Documentation
|
|
40
|
+
- Use **AsyncAPI** to document event topography.
|
|
41
|
+
- Treat Events as Public APIs.
|
|
42
|
+
|
|
43
|
+
## Security & Guardrails
|
|
44
|
+
|
|
45
|
+
### 1. Skill Security (Event Governance)
|
|
46
|
+
- **Schema Poisoning Prevention**: The Schema Registry itself is a critical security dependency. The agent must enforce that CI/CD pipelines require cryptographic signatures or strict RBAC approval before a new Schema Version (e.g., Avro `.avsc`) can be published. If an attacker can silently alter the schema to make a high-security field optional, downstream validation might fail open.
|
|
47
|
+
- **Dead-Letter Queue (DLQ) Containment**: The agent must stipulate that DLQs, which catch malformed or failing events, are subject to the same strict data residency and access controls as the primary topic. DLQs often accumulate edge-case data that might contain unexpected PII or raw secrets that crashed the parser.
|
|
48
|
+
|
|
49
|
+
### 2. System Integration Security
|
|
50
|
+
- **PII Field Pinning**: When defining backward/forward compatibility rules (Step 3), the agent must explicitly forbid the "silent deprecation" of fields tagged for security or compliance (e.g., `consent_withdrawn_timestamp`). Dropping these fields via schema evolution can cause downstream systems to violate GDPR/CCPA.
|
|
51
|
+
- **Event Forwarding Trust Boundaries**: If CloudEvents are forwarded across bounded contexts or network boundaries, the agent must mandate `mTLS` at the transport layer and strongly recommend payload-level encryption (e.g., AES-GCM) for sensitive fields, preventing cross-tenant data leakage in shared event brokers like Kafka.
|
|
52
|
+
|
|
53
|
+
### 3. LLM & Agent Guardrails
|
|
54
|
+
- **Compatibility-Over-Security Bias**: The LLM might suggest making all schema fields optional to maximize Forward/Backward compatibility. The agent must veto this for security-critical fields (e.g., `tenantId`, `authorizationRole`). Fields required for downstream authorization MUST remain strictly enforced and non-nullable.
|
|
55
|
+
- **Hallucinated AsyncAPI Authorization**: The LLM might generate an AsyncAPI specification that perfectly describes the message structure but entirely omits the security scheme (e.g., SASL/SCRAM or mutual TLS requirements). The agent must mathematically ensure that every produced AsyncAPI document contains an explicit `securitySchemes` definition.
|
|
@@ -0,0 +1,111 @@
|
|
|
1
|
+
---
|
|
2
|
+
name: fitness-functions
|
|
3
|
+
description: Define objective, measurable tests for architectural characteristics and wire them into CI as automated, continuous architecture governance.
|
|
4
|
+
triggers: [write architecture fitness functions, measure architectural characteristics, enforce layering rules in ci, set a latency budget test, atomic vs holistic fitness function, catch architectural drift automatically]
|
|
5
|
+
tags: [architecture, governance, evolutionary-architecture, ci, testing]
|
|
6
|
+
core: false
|
|
7
|
+
context_cost: medium
|
|
8
|
+
---
|
|
9
|
+
# Fitness Functions
|
|
10
|
+
|
|
11
|
+
## Goal
|
|
12
|
+
Make architecture an executable, enforced thing rather than a diagram that rots. A *fitness
|
|
13
|
+
function* is an objective, measurable test of an architectural characteristic — the
|
|
14
|
+
evolutionary-architecture mechanism for governing the "-ilities" the same way unit tests
|
|
15
|
+
govern logic. Where a unit test asserts a feature works, a fitness function asserts a
|
|
16
|
+
*structural property* holds: cyclomatic complexity stays under a limit, the domain layer never
|
|
17
|
+
imports infrastructure, p99 latency stays inside its budget, afferent/efferent coupling stays
|
|
18
|
+
bounded. Wired into CI, fitness functions turn architectural intent into automated governance
|
|
19
|
+
that fails the build the moment the system drifts away from its target characteristics.
|
|
20
|
+
|
|
21
|
+
## Steps
|
|
22
|
+
1. **Name the architectural characteristic to protect.** Pick one measurable "-ility" the
|
|
23
|
+
architecture must preserve (maintainability, performance, modularity, security boundary,
|
|
24
|
+
scalability). Vague goals cannot be governed — "should be maintainable" is not a fitness
|
|
25
|
+
function; "no module may have efferent coupling above 20" is.
|
|
26
|
+
2. **Define the objective, measurable test.** Translate the characteristic into a pass/fail
|
|
27
|
+
check with a concrete threshold and a clear unit of measure. Examples:
|
|
28
|
+
- *Maintainability*: cyclomatic complexity per method below a limit; max file/function length.
|
|
29
|
+
- *Modularity / layering*: dependency rules ("`domain` must not depend on `infrastructure`"),
|
|
30
|
+
no cyclic dependencies between packages.
|
|
31
|
+
- *Performance*: p99 latency under a budget; payload size under a cap.
|
|
32
|
+
- *Coupling*: afferent/efferent coupling or instability metric within bounds.
|
|
33
|
+
Each must be *objective* — two people running it get the same verdict.
|
|
34
|
+
3. **Classify each function on two axes.** This drives where and how it runs.
|
|
35
|
+
- **Atomic vs holistic**: atomic checks one characteristic in isolation (a single layering
|
|
36
|
+
rule). Holistic checks several interacting characteristics together (security *under*
|
|
37
|
+
load), and exists because some properties only emerge from combination.
|
|
38
|
+
- **Triggered vs continuous**: triggered runs on an event (per commit, per PR, on a schedule);
|
|
39
|
+
continuous runs constantly in production as a monitor (e.g. live latency/SLO alarms).
|
|
40
|
+
4. **Pick the right tool per function.** Use static-analysis frameworks for structure and
|
|
41
|
+
dependency rules (ArchUnit for Java/Kotlin, NetArchTest for .NET, `dependency-cruiser` or
|
|
42
|
+
bespoke ESLint rules for TS, Deptrac/PHPArkitect for PHP), complexity tools (lizard,
|
|
43
|
+
radon, ESLint complexity rules) for code metrics, and load/observability tooling (k6,
|
|
44
|
+
Locust, SLO monitors) for runtime budgets. Defer custom lint-rule authoring to
|
|
45
|
+
`agentic-linter.skill`.
|
|
46
|
+
5. **Wire triggered functions into CI as governance gates.** Run atomic, fast static checks on
|
|
47
|
+
every PR; run heavier holistic and load-based checks on a schedule or pre-merge. Fail the
|
|
48
|
+
build on violation — an architectural breach is a broken build, not a warning. Order
|
|
49
|
+
cheapest-first to keep PR feedback fast. This is the automated half of
|
|
50
|
+
`architecture-governance.skill`.
|
|
51
|
+
6. **Define waivers and continuous monitors.** For continuous functions, wire production
|
|
52
|
+
alarms/SLOs. For unavoidable violations, require an explicit, ticketed, time-boxed waiver
|
|
53
|
+
(an ADR plus a suppression comment referencing it) — never an unaudited silent bypass.
|
|
54
|
+
7. **Maintain the suite as a living asset.** Review thresholds when the system legitimately
|
|
55
|
+
evolves, retire functions for retired characteristics, and add new ones for new drivers.
|
|
56
|
+
Stale fitness functions either block valid change or rot into ignored noise.
|
|
57
|
+
|
|
58
|
+
## Constraints
|
|
59
|
+
- A fitness function tests the **characteristic it measures and nothing else**. A green suite
|
|
60
|
+
means "the checked properties hold," not "the architecture is good." Be honest about coverage:
|
|
61
|
+
unmeasured characteristics are ungoverned.
|
|
62
|
+
- Functions MUST be objective and deterministic where possible. A check whose verdict depends
|
|
63
|
+
on who ran it or on flaky timing erodes trust and gets disabled.
|
|
64
|
+
- Performance/latency budgets sampled in CI are estimates under test conditions, not a
|
|
65
|
+
production guarantee; pair them with continuous production monitors and say so.
|
|
66
|
+
- Governance checks MUST fail-closed in CI. If the analysis tool crashes or cannot load its
|
|
67
|
+
ruleset, the pipeline blocks — never treat "tool errored" as "passed."
|
|
68
|
+
- Thresholds are engineering judgments, not laws of nature. Record the rationale for each limit
|
|
69
|
+
so future maintainers can adjust it deliberately rather than cargo-cult it.
|
|
70
|
+
|
|
71
|
+
## Output Format
|
|
72
|
+
Produce a **set of fitness functions** following the structure of `FITNESS_FUNCTION_TEMPLATE.md`.
|
|
73
|
+
For each function record:
|
|
74
|
+
- The architectural characteristic it protects and the concrete metric + threshold (with unit).
|
|
75
|
+
- Its classification: atomic/holistic and triggered/continuous.
|
|
76
|
+
- The tool/implementation and where it runs (PR gate, scheduled, production monitor).
|
|
77
|
+
- The pass/fail criterion and the fail-closed behavior on tool error.
|
|
78
|
+
- The waiver policy (ticket + ADR reference) and the rationale for the chosen threshold.
|
|
79
|
+
Close with a coverage note listing which characteristics are governed and which remain
|
|
80
|
+
unmeasured. Hand the CI-gate wiring to `architecture-governance.skill` and custom rule authoring
|
|
81
|
+
to `agentic-linter.skill`.
|
|
82
|
+
|
|
83
|
+
## Security & Guardrails
|
|
84
|
+
|
|
85
|
+
### 1. Skill Security
|
|
86
|
+
- **Risk**: Ruleset or threshold files are edited to weaken a check (e.g. raising a complexity
|
|
87
|
+
cap) so a non-compliant PR merges. Mitigation: protect fitness-function config under CODEOWNERS
|
|
88
|
+
requiring architecture/security approval, and review threshold diffs as carefully as code; the
|
|
89
|
+
agent MUST refuse to quietly loosen a rule to make a failing build pass.
|
|
90
|
+
- **Risk**: A passing suite is reported as "architecture is sound," overstating its guarantee.
|
|
91
|
+
Mitigation: every report MUST scope the claim to the measured characteristics and list what is
|
|
92
|
+
unmeasured; the agent MUST NOT escalate "fitness functions pass" into "architecture is correct."
|
|
93
|
+
|
|
94
|
+
### 2. System Integration Security
|
|
95
|
+
- **Risk**: A fitness function fails open — a crashed analyzer or missing ruleset is silently
|
|
96
|
+
treated as success, giving false assurance. Mitigation: mandate fail-closed CI behavior; a tool
|
|
97
|
+
that cannot complete its check MUST block the pipeline, not pass it.
|
|
98
|
+
- **Risk**: Security boundary rules (e.g. "presentation layer may not open a DB connection";
|
|
99
|
+
"all external callers go through a circuit breaker") are absent, so violations ship undetected.
|
|
100
|
+
Mitigation: require explicit fitness functions for each security/trust boundary, and treat their
|
|
101
|
+
violations as build-breaking, not advisory.
|
|
102
|
+
|
|
103
|
+
### 3. LLM & Agent Guardrails
|
|
104
|
+
- **Risk**: The agent generates invalid or non-existent rule syntax (e.g. a fabricated ArchUnit
|
|
105
|
+
predicate) that silently no-ops, creating a false sense of governance. Mitigation: emit only
|
|
106
|
+
valid, tested syntax for the target tool; the agent MUST verify a generated rule actually
|
|
107
|
+
executes and can fail, never present an unrun rule as enforcing.
|
|
108
|
+
- **Risk**: Under pressure to unblock a developer, the agent recommends suppressing or deleting a
|
|
109
|
+
failing fitness function instead of fixing the underlying drift. Mitigation: the agent MUST
|
|
110
|
+
default to refactoring the violation; any bypass requires a ticketed, time-boxed, ADR-backed
|
|
111
|
+
waiver and MUST be surfaced for human review, never applied silently.
|