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 +1,262 @@
|
|
|
1
|
+
# RARV Cycle — Reason, Act, Reflect, Verify
|
|
2
|
+
|
|
3
|
+
> The per-agent cognitive loop. Every task follows this cycle.
|
|
4
|
+
> Used by all eng-* personas in Loki Mode and by single agents in standard mode.
|
|
5
|
+
|
|
6
|
+
---
|
|
7
|
+
|
|
8
|
+
## The Full Loop
|
|
9
|
+
|
|
10
|
+
```
|
|
11
|
+
Task assigned by orch-planner
|
|
12
|
+
│
|
|
13
|
+
▼
|
|
14
|
+
┌─────────────────────────────────────────────────────┐
|
|
15
|
+
│ REASON │
|
|
16
|
+
│ 1. Load task context │
|
|
17
|
+
│ 2. Read CONTINUITY.md (past failures) │
|
|
18
|
+
│ 3. Detect knowledge gaps │
|
|
19
|
+
│ 4. Formulate explicit plan │
|
|
20
|
+
└─────────────────────────────────────────────────────┘
|
|
21
|
+
│
|
|
22
|
+
├─── Knowledge gap? ──► research.skill (via orch-researcher)
|
|
23
|
+
│ │
|
|
24
|
+
│ Verified source found ──► Store in semantic memory
|
|
25
|
+
│ Not found ──► Human escalation
|
|
26
|
+
│
|
|
27
|
+
▼
|
|
28
|
+
┌─────────────────────────────────────────────────────┐
|
|
29
|
+
│ ACT │
|
|
30
|
+
│ 1. Write failing test (TDD Red) │
|
|
31
|
+
│ 2. Implement minimal code (TDD Green) │
|
|
32
|
+
│ 3. Use MCP tools as needed │
|
|
33
|
+
│ 4. Update task: status → IN_PROGRESS │
|
|
34
|
+
└─────────────────────────────────────────────────────┘
|
|
35
|
+
│
|
|
36
|
+
▼
|
|
37
|
+
┌─────────────────────────────────────────────────────┐
|
|
38
|
+
│ REFLECT │
|
|
39
|
+
│ 1. Library-First check: is business logic in domain?│
|
|
40
|
+
│ 2. Circular import check: did I introduce any? │
|
|
41
|
+
│ 3. API version check: via Context-7, not training? │
|
|
42
|
+
│ 4. Edge case check: are null/empty/error paths │
|
|
43
|
+
│ covered by tests? │
|
|
44
|
+
│ 5. Security check: did I validate inputs? Any PII │
|
|
45
|
+
│ in logs? Any hardcoded secret? │
|
|
46
|
+
│ 6. Governance check: Data classified? Events │
|
|
47
|
+
│ typed? DLQs configured? │
|
|
48
|
+
└─────────────────────────────────────────────────────┘
|
|
49
|
+
│
|
|
50
|
+
▼
|
|
51
|
+
┌─────────────────────────────────────────────────────┐
|
|
52
|
+
│ VERIFY │
|
|
53
|
+
│ Run: [test command] ──► GREEN? │
|
|
54
|
+
│ Run: [typecheck] ──────► zero errors? │
|
|
55
|
+
│ Run: [lint] ───────────► zero errors? │
|
|
56
|
+
│ Run: agentic-linter ───► no violations? │
|
|
57
|
+
└─────────────────────────────────────────────────────┘
|
|
58
|
+
│
|
|
59
|
+
├─── PASS ──► audit-trail.skill → task: DONE ──► DONE
|
|
60
|
+
│
|
|
61
|
+
└─── FAIL ──► self-heal.skill
|
|
62
|
+
│
|
|
63
|
+
├─ Attempt 1-4 ──► diagnose → fix → verify ──► loop back
|
|
64
|
+
│
|
|
65
|
+
└─ Attempt 5 FAIL ──► ESCALATE TO HUMAN
|
|
66
|
+
│
|
|
67
|
+
├─ Write escalation report
|
|
68
|
+
├─ AUDIT_LOG.md: HUMAN_ESCALATION
|
|
69
|
+
├─ project/TASKS.md: status → BLOCKED
|
|
70
|
+
└─ WAIT for human decision
|
|
71
|
+
│
|
|
72
|
+
Human responds
|
|
73
|
+
│
|
|
74
|
+
Apply decision ──► loop back to ACT
|
|
75
|
+
```
|
|
76
|
+
|
|
77
|
+
---
|
|
78
|
+
|
|
79
|
+
## REASON Phase — Detailed
|
|
80
|
+
|
|
81
|
+
### 1. Load Task Context
|
|
82
|
+
```
|
|
83
|
+
Read from orch-planner's task assignment:
|
|
84
|
+
- Task description and acceptance criteria
|
|
85
|
+
- Which layer/module this task belongs to
|
|
86
|
+
- Dependencies: what must be done before this task
|
|
87
|
+
|
|
88
|
+
Read from AGENTS.md:
|
|
89
|
+
- Architecture rules for this project
|
|
90
|
+
- Operational commands (test, lint, typecheck)
|
|
91
|
+
- Forbidden patterns
|
|
92
|
+
|
|
93
|
+
Read from CONSTITUTION.md:
|
|
94
|
+
- Immutable project law relevant to this task
|
|
95
|
+
```
|
|
96
|
+
|
|
97
|
+
### 2. Read CONTINUITY.md (MANDATORY — never skip)
|
|
98
|
+
```
|
|
99
|
+
Scan for entries related to:
|
|
100
|
+
- This module or layer
|
|
101
|
+
- Similar operations (if implementing auth, check auth-related entries)
|
|
102
|
+
- Libraries being used in this task
|
|
103
|
+
|
|
104
|
+
If relevant entry found:
|
|
105
|
+
"Past failure: [X]. Avoid [approach]. Use [resolution] instead."
|
|
106
|
+
Apply the recorded resolution without rediscovery.
|
|
107
|
+
```
|
|
108
|
+
|
|
109
|
+
### 3. Detect Knowledge Gaps
|
|
110
|
+
```
|
|
111
|
+
Ask yourself: "Can I cite an official Tier 1/2 source for each API I'm about to call?"
|
|
112
|
+
|
|
113
|
+
Research Gate — mandatory before:
|
|
114
|
+
- Using a library not in package.json / composer.json
|
|
115
|
+
- Calling an API method not recently verified
|
|
116
|
+
- Implementing any security or cryptographic operation
|
|
117
|
+
- Interpreting any regulatory requirement
|
|
118
|
+
|
|
119
|
+
If gap found: invoke knowledge-gap.skill → orch-researcher
|
|
120
|
+
If orch-researcher finds answer: proceed with verified knowledge
|
|
121
|
+
If orch-researcher cannot find answer: escalate to human
|
|
122
|
+
```
|
|
123
|
+
|
|
124
|
+
### 4. Formulate Explicit Plan
|
|
125
|
+
```
|
|
126
|
+
Write out (even briefly) before touching any file:
|
|
127
|
+
- "I will create: [file list]"
|
|
128
|
+
- "I will modify: [file list + what changes]"
|
|
129
|
+
- "I will write tests for: [behaviors]"
|
|
130
|
+
- "This change affects layers: [list]"
|
|
131
|
+
- "Potential risks: [list]"
|
|
132
|
+
|
|
133
|
+
For complex tasks: write mini-plan to project/TASKS.md task notes
|
|
134
|
+
```
|
|
135
|
+
|
|
136
|
+
---
|
|
137
|
+
|
|
138
|
+
## ACT Phase — Detailed
|
|
139
|
+
|
|
140
|
+
### TDD Integration
|
|
141
|
+
```
|
|
142
|
+
Step 1: Write failing test
|
|
143
|
+
- Create test file if it doesn't exist
|
|
144
|
+
- Write test that captures the EXACT acceptance criteria
|
|
145
|
+
- Run test → MUST FAIL (false-positive check!)
|
|
146
|
+
- If it passes immediately: test is broken, fix the test
|
|
147
|
+
|
|
148
|
+
Step 2: Write minimal implementation
|
|
149
|
+
- Implement ONLY what's needed to pass the test
|
|
150
|
+
- No gold-plating, no premature optimization
|
|
151
|
+
- No features not covered by a failing test
|
|
152
|
+
|
|
153
|
+
Step 3: Run tests → must be GREEN
|
|
154
|
+
```
|
|
155
|
+
|
|
156
|
+
### MCP Tool Usage
|
|
157
|
+
```
|
|
158
|
+
Context-7 MCP: Verify library API before calling
|
|
159
|
+
GitHub MCP: Search existing code for patterns, check PRs
|
|
160
|
+
PostgreSQL MCP: Introspect schema before migrations
|
|
161
|
+
Playwright MCP: Browser automation for visual TDD
|
|
162
|
+
Semgrep MCP: Security scan while implementing security features
|
|
163
|
+
Sequential Think: Complex multi-step reasoning before acting
|
|
164
|
+
```
|
|
165
|
+
|
|
166
|
+
---
|
|
167
|
+
|
|
168
|
+
## REFLECT Phase — Detailed
|
|
169
|
+
|
|
170
|
+
Self-critique questions (answer before claiming done):
|
|
171
|
+
|
|
172
|
+
```
|
|
173
|
+
Architecture:
|
|
174
|
+
"Is business logic in the correct layer (domain/application)?"
|
|
175
|
+
"Are there any new imports from outer layers in inner layers?"
|
|
176
|
+
"Did I create any new circular dependencies?"
|
|
177
|
+
|
|
178
|
+
Code Quality:
|
|
179
|
+
"Is cyclomatic complexity < 10 for new/modified functions?"
|
|
180
|
+
"Are there any magic numbers or strings that should be constants?"
|
|
181
|
+
"Is any function > 30 lines? Should it be extracted?"
|
|
182
|
+
|
|
183
|
+
Security:
|
|
184
|
+
"Are all user inputs validated at this layer boundary?"
|
|
185
|
+
"Is there any PII in log statements?"
|
|
186
|
+
"Are there any hardcoded secrets?"
|
|
187
|
+
"For auth/data features: was a threat model done?"
|
|
188
|
+
|
|
189
|
+
Governance:
|
|
190
|
+
"Data: Is new data classified (PII/Public/Confidential)?"
|
|
191
|
+
"Events: Do new events have a defined Schema?"
|
|
192
|
+
"Async: Does the new consumer have a DLQ?"
|
|
193
|
+
|
|
194
|
+
Tests:
|
|
195
|
+
"Are null/undefined edge cases tested?"
|
|
196
|
+
"Are error paths tested?"
|
|
197
|
+
"Are boundary values tested (empty string, max length, etc.)?"
|
|
198
|
+
```
|
|
199
|
+
|
|
200
|
+
---
|
|
201
|
+
|
|
202
|
+
## VERIFY Phase — Detailed
|
|
203
|
+
|
|
204
|
+
### Verification Commands (from AGENTS.md)
|
|
205
|
+
```bash
|
|
206
|
+
# Run in order — fix each before proceeding to next
|
|
207
|
+
[test command] # All tests MUST be green
|
|
208
|
+
[typecheck command] # Zero type errors
|
|
209
|
+
[lint command] # Zero lint errors
|
|
210
|
+
npx madge --circular src/ # Zero circular dependencies (optional, run periodically)
|
|
211
|
+
```
|
|
212
|
+
|
|
213
|
+
### Verification Failures → self-heal.skill
|
|
214
|
+
```
|
|
215
|
+
If any verification fails:
|
|
216
|
+
- Classify error type (type, test, lint, runtime, unknown)
|
|
217
|
+
- Apply fix (see self-heal.skill for full procedure)
|
|
218
|
+
- Re-run verification
|
|
219
|
+
- Repeat up to 5 times
|
|
220
|
+
- After 5: escalate to human
|
|
221
|
+
```
|
|
222
|
+
|
|
223
|
+
---
|
|
224
|
+
|
|
225
|
+
## Integration with Memory System
|
|
226
|
+
|
|
227
|
+
### After Successful RARV
|
|
228
|
+
```
|
|
229
|
+
1. Update project/TASKS.md: task status → DONE
|
|
230
|
+
2. Write AUDIT_LOG.md entry: TASK_DONE
|
|
231
|
+
3. Store any research findings in semantic/PROJECT_KNOWLEDGE_TEMPLATE.md
|
|
232
|
+
4. If pattern worth remembering: add to semantic memory
|
|
233
|
+
Example: "Prisma cursor pagination works with: { cursor: { id }, take: 20, skip: 1 }"
|
|
234
|
+
```
|
|
235
|
+
|
|
236
|
+
### After Failed RARV (escalation)
|
|
237
|
+
```
|
|
238
|
+
1. Write AUDIT_LOG.md entry: HUMAN_ESCALATION
|
|
239
|
+
2. Update project/TASKS.md: task status → BLOCKED
|
|
240
|
+
3. Write to CONTINUITY.md: what was tried and why it failed
|
|
241
|
+
This prevents the same failure in future sessions
|
|
242
|
+
4. Wait for human decision
|
|
243
|
+
```
|
|
244
|
+
|
|
245
|
+
---
|
|
246
|
+
|
|
247
|
+
## RARV in Context of Multi-Session Projects
|
|
248
|
+
|
|
249
|
+
```
|
|
250
|
+
Session 1: Complete tasks T-001 to T-020 via RARV
|
|
251
|
+
→ AUDIT_LOG records all decisions
|
|
252
|
+
→ SESSION_SNAPSHOT saved at end
|
|
253
|
+
|
|
254
|
+
[Interruption — session ends]
|
|
255
|
+
|
|
256
|
+
Session 2: session-resume.skill loads all memory
|
|
257
|
+
→ CONTINUITY.md reviewed (prevents repeating T-015's mistake)
|
|
258
|
+
→ AUDIT_LOG last 50 entries reviewed
|
|
259
|
+
→ Continue from T-021 via RARV
|
|
260
|
+
```
|
|
261
|
+
|
|
262
|
+
The RARV cycle is stateless per-task but accumulates knowledge through the memory system across sessions.
|
|
@@ -0,0 +1,183 @@
|
|
|
1
|
+
# The Extension Protocol: How to Extend GABBE Without Breaking It
|
|
2
|
+
|
|
3
|
+
GABBE is designed to absorb new methodologies, capabilities, and integrations over time without
|
|
4
|
+
ever forcing a breaking change on the people and agents already using it. The mechanism that makes
|
|
5
|
+
this safe is a single, strict rule: **extension is additive only**. You add new files and new keys;
|
|
6
|
+
you never remove a file, rename a key, retype an existing field, or change the meaning of something
|
|
7
|
+
that already exists. This guide is the canonical, step-by-step contract for adding each kind of
|
|
8
|
+
thing — a skill, a guide, a persona, a template, an agent-client emitter, an MCP server, or a model
|
|
9
|
+
— in a way that keeps every validator and backward-compatibility gate green.
|
|
10
|
+
|
|
11
|
+
## The one rule that makes everything else work
|
|
12
|
+
|
|
13
|
+
Backward compatibility is enforced, not merely encouraged. On every change GABBE runs six
|
|
14
|
+
backward-compatibility gates (via `scripts/gates/run_gates.sh`): API surface, CLI `--help`
|
|
15
|
+
byte-equality, config-schema superset, DB-schema superset, emitter golden vault, and CVE delta.
|
|
16
|
+
Read what "superset" implies: the new config schema and DB schema must be **supersets** of the old
|
|
17
|
+
ones. Adding a new optional key is a superset and passes; removing a key, making an optional key
|
|
18
|
+
required, or changing a key's type is not a superset and fails the gate. The same spirit applies to
|
|
19
|
+
the markdown kit. So before you add anything, internalize the rule:
|
|
20
|
+
|
|
21
|
+
- **Add** new files and new keys freely.
|
|
22
|
+
- **Never remove** an existing file, key, persona, skill, guide, or template.
|
|
23
|
+
- **Never rename or retype** an existing field — a rename is a remove plus an add, and the remove
|
|
24
|
+
half breaks compatibility. If you must evolve a field, add a new one alongside and leave the old
|
|
25
|
+
one working.
|
|
26
|
+
- **Never change the meaning** of an existing key, trigger, or phase id.
|
|
27
|
+
|
|
28
|
+
Everything below is just this rule applied to each artifact type.
|
|
29
|
+
|
|
30
|
+
## Adding a new skill
|
|
31
|
+
|
|
32
|
+
1. Create the file under the right category folder: `agents/skills/<category>/<name>.skill.md`
|
|
33
|
+
(categories include `core`, `coordination`, `architecture`, `coding`, `ops`, `security`, `ai`,
|
|
34
|
+
`data`, `product`, `industry`, `brain`).
|
|
35
|
+
2. Give it the required frontmatter contract — the same shape every existing skill uses:
|
|
36
|
+
|
|
37
|
+
```
|
|
38
|
+
---
|
|
39
|
+
name: <slug matching the filename>
|
|
40
|
+
description: <one line — what it does and when>
|
|
41
|
+
triggers: [<natural-language phrases that should activate it>]
|
|
42
|
+
tags: [<category>]
|
|
43
|
+
core: <true|false>
|
|
44
|
+
context_cost: <low|medium|high>
|
|
45
|
+
---
|
|
46
|
+
```
|
|
47
|
+
|
|
48
|
+
`context_cost` is load-bearing: preflight ranks capabilities by relevance × (1 / context_cost),
|
|
49
|
+
so set it honestly. Mark `core: true` only for skills that belong in the always-available set.
|
|
50
|
+
3. Write the body in the established skill shape (Goal, then Steps). Reference other skills,
|
|
51
|
+
personas, and guides **by name in backticks** (e.g. `clarify.skill`, `prod-architect`) — never
|
|
52
|
+
as markdown file-path links, which the link validator would have to resolve and which couple the
|
|
53
|
+
doc to a path.
|
|
54
|
+
4. Register it additively in `agents/skills/00-index.md` by adding a new catalog row. Do not
|
|
55
|
+
reorder or remove existing rows; append.
|
|
56
|
+
5. Keep the validators green (see the checklist at the end): `validate_skills.py` checks the
|
|
57
|
+
frontmatter contract, `check_skills_docs.py` / frontmatter validators check consistency, and
|
|
58
|
+
`validate_links.py` checks that no markdown link is broken.
|
|
59
|
+
|
|
60
|
+
## Adding a new guide
|
|
61
|
+
|
|
62
|
+
1. Create `agents/guides/<category>/<name>.md`. Guides are explanatory prose. Frontmatter is
|
|
63
|
+
optional for guides (some existing guides carry a one-line `description:`, many carry none) —
|
|
64
|
+
prefer self-contained prose and keep references in backticks by name, with no URLs and no
|
|
65
|
+
markdown file-path links.
|
|
66
|
+
2. Register it additively in `agents/guides/00-index.md` by appending a new row under the correct
|
|
67
|
+
domain section, and bump the displayed total if the index tracks one. Never remove or renumber
|
|
68
|
+
existing entries.
|
|
69
|
+
3. A guide adds knowledge, not behavior, so it touches no schema and no emitter — the only gate it
|
|
70
|
+
must satisfy is the link validator (no broken links) plus index consistency.
|
|
71
|
+
|
|
72
|
+
## Adding a new persona
|
|
73
|
+
|
|
74
|
+
1. Create `agents/personas/<swarm>-<role>.md` following the persona house style exactly: a
|
|
75
|
+
`# Persona: <name>` heading and an HTML-comment subtitle, then the sections
|
|
76
|
+
**Role**, **Does NOT**, **Context Scope**, **Primary Outputs**, **Skills Used**, a RARV cycle
|
|
77
|
+
(the **RARV Notes** block: Reason / Act / Reflect / Verify), **Constraints**, and an
|
|
78
|
+
**Invocation Example**. Match an existing persona such as `eng-qa` or `prod-pm` for structure.
|
|
79
|
+
2. In **Skills Used**, reference skills by name in backticks. If a referenced skill does not exist
|
|
80
|
+
yet, add it first (additively, per the skill steps above) or state honestly that the persona
|
|
81
|
+
defines the contract that skill must satisfy.
|
|
82
|
+
3. Register it additively in `agents/personas/00-index.md`: add the persona to the appropriate
|
|
83
|
+
swarm table and bump the persona count the index reports. Never remove an existing persona — an
|
|
84
|
+
agent or workflow may already invoke it by name.
|
|
85
|
+
|
|
86
|
+
## Adding a new template
|
|
87
|
+
|
|
88
|
+
1. Create the template under `agents/templates/<category>/<NAME>_TEMPLATE.md` (or the matching
|
|
89
|
+
convention for that category). Templates are fill-in documents agents complete during specific
|
|
90
|
+
lifecycle phases.
|
|
91
|
+
2. Register it additively in `agents/templates/00-index.md` with a new row and an updated total.
|
|
92
|
+
3. If a persona or skill is meant to produce the new template, reference it by name (in backticks)
|
|
93
|
+
from that persona/skill — additively, without altering their existing outputs.
|
|
94
|
+
|
|
95
|
+
## Adding a new agent-client emitter
|
|
96
|
+
|
|
97
|
+
GABBE's kit is emitted into each agent's native location on install (for example
|
|
98
|
+
`.claude/skills/<slug>/SKILL.md` for Claude, `.cursor/rules/*.mdc` for Cursor, `.github/skills/`
|
|
99
|
+
for VS Code/Copilot, `.gemini/`, and the universal `.agents/skills/<slug>/SKILL.md` tree).
|
|
100
|
+
|
|
101
|
+
1. Add a **new** emitter that writes to the new agent's native path — never modify an existing
|
|
102
|
+
emitter's output, because the **emitter golden vault** gate compares emitted output byte-for-byte
|
|
103
|
+
against captured baselines. Changing an existing emitter's bytes fails that gate.
|
|
104
|
+
2. Capture a baseline for the new emitter (the gates use `scripts/gates/capture_emitter_baseline.py`
|
|
105
|
+
and `scripts/gates/baselines/`) so the golden-vault gate has something to compare the new output
|
|
106
|
+
against going forward.
|
|
107
|
+
3. Wire the new emitter into the install flow additively (Node installer `bin/install.js` and/or
|
|
108
|
+
the Python/shell installers) so it runs alongside, not instead of, the existing emitters.
|
|
109
|
+
4. Confirm the existing emitters' baselines are still byte-identical — the whole point is that
|
|
110
|
+
adding agent N does not perturb the output for agents 1..N-1.
|
|
111
|
+
|
|
112
|
+
## Adding a new MCP server
|
|
113
|
+
|
|
114
|
+
1. Document the new server additively in `docs/MCP_CONFIGURATIONS.md` and any MCP registry the kit
|
|
115
|
+
ships — add an entry; do not change or remove existing entries.
|
|
116
|
+
2. If the optional `gabbe` CLI's MCP layer (`gabbe/mcp_server.py`) gains a new tool, add it as a
|
|
117
|
+
**new** tool with a new name. Do not rename or change the signature of an existing MCP tool —
|
|
118
|
+
that is part of the API surface the API-surface gate protects.
|
|
119
|
+
3. Keep secrets and endpoints out of committed config; reference them through the established
|
|
120
|
+
secret/config mechanism. Default to fail-closed, consistent with the kit's security posture.
|
|
121
|
+
|
|
122
|
+
## Adding a new model
|
|
123
|
+
|
|
124
|
+
1. Register the model additively in the model configuration (`gabbe/config.py` and the config
|
|
125
|
+
schema documented in `docs/SCHEMA.md`) as a **new** entry / new optional key. The config-schema
|
|
126
|
+
gate requires the new schema to be a superset of the old, so a new optional model key passes
|
|
127
|
+
while changing the type or default of an existing one fails.
|
|
128
|
+
2. Do not change existing model ids, defaults, or tiers — downstream configs and routing may depend
|
|
129
|
+
on them. Add the new model as an additional choice and, if needed, an additional tier.
|
|
130
|
+
3. If you are configuring or reasoning about a Claude/Anthropic model specifically, consult the
|
|
131
|
+
current `claude-api` reference rather than relying on memory for ids, pricing, or limits.
|
|
132
|
+
|
|
133
|
+
## The frontmatter + index-registration contract, in one place
|
|
134
|
+
|
|
135
|
+
Two invariants make a new artifact discoverable and selectable:
|
|
136
|
+
|
|
137
|
+
- **Frontmatter contract** (skills, and any artifact that carries it): the keys above must be
|
|
138
|
+
present and well-formed; `name` must match the filename slug; `context_cost` must be set because
|
|
139
|
+
selection ranking depends on it. Validators enforce this.
|
|
140
|
+
- **Index registration**: every artifact must be appended to its `00-index.md` (skills, guides,
|
|
141
|
+
personas, templates) so preflight's cheap index scan can see it. Append; never reorder or remove.
|
|
142
|
+
An artifact that exists on disk but is missing from its index is effectively invisible to the
|
|
143
|
+
selection flow, and the consistency checks will flag the mismatch.
|
|
144
|
+
|
|
145
|
+
## The validators and gates that must stay green
|
|
146
|
+
|
|
147
|
+
Before you consider an extension done, the same checks CI runs must pass. `scripts/verify_all.sh`
|
|
148
|
+
orchestrates them; the ones you will most often touch are:
|
|
149
|
+
|
|
150
|
+
- **Backward-compat gates** — `scripts/gates/run_gates.sh`: API surface, CLI `--help` byte-equality,
|
|
151
|
+
config-schema superset, DB-schema superset, emitter golden vault, CVE delta. These encode the
|
|
152
|
+
additive-only rule mechanically.
|
|
153
|
+
- **`agents/scripts/validate_skills.py`** — skill frontmatter contract and structure.
|
|
154
|
+
- **`agents/scripts/validate_links.py`** — no broken markdown links. (Keeping references in
|
|
155
|
+
backticks by name, rather than as bracket-and-parenthesis file-path links, is the simplest way
|
|
156
|
+
to never break this.)
|
|
157
|
+
- **`agents/scripts/validate_integrity.py`** and the other consistency/capability validators
|
|
158
|
+
(frontmatter, use-cases, triggers/MCP, methodology graph) — cross-file coherence, including that
|
|
159
|
+
index registrations match the files on disk and that referenced phases/skills exist.
|
|
160
|
+
|
|
161
|
+
If all of these are green and you added only new files and new keys, your extension is, by
|
|
162
|
+
construction, backward compatible.
|
|
163
|
+
|
|
164
|
+
## Why this protocol is the absorption mechanism
|
|
165
|
+
|
|
166
|
+
Because every extension is additive and every existing surface is gate-protected, GABBE can take on
|
|
167
|
+
a new methodology — a new persona swarm, a new lifecycle phase id (the phase validator already
|
|
168
|
+
accepts extended Day-2 phases like S11/S12 alongside S01–S10), a new skill family, a new target
|
|
169
|
+
agent — by **adding** the artifacts that express it, never by mutating what is already there.
|
|
170
|
+
Nothing that works today stops working tomorrow. That is the contract that lets the system grow
|
|
171
|
+
indefinitely without a breaking change, and it is worth following exactly rather than approximately:
|
|
172
|
+
the gates do not negotiate, and that strictness is the feature.
|
|
173
|
+
|
|
174
|
+
## Honest limits
|
|
175
|
+
|
|
176
|
+
- The gates catch *compatibility* regressions, not *quality* — an additive change can be green and
|
|
177
|
+
still be a bad idea. Review still matters.
|
|
178
|
+
- "Additive only" can accumulate cruft over time (deprecated-but-retained keys, superseded skills).
|
|
179
|
+
GABBE accepts that cost deliberately as the price of never breaking callers; periodic curation is
|
|
180
|
+
a separate, human-gated decision, not something this protocol authorizes you to do unilaterally.
|
|
181
|
+
- A new artifact is only as discoverable as its index entry and its `triggers`/`context_cost`; a
|
|
182
|
+
technically-valid file with poor metadata may never get selected. Registration is necessary but
|
|
183
|
+
not sufficient for the capability to actually be used.
|
|
@@ -0,0 +1,47 @@
|
|
|
1
|
+
# Guide: Full System Lifecycle (The Golden Thread)
|
|
2
|
+
|
|
3
|
+
Traceability is not red tape. It is the only way to know if you are building the *right* thing and if it *works*.
|
|
4
|
+
|
|
5
|
+
## 1. The Golden Thread
|
|
6
|
+
|
|
7
|
+
The "Golden Thread" is the unbroken line linking a business need to a deployed binary.
|
|
8
|
+
|
|
9
|
+
0. **Discovery (Day-0, S00)**: Before any requirement exists, S00 frames the problem,
|
|
10
|
+
sizes the opportunity, sets the North-Star/HEART metrics, and prioritizes the bet
|
|
11
|
+
(RICE). The business case below is the *output* of a passed S00 human GO/NO-GO gate —
|
|
12
|
+
the thread starts at the discovered problem, not at the first requirement.
|
|
13
|
+
1. **Business Case**: "We need to reduce fraud."
|
|
14
|
+
2. **Requirement (PRD)**: `REQ-050`: "System must Block IP after 5 failed attempts."
|
|
15
|
+
3. **Architecture (Design)**: `ADR-010`: "Use Redis for disjoint rate limiting."
|
|
16
|
+
4. **Implementation (Code)**: `RateLimiter.py`: Implements sliding window logic.
|
|
17
|
+
5. **Verification (Test)**: `test_rate_limiter.py`: Simulates 6 failures and asserts block.
|
|
18
|
+
6. **Operate (Day-2, S11)**: SLOs, runbooks, on-call, patching and cost monitoring keep
|
|
19
|
+
the deployed binary healthy — the thread now links the live metric back to `REQ-050`.
|
|
20
|
+
7. **Evolve (Day-2, S12)**: Blameless retrospectives, product analytics and A/B
|
|
21
|
+
experiments turn live signal into the *next* discovery, looping back to S00/S01.
|
|
22
|
+
8. **Sunset (Day-2, S13)**: When the need is gone, the deprecation/retention/migration
|
|
23
|
+
plan retires the code deliberately — closing the thread instead of leaving Zombie Code.
|
|
24
|
+
|
|
25
|
+
**If you break this thread, you have "Zombie Code" (code with no purpose) or "Orphan Requirements" (needs with no code).**
|
|
26
|
+
The thread is therefore a full Day-0 → build → Day-2 loop: discovery (S00) opens it,
|
|
27
|
+
operate/evolve/sunset (S11–S13) keep it honest and eventually close it.
|
|
28
|
+
|
|
29
|
+
## 2. Managing Requirements
|
|
30
|
+
- **Atomic**: One requirement = one testable statement.
|
|
31
|
+
- **ID-Driven**: Give everything an ID (`REQ-XXX`). Never refer to "that login feature".
|
|
32
|
+
- **Immutable**: Don't change a requirement. Obsolete it and create a new one.
|
|
33
|
+
|
|
34
|
+
## 3. Backward vs Forward Traceability
|
|
35
|
+
- **Forward**: PRD -> Code -> Test. "Did we build everything we asked for?"
|
|
36
|
+
- **Backward**: Test -> Code -> PRD. "Why does this code exist?" (Great for deduping).
|
|
37
|
+
|
|
38
|
+
## 4. The definition of Done (DoD)
|
|
39
|
+
You are not done when the code runs. You are done when:
|
|
40
|
+
1. Code is written.
|
|
41
|
+
2. Tests pass.
|
|
42
|
+
3. Traceability Matrix is updated.
|
|
43
|
+
4. Documentation reflects the change.
|
|
44
|
+
|
|
45
|
+
## 5. Tools
|
|
46
|
+
- **Skill**: `system-lifecycle`
|
|
47
|
+
- **Template**: `core/TRACEABILITY_MATRIX_TEMPLATE.md`
|
|
@@ -0,0 +1,82 @@
|
|
|
1
|
+
# Knowledge Integration Guide
|
|
2
|
+
|
|
3
|
+
> **Goal**: Equip your agents with persistent, searchable knowledge (RAG) and active connections to external systems.
|
|
4
|
+
|
|
5
|
+
---
|
|
6
|
+
|
|
7
|
+
## 1. Overview: The "Second Brain"
|
|
8
|
+
Agents have limited context windows. To build expert systems, you must give them a "Second Brain" — a Vector Database or Knowledge Graph that stores infinite context.
|
|
9
|
+
|
|
10
|
+
**Components:**
|
|
11
|
+
1. **Connectors (MCP)**: The "Hands" — fetch data from Notion, GitHub, Google Drive.
|
|
12
|
+
2. **Embedding Model**: The "Translator" — converts text to numbers (vectors).
|
|
13
|
+
3. **Vector DB**: The "Long-Term Memory" — stores vectors for fast similarity search.
|
|
14
|
+
4. **Integration Skill**: `core/knowledge-connect.skill.md` — The "Workflow".
|
|
15
|
+
|
|
16
|
+
---
|
|
17
|
+
|
|
18
|
+
## 2. Quick Start: Local RAG (Zero Cost)
|
|
19
|
+
|
|
20
|
+
1. **Install Connectors**:
|
|
21
|
+
Ensure `filesystem-kb` or basic file reading is enabled.
|
|
22
|
+
|
|
23
|
+
2. **Create Knowledge Map**:
|
|
24
|
+
Fill out `agents/templates/brain/KNOWLEDGE_MAP_TEMPLATE.md`.
|
|
25
|
+
*Example*: Map your `/docs` folder to a `project_docs` collection.
|
|
26
|
+
|
|
27
|
+
3. **Ingest (Manual/Scripted)**:
|
|
28
|
+
* Use a simple script (Python/JS) to read Markdown files.
|
|
29
|
+
* Split by headers (`#`, `##`).
|
|
30
|
+
* Store in a local vector store (e.g., ChromaDB or simple JSON with embeddings).
|
|
31
|
+
|
|
32
|
+
4. **Query**:
|
|
33
|
+
* *User*: "How does the auth system work?"
|
|
34
|
+
* *Agent*:
|
|
35
|
+
1. Embeds query "auth system".
|
|
36
|
+
2. Searches Vector DB.
|
|
37
|
+
3. Retrieves `docs/auth.md` chunk.
|
|
38
|
+
4. Answers: "According to `docs/auth.md`, we use OAuth2..."
|
|
39
|
+
|
|
40
|
+
---
|
|
41
|
+
|
|
42
|
+
## 3. High-Scale Patterns (Enterprise)
|
|
43
|
+
|
|
44
|
+
### Pattern A: Live MCP Retrieval
|
|
45
|
+
Instead of verifying, let the Agent ask the source directly via MCP.
|
|
46
|
+
* *Agent*: "I need the latest Q3 roadmap."
|
|
47
|
+
* *Tool*: `notion_mcp.search("Q3 Roadmap")`
|
|
48
|
+
* *Result*: Returns page content within seconds.
|
|
49
|
+
* **Pros**: Always fresh. **Cons**: Slower, API rate limits.
|
|
50
|
+
|
|
51
|
+
### Pattern B: Async Ingestion Pipeline
|
|
52
|
+
Background jobs sync sources to Vector DB.
|
|
53
|
+
* **ETL Job**: Runs every hour. Syncs GitHub -> Qdrant.
|
|
54
|
+
* **Agent**: Queries Qdrant (fast, <100ms).
|
|
55
|
+
* **Pros**: Fast, scalable. **Cons**: Data latency (can be stale).
|
|
56
|
+
|
|
57
|
+
### Pattern C: A2A (Agent-to-Agent) Knowledge Exchange
|
|
58
|
+
One agent acts as the "Librarian".
|
|
59
|
+
* *Coder Agent*: "Hey Librarian, do we have a standard for error handling?"
|
|
60
|
+
* *Librarian Agent*: Checks semantic memory, returns the specific "Error Handling RFC".
|
|
61
|
+
|
|
62
|
+
---
|
|
63
|
+
|
|
64
|
+
## 4. Vector Database Options
|
|
65
|
+
|
|
66
|
+
| Database | Best For | Setup |
|
|
67
|
+
|---|---|---|
|
|
68
|
+
| **Qdrant** | Production, performance, filtering | `docker run qdrant/qdrant` |
|
|
69
|
+
| **Chroma** | Simplicity, local dev (Python/JS) | `pip install chromadb` |
|
|
70
|
+
| **Pinecone** | Managed service (Serverless) | Cloud Sign-up |
|
|
71
|
+
| **Pgvector** | Use if you already have Postgres | Extension on existing DB |
|
|
72
|
+
|
|
73
|
+
---
|
|
74
|
+
|
|
75
|
+
## 5. Security & Governance
|
|
76
|
+
|
|
77
|
+
> [!WARNING]
|
|
78
|
+
> **Never index secrets.** A RAG system will happily retrieve "AWS_SECRET_KEY" if asked, if you indexed your `.env` file.
|
|
79
|
+
|
|
80
|
+
* **Pii Scrubbing**: Use `presidio` or Regex to purge emails/phones before indexing.
|
|
81
|
+
* **ACLs**: Store `user_id` or `group_id` in metadata. Verify access time.
|
|
82
|
+
* **Data Sovereignty**: Ensure Vector DB location complies with GDPR (e.g., EU region).
|