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 +1,309 @@
|
|
|
1
|
+
# Guide: AI / Agentic Engineering
|
|
2
|
+
<!-- RARV Cycle, SDD Lifecycle, Memory Architecture, MCP, Multi-Agent Orchestration -->
|
|
3
|
+
|
|
4
|
+
---
|
|
5
|
+
|
|
6
|
+
## The Agentic Engineering Stack
|
|
7
|
+
|
|
8
|
+
```
|
|
9
|
+
┌─────────────────────────────────────────────────────┐
|
|
10
|
+
│ AGENTS.md (Agent Context Layer) │
|
|
11
|
+
│ - Project `diagramming`, `domain-model`, `adaptive-architecture`, `compatibility-design` | diagram, domain, local-first, compatibility |
|
|
12
|
+
| `architecture-governance`, `error-handling-strategy`, `event-governance` | archunit, error handling, schema registry |identity, commands, architecture rules │
|
|
13
|
+
│ - Workflow policies, research rules, self-heal limits│
|
|
14
|
+
├─────────────────────────────────────────────────────┤
|
|
15
|
+
│ Skills (Capability Layer) │
|
|
16
|
+
│ - Packaged workflows with triggers + constraints │
|
|
17
|
+
│ - Invoked by keyword or explicit name │
|
|
18
|
+
├─────────────────────────────────────────────────────┤
|
|
19
|
+
│ MCP Servers (Tool Layer — "Agent Hands") │
|
|
20
|
+
│ - Context-7, GitHub, PostgreSQL, Semgrep, Playwright│
|
|
21
|
+
│ - Configured in MCP_CONFIG_TEMPLATE.json │
|
|
22
|
+
├─────────────────────────────────────────────────────┤
|
|
23
|
+
│ Memory (Continuity Layer) │
|
|
24
|
+
│ - Working → Episodic → Semantic → Procedural │
|
|
25
|
+
│ - Stored in agents/memory/ │
|
|
26
|
+
└─────────────────────────────────────────────────────┘
|
|
27
|
+
```
|
|
28
|
+
|
|
29
|
+
---
|
|
30
|
+
|
|
31
|
+
## RARV Cycle — The Agent Cognitive Loop
|
|
32
|
+
|
|
33
|
+
Every task follows Reason → Act → Reflect → Verify:
|
|
34
|
+
|
|
35
|
+
### Reason
|
|
36
|
+
```
|
|
37
|
+
1. Read relevant context: AGENTS.md, CONSTITUTION.md, current task
|
|
38
|
+
2. Read CONTINUITY.md — what past failures are relevant?
|
|
39
|
+
3. Detect knowledge gaps → invoke knowledge-gap.skill if uncertain
|
|
40
|
+
4. Formulate explicit plan: what files, what tests, what outcome?
|
|
41
|
+
5. If security-sensitive: invoke threat-model.skill first
|
|
42
|
+
```
|
|
43
|
+
|
|
44
|
+
### Act
|
|
45
|
+
```
|
|
46
|
+
1. Write failing test (TDD Red)
|
|
47
|
+
2. Implement minimal code (TDD Green)
|
|
48
|
+
3. Use MCP tools for: DB queries, code search, external APIs, research
|
|
49
|
+
4. Update task status in project/TASKS.md → IN_PROGRESS
|
|
50
|
+
```
|
|
51
|
+
|
|
52
|
+
### Reflect
|
|
53
|
+
```
|
|
54
|
+
Self-critique before claiming done:
|
|
55
|
+
- "Did I follow Library-First? Is business logic in the domain layer?"
|
|
56
|
+
- "Did I introduce any circular imports?"
|
|
57
|
+
- "Did I verify the API version via Context-7 (not training data)?"
|
|
58
|
+
- "Are all edge cases covered in tests?"
|
|
59
|
+
- "Would a security reviewer find issues here?"
|
|
60
|
+
```
|
|
61
|
+
|
|
62
|
+
### Verify
|
|
63
|
+
```
|
|
64
|
+
1. Run: [test command] → must be GREEN
|
|
65
|
+
2. Run: [typecheck command] → zero errors
|
|
66
|
+
3. Run: [lint command] → zero errors
|
|
67
|
+
4. Run: agentic-linter → no boundary violations
|
|
68
|
+
5. If FAIL: invoke self-heal.skill (max 5 attempts)
|
|
69
|
+
6. If still FAIL after 5: ESCALATE to human (stop all action)
|
|
70
|
+
```
|
|
71
|
+
|
|
72
|
+
---
|
|
73
|
+
|
|
74
|
+
## SDD Lifecycle — Spec-Driven Development
|
|
75
|
+
|
|
76
|
+
### Phase 1: Specify (`spec-writer.skill`)
|
|
77
|
+
```
|
|
78
|
+
Input: User goal ("Build X for Y")
|
|
79
|
+
Process:
|
|
80
|
+
1. Identify actors, use cases, constraints
|
|
81
|
+
2. Invoke Ambiguity Layer — ask clarifying questions
|
|
82
|
+
3. Generate PRD.md with EARS requirements
|
|
83
|
+
4. Define acceptance criteria (Given/When/Then)
|
|
84
|
+
Output: PRD.md — human reviews and approves
|
|
85
|
+
```
|
|
86
|
+
|
|
87
|
+
### Phase 2: Clarify (Ambiguity Layer, built into spec-writer.skill)
|
|
88
|
+
```
|
|
89
|
+
Questions the agent MUST ask before writing any requirement:
|
|
90
|
+
- "Who are the users? What are their roles/permissions?"
|
|
91
|
+
- "What happens when [edge case]?"
|
|
92
|
+
- "What is explicitly out of scope for v1?"
|
|
93
|
+
- "Are there regulatory requirements? (GDPR, HIPAA, PCI)"
|
|
94
|
+
- "What are the performance expectations?"
|
|
95
|
+
|
|
96
|
+
No assumptions allowed — everything ambiguous must be clarified.
|
|
97
|
+
```
|
|
98
|
+
|
|
99
|
+
### Phase 3: Plan (`adr-writer.skill` + prod-architect persona)
|
|
100
|
+
```
|
|
101
|
+
Input: Approved PRD.md
|
|
102
|
+
Process:
|
|
103
|
+
1. Identify architecture impact — which layers change?
|
|
104
|
+
2. Create ADR for each significant technology decision
|
|
105
|
+
3. Create C4 Level 1-3 diagrams
|
|
106
|
+
4. Invoke `security-audit`, `threat-model`, `privacy-audit`, `compliance-review`, `legal-review` | security, threat, privacy, SOC2, legal |
|
|
107
|
+
| `access-control`, `data-governance`, `backup-recovery`, `queue-management` | rbac, lineage, backup, dlq |threat-model.skill for security features
|
|
108
|
+
5. Write PLAN.md with ordered implementation phases
|
|
109
|
+
Output: PLAN.md + ADRs + threat model — human reviews and approves
|
|
110
|
+
```
|
|
111
|
+
|
|
112
|
+
### Phase 4: Decompose (15-Minute Rule)
|
|
113
|
+
```
|
|
114
|
+
Input: Approved PLAN.md
|
|
115
|
+
Process:
|
|
116
|
+
1. Break each phase into atomic tasks
|
|
117
|
+
2. Each task: achievable in ~15 minutes, single file/function
|
|
118
|
+
3. Each task: has testable acceptance criteria
|
|
119
|
+
4. Verify task ordering matches dependencies
|
|
120
|
+
Output: project/TASKS.md — reviewed by tech lead
|
|
121
|
+
```
|
|
122
|
+
|
|
123
|
+
### Phase 5: Implement (RARV cycle per task)
|
|
124
|
+
```
|
|
125
|
+
Input: project/TASKS.md, AGENTS.md, CONSTITUTION.md, CONTINUITY.md
|
|
126
|
+
For each task:
|
|
127
|
+
1. RARV cycle (above)
|
|
128
|
+
2. Audit trail entry
|
|
129
|
+
3. Task status → DONE
|
|
130
|
+
4. sdlc-checkpoint at phase boundaries
|
|
131
|
+
```
|
|
132
|
+
|
|
133
|
+
---
|
|
134
|
+
|
|
135
|
+
## Memory Architecture — 4 Layers
|
|
136
|
+
|
|
137
|
+
### Working Memory
|
|
138
|
+
```
|
|
139
|
+
Scope: Current context window
|
|
140
|
+
Contains: Current task, recent code, this session's decisions
|
|
141
|
+
Lifetime: Single session
|
|
142
|
+
Management: Managed automatically by the agent runtime
|
|
143
|
+
```
|
|
144
|
+
|
|
145
|
+
### Episodic Memory
|
|
146
|
+
```
|
|
147
|
+
Scope: Project-level, persists across sessions
|
|
148
|
+
Location: agents/memory/episodic/
|
|
149
|
+
Contains: Past decisions, failed experiments per session (DECISION_LOG)
|
|
150
|
+
Per-milestone snapshots (SESSION_SNAPSHOT/)
|
|
151
|
+
Audit log of all actions (AUDIT_LOG.md)
|
|
152
|
+
Lifetime: Project lifetime
|
|
153
|
+
Use: session-resume.skill reads last 50 AUDIT_LOG entries + latest snapshot
|
|
154
|
+
```
|
|
155
|
+
|
|
156
|
+
### Semantic Memory
|
|
157
|
+
```
|
|
158
|
+
Scope: Project-level, crystallized knowledge
|
|
159
|
+
Location: agents/memory/semantic/PROJECT_KNOWLEDGE_TEMPLATE.md
|
|
160
|
+
Contains: Verified facts: auth quirks, schema conventions, API constraints
|
|
161
|
+
Research findings from research.skill
|
|
162
|
+
Decisions that affect all future work
|
|
163
|
+
Lifetime: Project lifetime (updated, not replaced)
|
|
164
|
+
Use: session-resume.skill loads this at start
|
|
165
|
+
```
|
|
166
|
+
|
|
167
|
+
### Procedural Memory
|
|
168
|
+
```
|
|
169
|
+
Scope: Global (across projects)
|
|
170
|
+
Location: agents/skills/*.skill.md
|
|
171
|
+
Contains: Immutable how-to guides (TDD cycle, debug flow, etc.)
|
|
172
|
+
Referenced by agent keywords
|
|
173
|
+
Lifetime: Stable — only updated when workflows change
|
|
174
|
+
Use: Invoked on demand by trigger keywords
|
|
175
|
+
```
|
|
176
|
+
|
|
177
|
+
### CONTINUITY.md — The Most Important Memory File
|
|
178
|
+
```
|
|
179
|
+
Location: agents/memory/CONTINUITY.md
|
|
180
|
+
Read: EVERY session start (before any action)
|
|
181
|
+
Contains: Past failures: "Tried X, failed because Y, switched to Z"
|
|
182
|
+
Prevents: Agents repeating failed approaches across sessions
|
|
183
|
+
|
|
184
|
+
Entry format:
|
|
185
|
+
### [DATE] — [Brief title]
|
|
186
|
+
Context: What were you trying to do?
|
|
187
|
+
Approach tried: What did you try?
|
|
188
|
+
Why it failed: Root cause
|
|
189
|
+
Resolution: What worked, or "unresolved"
|
|
190
|
+
Tags: [library-conflict | type-error | architecture | security]
|
|
191
|
+
```
|
|
192
|
+
|
|
193
|
+
---
|
|
194
|
+
|
|
195
|
+
## EARS Syntax — Quick Reference
|
|
196
|
+
|
|
197
|
+
### All 5 Patterns
|
|
198
|
+
|
|
199
|
+
```
|
|
200
|
+
Ubiquitous (always):
|
|
201
|
+
THE SYSTEM SHALL [action].
|
|
202
|
+
|
|
203
|
+
Event-Driven (triggered):
|
|
204
|
+
WHEN [trigger]
|
|
205
|
+
THE SYSTEM SHALL [response].
|
|
206
|
+
|
|
207
|
+
State-Driven (while in state):
|
|
208
|
+
WHILE [state]
|
|
209
|
+
THE SYSTEM SHALL [behavior].
|
|
210
|
+
|
|
211
|
+
Optional Feature (conditional):
|
|
212
|
+
WHERE [feature enabled]
|
|
213
|
+
THE SYSTEM SHALL [behavior].
|
|
214
|
+
|
|
215
|
+
Unwanted (negative):
|
|
216
|
+
THE SYSTEM SHALL NOT [forbidden behavior].
|
|
217
|
+
```
|
|
218
|
+
|
|
219
|
+
### Bad vs Good Requirements
|
|
220
|
+
|
|
221
|
+
```
|
|
222
|
+
BAD (vague — not testable):
|
|
223
|
+
"The system should be fast"
|
|
224
|
+
"Users might be able to export data"
|
|
225
|
+
"The API should handle errors gracefully"
|
|
226
|
+
|
|
227
|
+
GOOD (EARS — testable):
|
|
228
|
+
WHEN an API request is made to any endpoint
|
|
229
|
+
THE SYSTEM SHALL respond within 200ms at p99 under 100 concurrent requests.
|
|
230
|
+
|
|
231
|
+
WHERE the data export feature is enabled for the account
|
|
232
|
+
THE SYSTEM SHALL allow users to export their data in CSV or JSON format.
|
|
233
|
+
|
|
234
|
+
WHEN an API error occurs
|
|
235
|
+
THE SYSTEM SHALL return an RFC 7807 Problem Details JSON response with appropriate HTTP status code.
|
|
236
|
+
```
|
|
237
|
+
|
|
238
|
+
---
|
|
239
|
+
|
|
240
|
+
## MCP Configuration for Agentic Projects
|
|
241
|
+
|
|
242
|
+
```json
|
|
243
|
+
{
|
|
244
|
+
"mcpServers": {
|
|
245
|
+
"context7": { "command": "npx", "args": ["@context7/mcp-server"] },
|
|
246
|
+
"sequential-thinking": { "command": "npx", "args": ["-y", "@modelcontextprotocol/server-sequential-thinking"] },
|
|
247
|
+
"github": {
|
|
248
|
+
"command": "npx",
|
|
249
|
+
"args": ["-y", "@modelcontextprotocol/server-github"],
|
|
250
|
+
"env": { "GITHUB_PERSONAL_ACCESS_TOKEN": "${GITHUB_TOKEN}" }
|
|
251
|
+
},
|
|
252
|
+
"postgres": {
|
|
253
|
+
"command": "npx",
|
|
254
|
+
"args": ["-y", "@modelcontextprotocol/server-postgres"],
|
|
255
|
+
"env": { "POSTGRES_CONNECTION_STRING": "${DATABASE_URL}" }
|
|
256
|
+
}
|
|
257
|
+
}
|
|
258
|
+
}
|
|
259
|
+
```
|
|
260
|
+
|
|
261
|
+
**Key MCP servers for agentic engineering:**
|
|
262
|
+
- **Context-7**: Up-to-date library docs (prevents hallucinated API usage)
|
|
263
|
+
- **Sequential Thinking**: Forces structured reasoning before acting
|
|
264
|
+
- **GitHub MCP**: Read PRs, issues, search code — agent awareness of project history
|
|
265
|
+
- **Semgrep MCP**: SAST security scanning from within the agent session
|
|
266
|
+
|
|
267
|
+
---
|
|
268
|
+
|
|
269
|
+
## 7-Gate Quality System
|
|
270
|
+
|
|
271
|
+
| Gate | Tool | Command | Pass Criteria |
|
|
272
|
+
|---|---|---|---|
|
|
273
|
+
| 1 Syntax/Lint | ESLint / Pint | `[lint command]` | 0 errors |
|
|
274
|
+
| 2 Type Safety | TypeScript / PHPStan | `[typecheck command]` | 0 errors |
|
|
275
|
+
| 3 Test Coverage | Vitest / Pest | `[coverage command]` | ≥ 99% |
|
|
276
|
+
| 4 Integration | Docker Compose | `docker compose run tests` | Pass |
|
|
277
|
+
| 5 Security | npm audit / Semgrep | `[security_scan]` | 0 critical CVEs |
|
|
278
|
+
| 6 Complexity | complexity-report | `npx complexity-report` | Max < 10 |
|
|
279
|
+
| 7 EARS Compliance | spec-analyze.skill | Manual | All reqs have tests |
|
|
280
|
+
|
|
281
|
+
All 7 gates must pass before any SDLC checkpoint after S05.
|
|
282
|
+
|
|
283
|
+
---
|
|
284
|
+
|
|
285
|
+
## When to Use Loki Mode (Multi-Agent)
|
|
286
|
+
|
|
287
|
+
```
|
|
288
|
+
Single agent is sufficient for:
|
|
289
|
+
- Features with < 5 tasks
|
|
290
|
+
- Bug fixes and small refactors
|
|
291
|
+
- Code reviews and audits
|
|
292
|
+
- Documentation updates
|
|
293
|
+
|
|
294
|
+
Switch to Loki Mode for:
|
|
295
|
+
- New product builds (> 5 features)
|
|
296
|
+
- Architecture migrations
|
|
297
|
+
- Projects spanning multiple sessions/days
|
|
298
|
+
- When single agent hits context limits
|
|
299
|
+
- When parallel workstreams would benefit from specialization
|
|
300
|
+
```
|
|
301
|
+
|
|
302
|
+
See `agents/skills/brain/README.md` for Loki Mode setup and persona guide.
|
|
303
|
+
|
|
304
|
+
---
|
|
305
|
+
|
|
306
|
+
## Core Performance Skills
|
|
307
|
+
- [Performant AI Skill](../../skills/coding/performant-ai.skill.md) — Mastery of Context & Tokens.
|
|
308
|
+
- [Performant Python Skill](../../skills/coding/performant-python.skill.md) — High-throughput AI backends.
|
|
309
|
+
- [Performance Optimization](../../skills/ops/performance-optimization.skill.md) — Infrastructure scaling.
|
|
@@ -0,0 +1,60 @@
|
|
|
1
|
+
# Beyond LLMs: Advanced AI Paradigms
|
|
2
|
+
|
|
3
|
+
**The frontier of Agentic Intelligence in 2026.**
|
|
4
|
+
|
|
5
|
+
This guide explores paradigms that extend beyond pure Large Language Models, offering Explainability, Evolution, and Epistemic clarity.
|
|
6
|
+
|
|
7
|
+
---
|
|
8
|
+
|
|
9
|
+
## 1. Neuro-Symbolic AI (Hybrid)
|
|
10
|
+
**The Best of Both Worlds:**
|
|
11
|
+
* **Neural (System 1):** Fast, intuitive, handles fuzzy data (Images, Text).
|
|
12
|
+
* **Symbolic (System 2):** Slow, logical, guarantees correctness (Logic, Math, Rules).
|
|
13
|
+
|
|
14
|
+
### Application in Engineering
|
|
15
|
+
* **Formal Verification:** LLM translates code to Formal Logic (TLA+ / Coq). Symbolic Prover verifies it.
|
|
16
|
+
* **Constraint Solving:** LLM formulates the problem. SMT Solver (Z3) finds the optimal solution.
|
|
17
|
+
* **Agent Pattern:** The "Judge" (`orch-judge`) should be Neuro-Symbolic, verifying the "Artist's" work against hard rules.
|
|
18
|
+
|
|
19
|
+
---
|
|
20
|
+
|
|
21
|
+
## 2. Evolutionary & Genetic Algorithms (GA)
|
|
22
|
+
**Code that Evolves.**
|
|
23
|
+
Instead of "one-shot" generation, use "Population-based" improvement.
|
|
24
|
+
|
|
25
|
+
### The "Darwinian Code" Loop
|
|
26
|
+
1. **Population:** Generate 50 variants of a function (`ui-gen` skill).
|
|
27
|
+
2. **Fitness Function:** Run unit tests + performance benchmarks (e.g., execution time).
|
|
28
|
+
3. **Selection:** Keep top 5.
|
|
29
|
+
4. **Crossover/Mutation:** Ask LLM to "Mix strategy A and B" or "Mutate parameter X".
|
|
30
|
+
5. **Repeat:** Until optimal.
|
|
31
|
+
|
|
32
|
+
*See `brain/learning-adaptation.skill.md` and `brain/self-improvement.skill.md`.*
|
|
33
|
+
|
|
34
|
+
---
|
|
35
|
+
|
|
36
|
+
## 3. Active Inference & The Free Energy Principle
|
|
37
|
+
**Minimizing Surprise.**
|
|
38
|
+
Based on Karl Friston's work. Agents act to confirm their predictions about the world.
|
|
39
|
+
*See `brain/active-inference.skill.md`.*
|
|
40
|
+
|
|
41
|
+
* **Generative Model:** The Agent maintains a belief state of the Project.
|
|
42
|
+
* **Prediction Error:** The difference between "Expected State" (All tests pass) and "Sensed State" (Build failed).
|
|
43
|
+
* **Action:** The Agent codes *solely* to minimize this Prediction Error.
|
|
44
|
+
* **Epistemic Exploration:** Agent acts not just to fix, but to *learn* ("I will add a log to see what's happening").
|
|
45
|
+
|
|
46
|
+
---
|
|
47
|
+
|
|
48
|
+
## 4. Bayesian Networks
|
|
49
|
+
**Probabilistic Reasoning.**
|
|
50
|
+
LLMs are often overconfident. Bayesian Agents quantify uncertainty.
|
|
51
|
+
* **Application:** Risk Assessment. "There is a 12% probability this refactor breaks the Legacy API."
|
|
52
|
+
* **Pattern:** Update "Priors" based on "Evidence" (Test results).
|
|
53
|
+
|
|
54
|
+
---
|
|
55
|
+
|
|
56
|
+
## 5. Implementation Strategy
|
|
57
|
+
Do not abandon LLMs. **Orchestrate** them with these paradigms.
|
|
58
|
+
* Use GAs to *prompt* LLMs.
|
|
59
|
+
* Use Symbolic Logic to *filter* LLM outputs.
|
|
60
|
+
* Use Active Inference to *drive* LLM goals.
|
|
@@ -0,0 +1,121 @@
|
|
|
1
|
+
# Dynamic Capability Loading: The Load-or-Ask Flow
|
|
2
|
+
|
|
3
|
+
GABBE is built so an agent does not need every capability pre-loaded. When a task needs something
|
|
4
|
+
the agent does not currently have — a skill, a piece of knowledge, an awareness of some new tool —
|
|
5
|
+
GABBE follows a defined **load-or-ask** flow: try to discover and load the missing capability from
|
|
6
|
+
known sources; if it genuinely cannot be resolved, fall back to asking the user. This guide
|
|
7
|
+
describes that decision flow end to end.
|
|
8
|
+
|
|
9
|
+
The governing principle is simple: **prefer loading over guessing, and prefer asking over
|
|
10
|
+
hallucinating.** An agent should never invent a capability it does not have. It either finds the
|
|
11
|
+
real one, or it asks.
|
|
12
|
+
|
|
13
|
+
## The trigger: a capability gap
|
|
14
|
+
|
|
15
|
+
A capability gap is detected when the current task requires something the agent cannot satisfy
|
|
16
|
+
with what is already in context — for example, the task needs a skill that is not in
|
|
17
|
+
`agents/skills/00-index.md`, or it depends on knowledge the agent does not hold, or it touches a
|
|
18
|
+
technology the agent is unsure is current. Preflight surfaces many of these gaps at session start;
|
|
19
|
+
others appear mid-task. Either way, the same resolution flow applies.
|
|
20
|
+
|
|
21
|
+
## The four discovery sources
|
|
22
|
+
|
|
23
|
+
GABBE resolves a gap by consulting four sources, roughly in order of locality (cheapest and most
|
|
24
|
+
trusted first):
|
|
25
|
+
|
|
26
|
+
1. **`skills-registry.skill` — import an existing skill.** The first question is always "does this
|
|
27
|
+
capability already exist somewhere we can import?" The skills registry is the catalog of
|
|
28
|
+
available skills and the mechanism for pulling one in. If the missing capability is a known
|
|
29
|
+
skill (locally or in a registry GABBE can import from), this resolves the gap directly, with no
|
|
30
|
+
new research needed. Always check here before reaching for the network.
|
|
31
|
+
|
|
32
|
+
2. **`update-scan.skill` — gated discovery of what is new.** If the capability is not already
|
|
33
|
+
known, GABBE may need to discover whether it exists in the wider world. `update-scan.skill`
|
|
34
|
+
performs this discovery as a **gated** action: it is allowed to look outward (for new tools,
|
|
35
|
+
versions, or techniques) but only under the autonomy posture in effect — under `ask` it
|
|
36
|
+
proposes the scan and waits; under `hybrid`/`auto` it may proceed within budget. The gating
|
|
37
|
+
matters: discovery can cost tokens and pull in unvetted information, so it is deliberately not
|
|
38
|
+
automatic and unbounded.
|
|
39
|
+
|
|
40
|
+
3. **`emerging-tech` — the tech radar.** When the gap is "is there a newer or better way to do
|
|
41
|
+
this that I'm not aware of?", the `emerging-tech` skill acts as a tech radar: a curated view of
|
|
42
|
+
adopt / trial / assess / hold technologies. It answers currency questions ("is this library
|
|
43
|
+
still the right choice?", "has the recommended approach moved on?") so the agent can choose a
|
|
44
|
+
current capability rather than a stale one.
|
|
45
|
+
|
|
46
|
+
4. **`knowledge-connect.skill` — RAG over connected knowledge.** When the gap is informational
|
|
47
|
+
rather than tool-shaped — the agent needs *facts*, not a skill — `knowledge-connect.skill`
|
|
48
|
+
retrieves from connected knowledge sources (retrieval-augmented generation). This grounds the
|
|
49
|
+
agent in real, cited material instead of relying on parametric memory, which is exactly how a
|
|
50
|
+
knowledge gap should be closed honestly.
|
|
51
|
+
|
|
52
|
+
These are complementary, not redundant: registry import answers "do we already have the skill?",
|
|
53
|
+
update-scan answers "does it exist out there?", emerging-tech answers "is what we'd use current?",
|
|
54
|
+
and knowledge-connect answers "what are the actual facts?".
|
|
55
|
+
|
|
56
|
+
## Preflight ranks the optimal set
|
|
57
|
+
|
|
58
|
+
Discovery typically surfaces *more* candidate capabilities than the task needs. Loading all of
|
|
59
|
+
them would bloat the context window and slow everything down. So selection is a ranking problem,
|
|
60
|
+
and `preflight.skill` performs it with an explicit objective:
|
|
61
|
+
|
|
62
|
+
```
|
|
63
|
+
rank candidates by: task_relevance × ( 1 / context_cost )
|
|
64
|
+
```
|
|
65
|
+
|
|
66
|
+
Each skill declares a `context_cost` (low / medium / high) in its frontmatter. Preflight prefers
|
|
67
|
+
high-relevance, low-cost capabilities and only pulls expensive (`high`) ones when the task truly
|
|
68
|
+
needs them. The result is the **smallest set of capabilities that covers the task** — load what
|
|
69
|
+
moves the needle, leave the rest indexed but unloaded. Index summaries are loaded cheaply; full
|
|
70
|
+
skill bodies are pulled only for the winners of this ranking.
|
|
71
|
+
|
|
72
|
+
## The fallback: ask the user
|
|
73
|
+
|
|
74
|
+
Discovery does not always succeed. The capability may not exist in any registry, the knowledge may
|
|
75
|
+
not be in any connected source, or the requirement itself may be ambiguous enough that no amount of
|
|
76
|
+
loading resolves it. When the gap is **unresolved after discovery**, GABBE does not guess and does
|
|
77
|
+
not fabricate a capability. It falls back to `clarify.skill`, which asks the user a focused,
|
|
78
|
+
batched set of questions — routed through whatever coding agent the user is driving (Claude Code,
|
|
79
|
+
Cursor, Copilot Chat, and so on). Asking is a first-class, expected outcome of this flow, not a
|
|
80
|
+
failure mode.
|
|
81
|
+
|
|
82
|
+
## The end-to-end decision flow
|
|
83
|
+
|
|
84
|
+
```
|
|
85
|
+
Task needs a capability the agent doesn't have
|
|
86
|
+
│
|
|
87
|
+
▼
|
|
88
|
+
Is it an already-known skill? ── yes ──▶ skills-registry.skill: import it
|
|
89
|
+
│ no
|
|
90
|
+
▼
|
|
91
|
+
Discover whether it exists / is current:
|
|
92
|
+
• update-scan.skill (gated discovery — respects autonomy posture & budget)
|
|
93
|
+
• emerging-tech (tech radar — is the candidate current?)
|
|
94
|
+
• knowledge-connect.skill (RAG — retrieve the actual facts, cited)
|
|
95
|
+
│
|
|
96
|
+
▼
|
|
97
|
+
Found one or more candidates? ── no ──▶ clarify.skill: ASK the user (via the coding agent)
|
|
98
|
+
│ yes
|
|
99
|
+
▼
|
|
100
|
+
preflight.skill ranks by relevance × (1 / context_cost)
|
|
101
|
+
│
|
|
102
|
+
▼
|
|
103
|
+
Load ONLY the winning minimal set (full bodies); proceed with the task
|
|
104
|
+
│
|
|
105
|
+
▼
|
|
106
|
+
Still blocked / ambiguous mid-task? ──▶ clarify.skill: ASK the user
|
|
107
|
+
```
|
|
108
|
+
|
|
109
|
+
## Honest limits
|
|
110
|
+
|
|
111
|
+
- **Discovery is gated, not omniscient.** `update-scan.skill` only finds what its sources expose,
|
|
112
|
+
and it runs under autonomy/budget gates — it will not silently scan the whole internet.
|
|
113
|
+
- **RAG is only as good as what is connected.** `knowledge-connect.skill` can only retrieve from
|
|
114
|
+
sources that are actually wired up; an empty or stale knowledge base returns little, and the
|
|
115
|
+
honest response there is to ask rather than to confabulate.
|
|
116
|
+
- **The ranking weights are heuristic.** `relevance × (1/context_cost)` is a sensible default, but
|
|
117
|
+
relevance is an estimate; preflight can pick a suboptimal set, which is one reason clarify exists.
|
|
118
|
+
- **Importing a skill is not the same as vetting it.** A newly imported skill should still be
|
|
119
|
+
reviewed before it is trusted for high-stakes work; discovery resolves availability, not safety.
|
|
120
|
+
- **Asking is the correct terminal state.** When nothing resolves the gap, falling back to
|
|
121
|
+
`clarify.skill` is the designed-for outcome — silence or invention would be the bug.
|
|
@@ -0,0 +1,111 @@
|
|
|
1
|
+
# What Is Genuinely Novel in GABBE — and What Is Conceptual
|
|
2
|
+
|
|
3
|
+
This guide is a deliberately honest inventory. GABBE makes several distinctive design bets, and
|
|
4
|
+
some of them are backed by working code while others are aspirational framing on top of a simpler
|
|
5
|
+
reality. The goal here is to let a reader tell the two apart, because the value of an honest
|
|
6
|
+
inventory is exactly that it does not overclaim. For each idea you will find: the claim, what is
|
|
7
|
+
real and working, and what is conceptual or aspirational. There are no "best-in-class" or
|
|
8
|
+
"mathematically guaranteed" claims here, by design.
|
|
9
|
+
|
|
10
|
+
## 1. Brain inference via skills
|
|
11
|
+
|
|
12
|
+
**The claim.** GABBE's "intelligence" is not locked inside a binary; it lives in structured
|
|
13
|
+
markdown skills, and a meta-cognitive "brain" reasons over project state using Active Inference to
|
|
14
|
+
choose the next strategic action.
|
|
15
|
+
|
|
16
|
+
**What is real and working.** The brain loop in `gabbe/brain.py` genuinely reads project state
|
|
17
|
+
from a database, selects a prompt via an epsilon-greedy bandit over stored "genes", calls an LLM
|
|
18
|
+
to propose the next action, and rewards the chosen gene with a monotonic success-rate bump. The
|
|
19
|
+
skills themselves are real markdown that any coding agent can load and follow with zero CLI
|
|
20
|
+
dependencies — that runtime-agnostic part is genuine and is GABBE's most distinctive trait.
|
|
21
|
+
|
|
22
|
+
**What is conceptual / aspirational.** "Active Inference" and "minimize free energy/surprise" are
|
|
23
|
+
*framing words in a system prompt*, not implemented math. No free-energy functional, generative
|
|
24
|
+
model, or belief update is computed anywhere. The honest description is "an epsilon-greedy bandit
|
|
25
|
+
over prompt variants with a success-rate reward". Also, the current reward signal means "the LLM
|
|
26
|
+
returned output", not "the output was good" — so the loop optimizes for plausible responses, not
|
|
27
|
+
yet for verified-good decisions. (See `self-evolving-skills.md` for the full breakdown.)
|
|
28
|
+
|
|
29
|
+
## 2. Self-evolving genes
|
|
30
|
+
|
|
31
|
+
**The claim.** GABBE improves its own prompts over time through evolutionary optimization.
|
|
32
|
+
|
|
33
|
+
**What is real and working.** `evolve_prompts()` in `gabbe/brain.py` does perform Evolutionary
|
|
34
|
+
Prompt Optimization: it takes the current best prompt for a skill, asks an LLM to rewrite it more
|
|
35
|
+
effectively, and stores the rewrite as a new generation in a SQLite `genes` table. Selection
|
|
36
|
+
(epsilon-greedy, 80% exploit / 20% explore) and reward (+0.1 per successful use, capped at 1.0)
|
|
37
|
+
are working code. Over repeated runs, fitter prompts get used more.
|
|
38
|
+
|
|
39
|
+
**What is conceptual / aspirational.** This is a single-parent, LLM-rewrite mutation with a bandit
|
|
40
|
+
selector — there is **no crossover, no population culling, and no random genetic operators**, so
|
|
41
|
+
calling it "genetic/evolutionary" is a useful metaphor more than a literal genetic algorithm.
|
|
42
|
+
Fitness is monotonic and based on "did the call return something", so a prompt can reach maximum
|
|
43
|
+
fitness without ever having given good advice. Improving the reward to be outcome- or judge-based
|
|
44
|
+
is open work, not a shipped capability.
|
|
45
|
+
|
|
46
|
+
## 3. The runtime-agnostic markdown kit
|
|
47
|
+
|
|
48
|
+
**The claim.** The entire GABBE methodology — skills, personas, guides, templates — is portable
|
|
49
|
+
markdown that works inside any coding agent (Claude Code, Cursor, Copilot Chat, Windsurf, and so
|
|
50
|
+
on) with no runtime lock-in.
|
|
51
|
+
|
|
52
|
+
**What is real and working.** This is one of GABBE's strongest and most genuinely-true claims. The
|
|
53
|
+
skills, personas, and guides are plain structured markdown. An agent can follow them by reading
|
|
54
|
+
them; the optional `gabbe` Python CLI adds persistence, metrics, and enforcement but is not
|
|
55
|
+
required to use the methodology. The index files and frontmatter conventions make the kit
|
|
56
|
+
discoverable and selectable. Portability is real.
|
|
57
|
+
|
|
58
|
+
**What is conceptual / aspirational.** "Works in any agent" depends on the host agent actually
|
|
59
|
+
reading and honoring the markdown; weaker agents may ignore structure, skip gates, or not load the
|
|
60
|
+
right skills. The platform controls (budgets, hard stops, gates) are **markdown-enforced only**
|
|
61
|
+
unless the `gabbe` CLI is in the loop — i.e. in a pure-markdown runtime they are conventions an
|
|
62
|
+
agent is asked to follow, not guarantees the environment imposes. Treat cross-agent behavior as
|
|
63
|
+
"portable in principle, variable in practice".
|
|
64
|
+
|
|
65
|
+
## 4. The four-layer memory
|
|
66
|
+
|
|
67
|
+
**The claim.** GABBE gives agents durable, structured memory across sessions, organized in layers
|
|
68
|
+
(e.g. project state, continuity of past failures, episodic session snapshots, and an audit log).
|
|
69
|
+
|
|
70
|
+
**What is real and working.** The memory files exist and are used: `PROJECT_STATE.md` tracks the
|
|
71
|
+
current SDLC phase and last checkpoint, `CONTINUITY.md` records past failures to avoid repeating,
|
|
72
|
+
episodic `SESSION_SNAPSHOT` entries capture per-session state, and `AUDIT_LOG.md` is the minimum
|
|
73
|
+
authoritative trace. Preflight loads compact headers from these on activation, and checkpoints
|
|
74
|
+
write to them. This gives real cross-session continuity grounded in files on disk.
|
|
75
|
+
|
|
76
|
+
**What is conceptual / aspirational.** The "memory priming with decay" and "biologically-inspired
|
|
77
|
+
forgetting" described in the skills are a sensible retrieval *policy* expressed in markdown, not a
|
|
78
|
+
learned or statistically-decayed memory model — the agent is *asked* to weight by recency and
|
|
79
|
+
relevance, and honors that to the degree the host agent follows instructions. The richness of the
|
|
80
|
+
memory also depends on the agent diligently writing checkpoints; nothing forces it in a
|
|
81
|
+
pure-markdown runtime. So the structure is real; the discipline that fills it is convention.
|
|
82
|
+
|
|
83
|
+
## 5. The Loki swarm SDLC
|
|
84
|
+
|
|
85
|
+
**The claim.** "Loki mode" orchestrates a swarm of specialized personas through a phased software
|
|
86
|
+
lifecycle (S01–S10, plus Day-2 phases S11/S12), with gates and human checkpoints between phases.
|
|
87
|
+
|
|
88
|
+
**What is real and working.** The phase specifications (S01 Requirements through S10 Production
|
|
89
|
+
Deployment), the persona roster, the per-phase checkpoints that write to memory, and the
|
|
90
|
+
human-approval gates are all defined in the kit and are followed by an agent that loads them. The
|
|
91
|
+
phase validator even recognizes the extended Day-2 phases (S11/S12) as legitimate. The persona
|
|
92
|
+
specialization (each persona's Role / Does NOT / Context Scope / Outputs / RARV cycle) is concrete
|
|
93
|
+
and usable.
|
|
94
|
+
|
|
95
|
+
**What is conceptual / aspirational.** "Swarm" describes orchestrated *single-agent role-switching
|
|
96
|
+
and delegation guided by markdown*, not necessarily many autonomous agents running concurrently —
|
|
97
|
+
how much true parallelism happens depends entirely on the host runtime. The gates are as binding
|
|
98
|
+
as the host agent's willingness to honor them; without the `gabbe` CLI enforcing hard stops, a
|
|
99
|
+
phase gate is a strong instruction, not a hard barrier. The lifecycle is a genuinely well-specified
|
|
100
|
+
process; whether it executes as a literal multi-agent swarm depends on the environment it runs in.
|
|
101
|
+
|
|
102
|
+
## How to talk about GABBE honestly
|
|
103
|
+
|
|
104
|
+
- Lead with the runtime-agnostic markdown kit and the structured memory and SDLC — these are the
|
|
105
|
+
most real, most differentiated, and most defensible claims.
|
|
106
|
+
- Describe the brain and genes as "a self-improving prompt loop using an epsilon-greedy bandit
|
|
107
|
+
with a success-rate reward and LLM-driven mutation" — accurate and still interesting.
|
|
108
|
+
- Never say "active inference / free energy" as if it were computed; it is framing.
|
|
109
|
+
- Never say "guaranteed", "mathematically proven", or "best-in-class". GABBE's strength is a
|
|
110
|
+
coherent, portable methodology with a small real learning loop — that is worth describing
|
|
111
|
+
accurately rather than inflating.
|