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 +1,446 @@
|
|
|
1
|
+
# Loki Mode — Detailed SDLC Phase Specifications (S00–S13)
|
|
2
|
+
|
|
3
|
+
> Referenced by `agents/skills/brain/loki-mode.skill.md`. This holds the full
|
|
4
|
+
> per-phase detail (personas, tasks, outputs, gates, checkpoints) so the skill
|
|
5
|
+
> stays under the activation-size budget. Loaded on demand during orchestration.
|
|
6
|
+
>
|
|
7
|
+
> The core build loop is S01–S10. **S00 is the Day-0 strategy & discovery phase**
|
|
8
|
+
> that runs BEFORE S01, and **S11–S13 are the Day-2 phases** (operate, evolve,
|
|
9
|
+
> sunset) that run AFTER S10 once the system is live.
|
|
10
|
+
|
|
11
|
+
## Orchestration Loop — SDLC Phases (S00–S13)
|
|
12
|
+
|
|
13
|
+
### PHASE S00 — Strategy & Discovery (Day-0)
|
|
14
|
+
|
|
15
|
+
```
|
|
16
|
+
Personas: prod-research (lead), prod-pm
|
|
17
|
+
Tasks: prod-research:
|
|
18
|
+
- Run ideation-facilitation.skill (structured ideation, problem framing)
|
|
19
|
+
- Run user-research-synthesis.skill (synthesize interviews/signals → insights)
|
|
20
|
+
- Market & competitive scan; map the value chain with a Wardley map
|
|
21
|
+
- Draft the problem statement (the job-to-be-done, who hurts, why now)
|
|
22
|
+
prod-pm:
|
|
23
|
+
- Run opportunity-assessment.skill (size the opportunity, risks, bets)
|
|
24
|
+
- Define the North-Star metric + supporting HEART metrics
|
|
25
|
+
- Prioritize candidate bets with RICE (Reach·Impact·Confidence ÷ Effort)
|
|
26
|
+
- Frame go/no-go recommendation with explicit success criteria
|
|
27
|
+
|
|
28
|
+
Output: docs/discovery/PROBLEM_STATEMENT.md
|
|
29
|
+
docs/discovery/OPPORTUNITY_ASSESSMENT.md (RICE table, North-Star/HEART)
|
|
30
|
+
docs/discovery/MARKET_SCAN.md (competitive scan + Wardley map)
|
|
31
|
+
|
|
32
|
+
Gate: HUMAN GO/NO-GO REQUIRED — hard stop
|
|
33
|
+
Present discovery summary (problem, opportunity, metrics, RICE) to user.
|
|
34
|
+
Human decides go/no-go BEFORE S01 may start.
|
|
35
|
+
NO-GO → archive discovery, stop. GO → proceed to S01.
|
|
36
|
+
|
|
37
|
+
Checkpoint: sdlc-checkpoint.skill S00
|
|
38
|
+
- Write: agents/memory/episodic/SESSION_SNAPSHOT/S00_discovery.md
|
|
39
|
+
- Update: agents/memory/PROJECT_STATE.md → phase: S00, status: DONE
|
|
40
|
+
- Log: agents/memory/AUDIT_LOG.md → PHASE_TRANSITION: S00 complete (GO/NO-GO recorded)
|
|
41
|
+
```
|
|
42
|
+
|
|
43
|
+
### PHASE S01 — Requirements
|
|
44
|
+
|
|
45
|
+
```
|
|
46
|
+
Persona: prod-pm
|
|
47
|
+
Task: Write PRD.md using EARS syntax
|
|
48
|
+
Ask user clarifying questions (ambiguity layer)
|
|
49
|
+
Fill templates/product/PRD_TEMPLATE.md
|
|
50
|
+
Run ai-ethics-compliance.skill (Mandatory Bias Check)
|
|
51
|
+
IF CRITICAL (Health/Aviation):
|
|
52
|
+
- Engage prod-safety-engineer
|
|
53
|
+
- Run hazard-analysis.skill (FMEA/STPA)
|
|
54
|
+
Output: docs/requirements/PRD.md
|
|
55
|
+
docs/requirements/EARS_REQUIREMENTS.md
|
|
56
|
+
|
|
57
|
+
Gate: HUMAN APPROVAL REQUIRED
|
|
58
|
+
Present PRD to user → wait for explicit approval
|
|
59
|
+
User may request changes → loop until approved
|
|
60
|
+
|
|
61
|
+
Checkpoint: sdlc-checkpoint.skill S01
|
|
62
|
+
- Write: agents/memory/episodic/SESSION_SNAPSHOT/S01_requirements.md
|
|
63
|
+
- Update: agents/memory/PROJECT_STATE.md → phase: S01, status: DONE
|
|
64
|
+
- Log: agents/memory/AUDIT_LOG.md → PHASE_TRANSITION: S01 complete
|
|
65
|
+
```
|
|
66
|
+
|
|
67
|
+
### PHASE S02 — Architecture Design
|
|
68
|
+
|
|
69
|
+
```
|
|
70
|
+
Personas: prod-architect (lead), ops-security (threat review)
|
|
71
|
+
Tasks: prod-architect:
|
|
72
|
+
- Write PLAN.md using C4 model
|
|
73
|
+
- Define Error Handling Strategy (RFC 7807) using error-handling-strategy.skill
|
|
74
|
+
- Create docs/architecture/C4_ARCHITECTURE.md
|
|
75
|
+
- Write ADRs for all major decisions → docs/architecture/decisions/
|
|
76
|
+
ops-security:
|
|
77
|
+
- Review architecture for security concerns (adversarial)
|
|
78
|
+
- Run threat-model.skill on critical components
|
|
79
|
+
- Write THREAT_MODEL.md → docs/security/
|
|
80
|
+
|
|
81
|
+
Output: PLAN.md, C4_ARCHITECTURE.md, ADR-001+, THREAT_MODEL.md
|
|
82
|
+
|
|
83
|
+
Gate: HUMAN APPROVAL REQUIRED
|
|
84
|
+
Present: architecture summary + threat assessment + (Safety Case if Critical)
|
|
85
|
+
Wait for approval. Loop if changes requested.
|
|
86
|
+
|
|
87
|
+
Checkpoint: sdlc-checkpoint.skill S02
|
|
88
|
+
```
|
|
89
|
+
|
|
90
|
+
### PHASE S03 — Technical Specification
|
|
91
|
+
|
|
92
|
+
```
|
|
93
|
+
Persona: prod-tech-lead (with prod-architect review)
|
|
94
|
+
Tasks: - Fill templates/product/SPEC_TEMPLATE.md
|
|
95
|
+
- Define all API contracts (OpenAPI YAML)
|
|
96
|
+
- Define Event Topology (AsyncAPI) & Schemas (event-governance.skill)
|
|
97
|
+
- Define database schema changes
|
|
98
|
+
- Define Data Governance (Classification) & Access Control (RBAC)
|
|
99
|
+
- Define RPO/RTO targets
|
|
100
|
+
- Define testing strategy
|
|
101
|
+
Output: SPEC.md, docs/api/openapi.yaml, docs/db/schema-changes.md
|
|
102
|
+
|
|
103
|
+
Gate: HUMAN APPROVAL — lighter / may be async (the tech spec IS human-approved, but it
|
|
104
|
+
is not a hard *blocking* stop like the S01, S02, S07, S08 gates)
|
|
105
|
+
|
|
106
|
+
Checkpoint: sdlc-checkpoint.skill S03
|
|
107
|
+
```
|
|
108
|
+
|
|
109
|
+
### PHASE S04 — Task Decomposition
|
|
110
|
+
|
|
111
|
+
```
|
|
112
|
+
Persona: prod-tech-lead (with orch-planner)
|
|
113
|
+
Tasks: - Read SPEC.md + PLAN.md
|
|
114
|
+
- Decompose into atomic tasks (15-minute rule enforced)
|
|
115
|
+
- Fill templates/core/TASKS_TEMPLATE.md
|
|
116
|
+
- Assign each task to the appropriate eng-* persona
|
|
117
|
+
- Identify dependencies (DAG) AND Independent tasks
|
|
118
|
+
- **Parallelism**: Mark independent tasks with `[PARALLEL]` tag
|
|
119
|
+
|
|
120
|
+
- **Adaptive Check**:
|
|
121
|
+
- *If Plan Complexity > High*: Inject `S02_DEEP_RESEARCH` (Consult KIs / Web)
|
|
122
|
+
- *If Security Critical*: Inject `safety-scan` pre-check
|
|
123
|
+
|
|
124
|
+
Output: project/TASKS.md with T-NNN IDs, status: TODO, tags: [PARALLEL] if applicable
|
|
125
|
+
|
|
126
|
+
Gate: orch-judge reviews task decomposition:
|
|
127
|
+
- Are all tasks < 15 minutes?
|
|
128
|
+
- Does task coverage match SPEC acceptance criteria?
|
|
129
|
+
- Are parallel groups correctly identified?
|
|
130
|
+
|
|
131
|
+
Checkpoint: sdlc-checkpoint.skill S04
|
|
132
|
+
```
|
|
133
|
+
|
|
134
|
+
### PHASE S05 — Implementation
|
|
135
|
+
|
|
136
|
+
```
|
|
137
|
+
Persona: orch-planner (coordinator), eng-* (executors)
|
|
138
|
+
SCM discipline: apply configuration-management.skill (branching model, baselines,
|
|
139
|
+
reproducible builds) alongside git-workflow.skill throughout this phase.
|
|
140
|
+
|
|
141
|
+
Implementation Loop (repeats until all tasks DONE):
|
|
142
|
+
1. orch-planner analyzes `project/TASKS.md`:
|
|
143
|
+
- Identifies next batch of independent TODO tasks (Parallel Group)
|
|
144
|
+
- Or next sequential task if dependencies exist
|
|
145
|
+
|
|
146
|
+
2. **Context Retrieval (RAG)**:
|
|
147
|
+
- Invoke `knowledge-connect.skill` query: "How to implement [task keywords]?"
|
|
148
|
+
- Retrieve top 3 relevant snippets from `VECTOR_DB_CONFIG` source
|
|
149
|
+
- **On Failure**: Log warning "RAG Unavailable", attempt fallback to `filesystem` search, or proceed with available context only.
|
|
150
|
+
- Inject into task context
|
|
151
|
+
|
|
152
|
+
3. **Delegation (A2A Check)**:
|
|
153
|
+
- Is this task for an external agent? (e.g., "Ask Security Swarm")
|
|
154
|
+
- YES -> Invoke `agent-interop.skill` -> Delegate -> Wait -> generic result
|
|
155
|
+
- NO -> Assign to internal `eng-*` persona
|
|
156
|
+
|
|
157
|
+
4. **Execution (Parallel/Batch)**:
|
|
158
|
+
- For each task in current batch (concurrently if model supports):
|
|
159
|
+
|
|
160
|
+
assigned eng-* persona executes RARV Cycle:
|
|
161
|
+
REASON: Load task context + AGENTS.md + CONTINUITY.md + RAG Context
|
|
162
|
+
Write mini-plan before touching files
|
|
163
|
+
|
|
164
|
+
ACT: Write failing test (TDD Red — MANDATORY)
|
|
165
|
+
Verify test fails before implementing
|
|
166
|
+
Run `safety-scan.skill` (Guardrail)
|
|
167
|
+
Implement minimal code (Apply secure-coding.skill triggers)
|
|
168
|
+
Update project/TASKS.md: status → IN_PROGRESS
|
|
169
|
+
|
|
170
|
+
REFLECT: Library-First? Layer boundaries? Security inputs? PII in logs?
|
|
171
|
+
|
|
172
|
+
VERIFY: Run: [test command] → must be GREEN
|
|
173
|
+
Run: [typecheck] → zero errors
|
|
174
|
+
Run: [lint] → zero errors
|
|
175
|
+
Run: agentic-linter → no violations
|
|
176
|
+
|
|
177
|
+
5. **Batch Result Processing**:
|
|
178
|
+
- If VERIFY passes:
|
|
179
|
+
- Update project/TASKS.md: status → DONE
|
|
180
|
+
- Write audit-trail.skill entry: TASK_DONE
|
|
181
|
+
|
|
182
|
+
- If VERIFY fails:
|
|
183
|
+
- **Quick Check**: Invoke `ci-autofix` (Autonomous Remediation)
|
|
184
|
+
- If FIXED -> Proceed to DONE logic
|
|
185
|
+
- **Dynamic Optimization**: Invoke `self-heal.skill` (max 5 attempts)
|
|
186
|
+
- *Input*: Error log + Task Context + RAG Context
|
|
187
|
+
- *Output*: Fix applied OR Escalation
|
|
188
|
+
- **Meta-Optimization**: If `self-heal` FAILS repeatedly (>3x):
|
|
189
|
+
- Invoke `meta-optimize.skill` (Rewrite the failing skill/prompt)
|
|
190
|
+
- Log: "Self-Evolution Triggered for [Skill Name]"
|
|
191
|
+
- If escalated:
|
|
192
|
+
- orch-coordinator logs HUMAN_ESCALATION
|
|
193
|
+
- task status → BLOCKED
|
|
194
|
+
|
|
195
|
+
6. Repeat until all tasks DONE
|
|
196
|
+
|
|
197
|
+
Checkpoint: sdlc-checkpoint.skill S05
|
|
198
|
+
(Save after every batch to prevent state loss)
|
|
199
|
+
```
|
|
200
|
+
|
|
201
|
+
### PHASE S06 — Testing & Quality
|
|
202
|
+
|
|
203
|
+
```
|
|
204
|
+
Persona: eng-qa (lead), orch-judge (validator)
|
|
205
|
+
|
|
206
|
+
eng-qa Tasks:
|
|
207
|
+
- Run full test suite → verify all green
|
|
208
|
+
- Check coverage ≥ 99% per module
|
|
209
|
+
- Run integration test suite
|
|
210
|
+
- Identify any missing test scenarios from EARS acceptance criteria
|
|
211
|
+
- Fill any gaps via tdd-cycle.skill
|
|
212
|
+
- Score probabilistic quality via eval-driven-development.skill; interpret benchmark/
|
|
213
|
+
A-B results with empirical-methods.skill (effect size, significance — not just averages)
|
|
214
|
+
|
|
215
|
+
orch-judge Tasks:
|
|
216
|
+
- Quality Gate Check (orch-judge's 7-gate system, extended here with E2E + EARS):
|
|
217
|
+
Gate 1: Lint/Syntax → ESLint/PHP-CS-Fixer → zero errors
|
|
218
|
+
Gate 2: Type Safety → tsc/PHPStan → zero errors
|
|
219
|
+
Gate 3: Coverage → Vitest/Pest → ≥ 99%
|
|
220
|
+
Gate 4: Integration → Docker Compose → all green
|
|
221
|
+
Gate 5: Security → dependency-security.skill → no critical vulnerabilities
|
|
222
|
+
Gate 6: Complexity → Cyclomatic < 10 for all functions
|
|
223
|
+
Gate 7: Architecture → architecture-governance.skill → no layer violations (Fitness Functions)
|
|
224
|
+
Gate 8: E2E → e2e-test-suite (Playwright/Cypress) → all critical flows PASS
|
|
225
|
+
Gate 9: EARS → All acceptance criteria have passing tests
|
|
226
|
+
|
|
227
|
+
(Numbering note: Gates 1–6 + EARS are orch-judge's canonical 7-gate set — EARS is
|
|
228
|
+
orch-judge's Gate 7, shown here as Gate 9; Loki adds Architecture + E2E as the two
|
|
229
|
+
extra checks. Same checks, Loki-local numbering. orch-judge.md remains the 7-gate authority.)
|
|
230
|
+
If any gate fails: assign remediation task to eng-* persona → loop
|
|
231
|
+
|
|
232
|
+
Gate: All 9 gates PASS
|
|
233
|
+
|
|
234
|
+
Checkpoint: sdlc-checkpoint.skill S06
|
|
235
|
+
```
|
|
236
|
+
|
|
237
|
+
### PHASE S07 — Security Review
|
|
238
|
+
|
|
239
|
+
```
|
|
240
|
+
Personas: ops-security (adversarial), eng-qa (verification)
|
|
241
|
+
|
|
242
|
+
ops-security Tasks:
|
|
243
|
+
- security-audit.skill → OWASP Top 10 full scan
|
|
244
|
+
- threat-model.skill → verify mitigations implemented
|
|
245
|
+
- privacy-audit.skill → PII scan (if applicable)
|
|
246
|
+
- ai-safety-guardrails.skill → Verify protection against prompt injection
|
|
247
|
+
- compliance-review.skill → if regulated (SOC2/PCI/HIPAA)
|
|
248
|
+
- Fill: templates/security/SECURITY_CHECKLIST.md
|
|
249
|
+
- Document all findings in: docs/security/SECURITY_REVIEW.md
|
|
250
|
+
|
|
251
|
+
Acceptance:
|
|
252
|
+
- SECURITY_CHECKLIST.md: all items ✓
|
|
253
|
+
- No HIGH severity open findings
|
|
254
|
+
- All MEDIUM findings have documented mitigations or accepted risks
|
|
255
|
+
|
|
256
|
+
Gate: SECURITY_CHECKLIST passed + no critical CVEs
|
|
257
|
+
|
|
258
|
+
Checkpoint: sdlc-checkpoint.skill S07
|
|
259
|
+
```
|
|
260
|
+
|
|
261
|
+
### PHASE S08 — Human Review
|
|
262
|
+
|
|
263
|
+
```
|
|
264
|
+
Personas: prod-tech-lead (review prep), orch-judge (EARS compliance), prod-ethicist (safety)
|
|
265
|
+
Professional conduct: prod-ethicist applies professional-practice.skill (ACM/IEEE-CS
|
|
266
|
+
Code of Ethics) for the human/ethics dimension of the review.
|
|
267
|
+
|
|
268
|
+
Prep:
|
|
269
|
+
- prod-tech-lead generates review summary:
|
|
270
|
+
- What was built (linked to SPEC acceptance criteria)
|
|
271
|
+
- All ADRs made during implementation
|
|
272
|
+
- All security findings and resolutions
|
|
273
|
+
- Test coverage report
|
|
274
|
+
- Any known limitations or deferred tech debt
|
|
275
|
+
- orch-judge: final EARS compliance check
|
|
276
|
+
- All requirements addressed? (DONE)
|
|
277
|
+
- Any "Nice to Have" deferred with documented reason?
|
|
278
|
+
|
|
279
|
+
- **Double Verification Protocol**:
|
|
280
|
+
1. orch-judge verifies logic & specs (Automated)
|
|
281
|
+
2. prod-tech-lead verifies code quality & patterns (Human-Proxy)
|
|
282
|
+
3. prod-ethicist verifies final safety check (Safety)
|
|
283
|
+
- Run **core/final-review.skill** (independent expert pass: correctness, security,
|
|
284
|
+
observability, spec/golden-thread, cost, simplicity) — must be SHIP before the human gate.
|
|
285
|
+
|
|
286
|
+
Gate: DOUBLE VERIFICATION + HUMAN APPROVAL REQUIRED
|
|
287
|
+
This is a mandatory stop — no autonomous continuation.
|
|
288
|
+
Human may request changes → loop back to S05 for specific tasks.
|
|
289
|
+
|
|
290
|
+
Checkpoint: sdlc-checkpoint.skill S08
|
|
291
|
+
```
|
|
292
|
+
|
|
293
|
+
### PHASE S09 — Staging Deployment
|
|
294
|
+
|
|
295
|
+
```
|
|
296
|
+
Persona: ops-devops (lead), eng-qa (smoke tests)
|
|
297
|
+
|
|
298
|
+
ops-devops Tasks:
|
|
299
|
+
- deployment.skill → staging environment
|
|
300
|
+
- Verify CI/CD pipeline passes
|
|
301
|
+
- Run smoke tests against staging
|
|
302
|
+
|
|
303
|
+
eng-qa Tasks:
|
|
304
|
+
- Verify critical user flows work in staging
|
|
305
|
+
- Verify Restore from Backup (backup-recovery.skill) — Mandatory
|
|
306
|
+
- Verify DLQ Consumption & Replay (queue-management.skill)
|
|
307
|
+
- Check monitoring/alerting is configured
|
|
308
|
+
- Run performance-audit.skill against staging
|
|
309
|
+
|
|
310
|
+
Gate: All smoke tests GREEN + monitoring verified
|
|
311
|
+
(If Critical: Failover Test PASS via reliability-engineering.skill)
|
|
312
|
+
|
|
313
|
+
Checkpoint: sdlc-checkpoint.skill S09
|
|
314
|
+
```
|
|
315
|
+
|
|
316
|
+
### PHASE S10 — Production Deployment
|
|
317
|
+
|
|
318
|
+
```
|
|
319
|
+
Persona: ops-devops (lead), ops-sre (reliability check)
|
|
320
|
+
|
|
321
|
+
Pre-deployment:
|
|
322
|
+
- ops-sre: verify rollback plan is documented
|
|
323
|
+
- ops-sre: verify monitoring/alerting will cover new features
|
|
324
|
+
- ops-sre: confirm SLO thresholds are set
|
|
325
|
+
|
|
326
|
+
Deployment:
|
|
327
|
+
- deployment.skill → production
|
|
328
|
+
- Feature flags (if applicable): enable for canary %
|
|
329
|
+
- Monitor for 15 minutes after deployment
|
|
330
|
+
|
|
331
|
+
Post-deployment:
|
|
332
|
+
- ops-monitor: verify dashboards show normal metrics
|
|
333
|
+
- Write deployment record to AUDIT_LOG.md
|
|
334
|
+
|
|
335
|
+
Gate: Production healthy for 15+ minutes
|
|
336
|
+
|
|
337
|
+
Checkpoint: sdlc-checkpoint.skill S10
|
|
338
|
+
- Update PROJECT_STATE.md: phase: S10, status: DONE (build loop complete; Day-2 begins)
|
|
339
|
+
- Write completion summary to AUDIT_LOG.md
|
|
340
|
+
- Archive SESSION_SNAPSHOT: S10_production.md
|
|
341
|
+
```
|
|
342
|
+
|
|
343
|
+
### PHASE S11 — Operate & Maintain (Day-2)
|
|
344
|
+
|
|
345
|
+
```
|
|
346
|
+
Personas: ops-sre (lead), ops-monitor, ops-incident, ops-cost
|
|
347
|
+
Tasks: ops-sre:
|
|
348
|
+
- Run observability-stack-setup.skill (metrics/logs/traces, dashboards, SLOs)
|
|
349
|
+
- Run runbook-authoring.skill → fill templates/ops/RUNBOOK_TEMPLATE.md per service
|
|
350
|
+
- Define on-call rotation; verify error budget policy against SLOs
|
|
351
|
+
- Run dependency-lifecycle.skill (patch cadence, dependency upgrades, CVE triage)
|
|
352
|
+
- Use feature-flag-management.skill to govern live flags (rollout/rollback)
|
|
353
|
+
ops-monitor:
|
|
354
|
+
- Watch dashboards/alerts; confirm SLO adherence; flag burn-rate breaches
|
|
355
|
+
ops-incident:
|
|
356
|
+
- Run incident response per runbook; capture timeline for blameless review (→ S12)
|
|
357
|
+
ops-cost:
|
|
358
|
+
- Monitor cloud/API spend vs budget; flag cost regressions and savings
|
|
359
|
+
|
|
360
|
+
Output: docs/ops/RUNBOOKS/ (one per service)
|
|
361
|
+
docs/ops/SLO_REPORT.md (SLO adherence + error-budget burn)
|
|
362
|
+
docs/ops/DEPENDENCY_STATUS.md (patch/upgrade log, open CVEs)
|
|
363
|
+
|
|
364
|
+
Gate: SLOs met + error budget healthy + no open critical CVEs + spend within budget
|
|
365
|
+
(Recurring/steady-state phase — re-enters on every operational cycle.)
|
|
366
|
+
|
|
367
|
+
Checkpoint: sdlc-checkpoint.skill S11
|
|
368
|
+
- Write: agents/memory/episodic/SESSION_SNAPSHOT/S11_operate.md
|
|
369
|
+
- Update: agents/memory/PROJECT_STATE.md → phase: S11, status: IN_PROGRESS (Day-2)
|
|
370
|
+
- Log: agents/memory/AUDIT_LOG.md → operational cycle recorded
|
|
371
|
+
```
|
|
372
|
+
|
|
373
|
+
### PHASE S12 — Evolve & Continuously Improve
|
|
374
|
+
|
|
375
|
+
```
|
|
376
|
+
Personas: prod-product-ops (lead), prod-pm
|
|
377
|
+
Tasks: prod-product-ops:
|
|
378
|
+
- Run retrospective.skill (blameless) → fill templates/core/PROJECT_RETROSPECTIVE_TEMPLATE.md
|
|
379
|
+
- Review DORA + SPACE metrics; identify delivery/health bottlenecks
|
|
380
|
+
- Plan tech-debt paydown; feed prioritized items back into S04 decomposition
|
|
381
|
+
- Govern feature-flag lifecycle with feature-flag-management.skill (retire stale flags)
|
|
382
|
+
prod-pm:
|
|
383
|
+
- Run product-analytics.skill (funnels, retention, North-Star movement)
|
|
384
|
+
- Design A/B experiments → fill templates/product/EXPERIMENT_PLAN_TEMPLATE.md
|
|
385
|
+
- Translate insights into prioritized iterations (loop back to S00/S01 as needed)
|
|
386
|
+
|
|
387
|
+
Output: docs/evolve/RETROSPECTIVE.md (blameless, action items)
|
|
388
|
+
docs/evolve/EXPERIMENTS/ (A/B plans + readouts)
|
|
389
|
+
docs/evolve/IMPROVEMENT_BACKLOG.md (tech-debt + analytics-driven bets)
|
|
390
|
+
|
|
391
|
+
Gate: Retrospective actions logged + experiments have a decision (ship/iterate/kill)
|
|
392
|
+
+ DORA/SPACE reviewed. Improvements re-enter the loop (→ S00/S01/S04).
|
|
393
|
+
|
|
394
|
+
Checkpoint: sdlc-checkpoint.skill S12
|
|
395
|
+
- Write: agents/memory/episodic/SESSION_SNAPSHOT/S12_evolve.md
|
|
396
|
+
- Update: agents/memory/PROJECT_STATE.md → phase: S12, status: IN_PROGRESS (Day-2)
|
|
397
|
+
- Log: agents/memory/AUDIT_LOG.md → improvement cycle recorded
|
|
398
|
+
```
|
|
399
|
+
|
|
400
|
+
### PHASE S13 — Decommission & Sunset
|
|
401
|
+
|
|
402
|
+
```
|
|
403
|
+
Personas: prod-pm (lead), ops-sre, biz-legal
|
|
404
|
+
Tasks: prod-pm:
|
|
405
|
+
- Run decommission-sunset.skill → fill templates/ops/DECOMMISSION_PLAN_TEMPLATE.md
|
|
406
|
+
- Define deprecation policy + timeline; plan user comms / migration paths
|
|
407
|
+
ops-sre:
|
|
408
|
+
- Execute data retention/migration plan; archive data + final backups
|
|
409
|
+
- Tear down infra safely (DNS, secrets, monitors); confirm no live dependents
|
|
410
|
+
biz-legal:
|
|
411
|
+
- Wind down licenses/contracts/vendor commitments; confirm compliance/retention
|
|
412
|
+
|
|
413
|
+
Output: docs/sunset/DECOMMISSION_PLAN.md
|
|
414
|
+
docs/sunset/DATA_RETENTION_AND_MIGRATION.md
|
|
415
|
+
docs/sunset/USER_COMMS.md (deprecation notices, migration guidance)
|
|
416
|
+
|
|
417
|
+
Gate: Deprecation policy approved + data retained/migrated/archived per policy
|
|
418
|
+
+ users notified + license/contract wind-down confirmed.
|
|
419
|
+
|
|
420
|
+
Checkpoint: sdlc-checkpoint.skill S13
|
|
421
|
+
- THIS IS THE FINAL LIFECYCLE CHECKPOINT
|
|
422
|
+
- Write: agents/memory/episodic/SESSION_SNAPSHOT/S13_sunset.md
|
|
423
|
+
- Update: agents/memory/PROJECT_STATE.md → phase: S13, status: DONE (system retired)
|
|
424
|
+
- Log: agents/memory/AUDIT_LOG.md → DECOMMISSION complete
|
|
425
|
+
```
|
|
426
|
+
|
|
427
|
+
## New mid-phase quality gates
|
|
428
|
+
|
|
429
|
+
These are lightweight gates inserted *between* existing phases. They do not renumber any
|
|
430
|
+
phase; they are checkpoints the orchestrator runs before advancing the adjacent phase.
|
|
431
|
+
|
|
432
|
+
- **S02.5 — Cost & Feasibility gate** (between S02 and S03): run financial-governance.skill
|
|
433
|
+
to validate the proposed architecture against budget/unit-economics before committing to a
|
|
434
|
+
spec. Gate: projected cost within approved envelope, or human-approved exception.
|
|
435
|
+
- **S04.5 — Parallelism / Dependency-feasibility gate** (between S04 and S05): build the task
|
|
436
|
+
dependency graph by filling templates/core/DEPENDENCY_GRAPH_TEMPLATE.md; verify the
|
|
437
|
+
`[PARALLEL]` groups are truly independent (no hidden edges, no cycles). Gate: DAG is acyclic
|
|
438
|
+
and parallel batches are conflict-free before implementation starts.
|
|
439
|
+
- **S06.5 — Performance-regression gate** (after S06): run the benchmark suite and compare
|
|
440
|
+
against the recorded baseline. Gate: no critical latency/throughput regression vs baseline,
|
|
441
|
+
or a human-accepted, documented exception.
|
|
442
|
+
- **S07.5 — Sustainability gate** (after S07): produce a green-software report (energy/carbon
|
|
443
|
+
per request, idle waste, efficiency hotspots). Gate: sustainability report reviewed; no
|
|
444
|
+
unmitigated efficiency red flags.
|
|
445
|
+
|
|
446
|
+
---
|
|
@@ -0,0 +1,38 @@
|
|
|
1
|
+
# Green Software Guide
|
|
2
|
+
|
|
3
|
+
## Overview
|
|
4
|
+
The software industry contributes to roughly 2-4% of global greenhouse gas emissions (on par with the aviation industry). Green software engineering is an emerging discipline aimed at building applications that are carbon-efficient from day one. This guide serves as the foundation for the `green-software` skill.
|
|
5
|
+
|
|
6
|
+
## 1. The Core Metrics
|
|
7
|
+
You cannot improve what you cannot measure. Green software relies on the **Software Carbon Intensity (SCI) Specification**, developed by the Green Software Foundation.
|
|
8
|
+
|
|
9
|
+
### The Algorithm: `SCI = ((E * I) + M) per R`
|
|
10
|
+
- **E (Energy)**: Energy consumed by the software in kWh.
|
|
11
|
+
- **I (Carbon Intensity)**: Grams of carbon emitted per kWh of electricity (dependent on datacenter location and time of day).
|
|
12
|
+
- **M (Embodied Carbon)**: The carbon debt of the hardware resources allocated to running the software.
|
|
13
|
+
- **R (Functional Unit)**: How the software scales (e.g., per user, per API request, per video minute).
|
|
14
|
+
|
|
15
|
+
*Goal: Drive the SCI score down to zero.*
|
|
16
|
+
|
|
17
|
+
## 2. Six Principles of Green Software Engineering
|
|
18
|
+
|
|
19
|
+
1. **Carbon Efficiency**: Emit the least amount of carbon possible.
|
|
20
|
+
2. **Energy Efficiency**: Consume the least amount of electricity possible.
|
|
21
|
+
3. **Carbon Awareness**: Run workloads when and where the electricity is greenest. Use APIs from groups like *Electricity Maps* or *WattTime* to predict carbon intensity.
|
|
22
|
+
4. **Hardware Efficiency**: Use the least amount of embodied carbon possible. Maximize the lifespan of the hardware your application runs on (e.g., don't drop support for 3-year-old operating systems unnecessarily).
|
|
23
|
+
5. **Measurement**: Measure carbon using the SCI.
|
|
24
|
+
6. **Climate Commitments**: Understand the reduction mechanism (e.g., offsetting vs. absolute reduction).
|
|
25
|
+
|
|
26
|
+
## 3. Practical Architecture Patterns
|
|
27
|
+
|
|
28
|
+
### Demand Shaping
|
|
29
|
+
Instead of auto-scaling servers to meet peak demand at all costs (which often requires keeping idle "warm" servers running), Demand Shaping alters the behavior of the application based on grid carbon intensity.
|
|
30
|
+
- *Examples*: A video streaming app defaults to 720p instead of 4K when the local grid is powered by coal. A background analytics job pauses until the wind is blowing.
|
|
31
|
+
|
|
32
|
+
### Sustainable Web Design
|
|
33
|
+
- **Dark Mode**: OLED screens use significantly less battery power when displaying true black (`#000000`).
|
|
34
|
+
- **Media Optimization**: Serve lazy-loaded, WebP/AVIF images.
|
|
35
|
+
- **Bundle Size**: Minify JavaScript and CSS. Every byte sent over the network consumes energy across dozens of switches and routers.
|
|
36
|
+
|
|
37
|
+
## 4. How to Use the Green Software Skill
|
|
38
|
+
Invoke the `green-software` skill during the PR/Review phase or during an Architectural Audit. The agent will analyze your compute patterns and generate recommendations prioritizing energy and carbon efficiency using the `GREEN_SOFTWARE_REPORT_TEMPLATE.md`.
|
|
@@ -0,0 +1,29 @@
|
|
|
1
|
+
# Sustainability & ESG Engineering Guide
|
|
2
|
+
|
|
3
|
+
## 1. Introduction
|
|
4
|
+
Sustainability in software engineering goes beyond recycling office paper; it concerns the direct energy consumption of our algorithms, the embodied carbon of the servers we rent, and the social impact of the software we deploy. This guide aligns engineering with Corporate ESG (Environmental, Social, Governance) mandates.
|
|
5
|
+
|
|
6
|
+
## 2. The Three Pillars of Green Software
|
|
7
|
+
|
|
8
|
+
### Energy Efficiency
|
|
9
|
+
Software consumes electricity. The goal is to consume less electricity per logical operation.
|
|
10
|
+
- **Algorithmic Efficiency**: Big-O notation matters for the planet. An O(n^2) algorithm wastes exponentially more energy than an O(n log n) one at scale.
|
|
11
|
+
- **Data Efficiency**: Transferring data across networks requires physical routers and switches to work harder. Compress assets, use smaller image formats (WebP/AVIF), and prune unused JSON payload fields.
|
|
12
|
+
|
|
13
|
+
### Hardware Efficiency
|
|
14
|
+
The manufacturing and disposal of servers (Embodied Carbon) often outweighs the electricity they use over their lifetime.
|
|
15
|
+
- **High Utilization**: A server running at 10% capacity consumes almost the same baseline power as one at 80%. Consolidate workloads using Kubernetes, Docker, or VMs.
|
|
16
|
+
- **Lifespan Extension**: Design software that functions well on older hardware (e.g., older Android devices, 5-year-old laptops) to delay e-waste.
|
|
17
|
+
|
|
18
|
+
### Carbon Awareness
|
|
19
|
+
Electricity grid greenness fluctuates based on weather (wind/solar) and time of day.
|
|
20
|
+
- **Spatial Shifting**: Deploy workloads to cloud regions powered by renewables (e.g., Iceland, specific AWS/GCP green zones).
|
|
21
|
+
- **Temporal Shifting**: Schedule heavy, non-urgent batch jobs (like ML training or DB backups) during periods when the local grid relies on excess renewable energy.
|
|
22
|
+
|
|
23
|
+
## 3. Social & Governance (The S and G in ESG)
|
|
24
|
+
- **Accessibility (A11y)**: Sustainable software must be usable by all. Ensure WCAG compliance so users with disabilities are not excluded.
|
|
25
|
+
- **Algorithmic Bias**: Audit AI or sorting algorithms to ensure they do not discriminate against minorities or disadvantaged groups.
|
|
26
|
+
- **Data Minimization**: Only collect what you need. Less data is better for privacy (Governance) and requires less storage (Environmental).
|
|
27
|
+
|
|
28
|
+
## 4. Agentic Workflow
|
|
29
|
+
Use the `sustainability-checks` skill to have an agent continuously audit PRs for energy waste. The agent will output a `GREEN_SOFTWARE_REPORT_TEMPLATE.md`.
|
|
@@ -0,0 +1,98 @@
|
|
|
1
|
+
# Guide: AI Risk Standards Map
|
|
2
|
+
<!-- Mapping GABBE capabilities to named AI-risk standards: OWASP LLM Top 10, NIST AI RMF, MITRE ATLAS, ISO/IEC 42001, EU AI Act -->
|
|
3
|
+
|
|
4
|
+
---
|
|
5
|
+
|
|
6
|
+
## 1. Why This Map Exists
|
|
7
|
+
|
|
8
|
+
GABBE makes governance claims about agentic and LLM-driven development. To keep those claims grounded — the same way ADD 3.0 and ATAM ground architecture decisions in named methods rather than opinion — this guide maps GABBE's capabilities (skills, gates, personas, and engine controls) onto the recognized AI-risk standards.
|
|
9
|
+
|
|
10
|
+
Each mapping answers one question per risk: *which concrete GABBE control addresses this?* Where a real control exists it is named in backticks. This is a coverage map, not a compliance certificate (see the honesty note at the end).
|
|
11
|
+
|
|
12
|
+
## 2. OWASP Top 10 for LLM Applications (2025)
|
|
13
|
+
|
|
14
|
+
Every row names at least one GABBE control.
|
|
15
|
+
|
|
16
|
+
| OWASP ID | Risk | GABBE control (skill / gate / persona) |
|
|
17
|
+
|---|---|---|
|
|
18
|
+
| LLM01 | Prompt Injection | `prompt-injection-defense.skill` (lethal-trifecta + rule-of-two, dual-LLM quarantine, spotlighting), `ai-safety-guardrails.skill` input rails, human-approval gates on trifecta-complete actions |
|
|
19
|
+
| LLM02 | Sensitive Information Disclosure | `output-validation.skill` (PII masking before external APIs and logs), `secrets-management.skill`, `ai-safety-guardrails.skill` PII scrubbing |
|
|
20
|
+
| LLM03 | Supply Chain | `dependency-security.skill` (SBOM, SCA, vulnerability patching), `integrity-check.skill` (artifact/provenance integrity) |
|
|
21
|
+
| LLM04 | Data & Model Poisoning | `integrity-check.skill`, `rag-evaluation.skill` (retrieval quality and source vetting), `threat-model.skill` for poisoning surfaces |
|
|
22
|
+
| LLM05 | Improper Output Handling | `output-validation.skill` (schema validation + retry-on-failure, encoding before side-effecting sinks), the fail-closed gateway |
|
|
23
|
+
| LLM06 | Excessive Agency | the policy engine / fail-closed gateway, human-approval gates, `prompt-injection-defense.skill` rule-of-two capability limits, least-privilege tokens |
|
|
24
|
+
| LLM07 | System Prompt Leakage | `prompt-injection-defense.skill` (no-secrets-in-system-prompt, deny verbatim reflection), `ai-safety-guardrails.skill` output rails |
|
|
25
|
+
| LLM08 | Vector & Embedding Weaknesses | `rag-evaluation.skill` (embedding/retrieval evaluation, source provenance), `threat-model.skill` for retrieval-boundary threats |
|
|
26
|
+
| LLM09 | Misinformation | `rag-evaluation.skill` (grounding/faithfulness checks), `output-validation.skill` (structure ≠ truth caveat), human-approval gates for high-impact claims |
|
|
27
|
+
| LLM10 | Unbounded Consumption | the budget / hardstop caps, `output-validation.skill` bounded retry loop, the policy engine / fail-closed gateway, loop-detection guards |
|
|
28
|
+
|
|
29
|
+
## 3. NIST AI RMF (and the Generative AI Profile)
|
|
30
|
+
|
|
31
|
+
The AI Risk Management Framework organizes risk work into five functions. GABBE coverage:
|
|
32
|
+
|
|
33
|
+
- **Govern**: persona roles (prod-ethicist, ops-security), the policy engine and fail-closed gateway as the organizational control plane; `ai-safety-guardrails.skill` as the standing safety posture.
|
|
34
|
+
- **Map**: `threat-model.skill` (STRIDE surfaces) and `prompt-injection-defense.skill` (trifecta/surface enumeration) identify context and risk.
|
|
35
|
+
- **Measure**: `rag-evaluation.skill`, `output-validation.skill` validation reports, and the cognitive-testing invariant/convergence reports quantify behavior.
|
|
36
|
+
- **Manage**: `dependency-security.skill`, `secrets-management.skill`, `integrity-check.skill`, human-approval gates, and the budget/hardstop caps act on prioritized risk.
|
|
37
|
+
- **Monitor**: input/output rails logging in `ai-safety-guardrails.skill`, egress filtering and guard-trigger telemetry from `prompt-injection-defense.skill`.
|
|
38
|
+
|
|
39
|
+
The **Generative AI Profile** (NIST AI 600-1) overlays GenAI-specific risks (confabulation, data privacy, harmful output); GABBE addresses these via `output-validation.skill`, `rag-evaluation.skill`, and the `ai-safety-guardrails.skill` rails taxonomy.
|
|
40
|
+
|
|
41
|
+
## 4. MITRE ATLAS (Adversarial Threat Landscape for AI Systems)
|
|
42
|
+
|
|
43
|
+
ATLAS catalogs adversary tactics against AI. Indicative GABBE coverage by tactic:
|
|
44
|
+
|
|
45
|
+
- **Reconnaissance / Resource Development**: `threat-model.skill` enumerates exposed surfaces before they are probed.
|
|
46
|
+
- **Initial Access (LLM Prompt Injection)**: `prompt-injection-defense.skill` direct + indirect injection defenses, input rails.
|
|
47
|
+
- **ML Supply Chain Compromise**: `dependency-security.skill`, `integrity-check.skill`.
|
|
48
|
+
- **Defense Evasion / LLM Jailbreak**: layered controls in `prompt-injection-defense.skill` and `ai-safety-guardrails.skill` (no single classifier trusted).
|
|
49
|
+
- **Exfiltration (via inference / tool feedback)**: egress filtering and `output-validation.skill` PII masking, human-approval gates on trifecta-complete actions.
|
|
50
|
+
- **Impact (Denial of ML Service / cost)**: the budget/hardstop caps and loop-detection guards.
|
|
51
|
+
|
|
52
|
+
## 5. ISO/IEC 42001 (AI Management System)
|
|
53
|
+
|
|
54
|
+
ISO/IEC 42001 specifies an Artificial Intelligence Management System (AIMS) — policy, roles, risk treatment, and continual improvement. GABBE supports the management-system intent through:
|
|
55
|
+
|
|
56
|
+
- **Policy & roles**: the policy engine, fail-closed gateway, and security/ethicist personas provide documented, enforced controls and accountable ownership.
|
|
57
|
+
- **Risk assessment & treatment**: `threat-model.skill` and `prompt-injection-defense.skill` for assessment; `output-validation.skill`, `dependency-security.skill`, `secrets-management.skill`, and `integrity-check.skill` for treatment.
|
|
58
|
+
- **Operational controls & monitoring**: `ai-safety-guardrails.skill` rails, budget/hardstop caps, and human-approval gates.
|
|
59
|
+
- **Continual improvement**: evaluation feedback from `rag-evaluation.skill` and the cognitive-testing reports feeds control refinement.
|
|
60
|
+
|
|
61
|
+
GABBE provides controls that *support* an AIMS; it does not constitute an AIMS by itself.
|
|
62
|
+
|
|
63
|
+
## 6. EU AI Act (Obligations Relevant to Agentic Dev Tooling)
|
|
64
|
+
|
|
65
|
+
For agentic developer tooling, the most relevant EU AI Act themes and GABBE's coverage:
|
|
66
|
+
|
|
67
|
+
- **Transparency**: provenance tracking and validation reports (`output-validation.skill`, `prompt-injection-defense.skill`) make agent actions auditable; document AI involvement in generated artifacts.
|
|
68
|
+
- **Risk management & robustness**: `threat-model.skill`, layered injection defenses, and the fail-closed gateway support documented risk management for higher-risk uses.
|
|
69
|
+
- **Data governance & privacy**: PII masking in `output-validation.skill` and `secrets-management.skill` align with data-protection obligations.
|
|
70
|
+
- **Human oversight**: human-approval gates and the rule-of-two capability limits in `prompt-injection-defense.skill` keep a human in the loop for high-impact actions.
|
|
71
|
+
- **Logging & traceability**: rails logging, egress telemetry, and `integrity-check.skill` support record-keeping expectations.
|
|
72
|
+
|
|
73
|
+
General-purpose / foundation-model obligations apply to the underlying models GABBE orchestrates, not to GABBE's controls themselves.
|
|
74
|
+
|
|
75
|
+
## 7. Adjacent & Lifecycle Standards (2025-2026 landscape)
|
|
76
|
+
|
|
77
|
+
Beyond the five mapped frameworks above, these standards round out a defensible
|
|
78
|
+
AI-governance posture. GABBE aligns to them by intent; none implies certification.
|
|
79
|
+
|
|
80
|
+
| Standard | Scope | GABBE alignment |
|
|
81
|
+
|---|---|---|
|
|
82
|
+
| **ISO/IEC 5338:2023** | AI system **life-cycle processes** (the ADLC anchor) | the S00–S13 lifecycle + memory/checkpoint model structure AI lifecycle activities |
|
|
83
|
+
| **ISO/IEC 23894:2023** | AI **risk management** guidance | `threat-model.skill`, `ai-red-teaming.skill`, fail-closed gateway, budget/hardstop caps |
|
|
84
|
+
| **ISO/IEC 25059:2023** | **Quality model** for AI systems | `eval-driven-development.skill`, `rag-evaluation.skill`, fitness functions, integrity gates |
|
|
85
|
+
| **ISO/IEC 22989:2022** | AI **concepts & terminology** | consistent vocabulary across the AI/brain skills |
|
|
86
|
+
| **ISO/IEC 42001:2023** | AI **management system** (AIMS) | governance via CONSTITUTION, audit trail, human-approval gates (see §4) |
|
|
87
|
+
| **IEEE 7000 / 7001 / 7002** | ethics-by-design, **transparency**, data privacy | `professional-practice.skill`, `output-validation.skill` PII masking, audit logging |
|
|
88
|
+
| **NIST AI 600-1** (Generative AI Profile) | GenAI risk categories + actions | layered injection defenses, this map, red-teaming, content provenance |
|
|
89
|
+
| **EU AI Act — GPAI Code of Practice** | obligations for general-purpose models | applies to the underlying models GABBE orchestrates; document model provenance (model cards) |
|
|
90
|
+
| **Google SAIF → CoSAI** | secure-AI framework / risk map | maps to `ai-safety-guardrails.skill`, `agent-sandboxing.skill`, MCP hardening |
|
|
91
|
+
|
|
92
|
+
AI-assurance artifacts: GABBE ships `MODEL_CARD_TEMPLATE.md`, `DATASHEET_TEMPLATE.md`, and
|
|
93
|
+
`SYSTEM_CARD_TEMPLATE.md` (security templates) to make these obligations concrete; TEVV
|
|
94
|
+
(test/evaluation/verification/validation) is covered by the eval + red-team skills.
|
|
95
|
+
|
|
96
|
+
## 8. Honesty Note
|
|
97
|
+
|
|
98
|
+
This guide documents **coverage and intent** — how GABBE's existing controls map onto named AI-risk standards — to keep the framework's governance claims grounded. It is **not** a certification, audit result, or compliance attestation. A control appearing in a mapping row means GABBE provides a relevant mechanism; it does NOT mean GABBE is certified against OWASP, NIST AI RMF, MITRE ATLAS, ISO/IEC 42001, or the EU AI Act. Formal conformance requires independent assessment against the specific standard's normative requirements.
|
|
@@ -0,0 +1,51 @@
|
|
|
1
|
+
# Guide: API Security Standards (2025)
|
|
2
|
+
<!-- OWASP API Top 10, Authentication, Authorization, Rate Limiting -->
|
|
3
|
+
|
|
4
|
+
---
|
|
5
|
+
|
|
6
|
+
## 1. Authentication & Identity
|
|
7
|
+
Never roll your own crypto or identity provider. Use established standards.
|
|
8
|
+
|
|
9
|
+
### Standards
|
|
10
|
+
- **User Authentication**: OpenID Connect (OIDC) via Auth0, Okta, or Keycloak.
|
|
11
|
+
- **Machine-to-Machine**: OAuth 2.0 Client Credentials flow.
|
|
12
|
+
- **Session Tokens**: JWT (JSON Web Tokens) with short lifespans (< 15 mins) and refresh tokens (sliding windows, rotating).
|
|
13
|
+
|
|
14
|
+
### JWT Best Practices
|
|
15
|
+
- **Algorithm**: Enforce `alg: RS256` (or EdDSA). NEVER allow `alg: none`.
|
|
16
|
+
- **Payload**: Never store PII or sensitive data in the JWT payload (it's bas64 encoded, not encrypted).
|
|
17
|
+
- **Validation**: Always validate `exp` (expiration), `iss` (issuer), and `aud` (audience).
|
|
18
|
+
|
|
19
|
+
## 2. Authorization (Access Control)
|
|
20
|
+
Authentication proves *who* you are; Authorization proves *what* you can do.
|
|
21
|
+
|
|
22
|
+
- **BOLA (Broken Object Level Authorization)**: Always verify that the authenticated user owns the object they are requesting (e.g., `GET /api/users/123/financials` should check if the current user ID is 123 or an admin).
|
|
23
|
+
- **RBAC vs ABAC**: Use Role-Based Access Control (Admin, User) for broad permissions. Use Attribute-Based Access Control for fine-grained permissions (e.g., "Can edit document if document.owner == user.id").
|
|
24
|
+
- **Zero Trust**: Never assume a request is safe because it comes from an internal network. Authenticate and authorize every internal microservice call (mTLS + JWT).
|
|
25
|
+
|
|
26
|
+
## 3. Input Validation & Output Encoding
|
|
27
|
+
Validate strictly on the way in; encode strictly on the way out.
|
|
28
|
+
|
|
29
|
+
- **Schema Validation**: Use strict schemas (Zod in TS, Pydantic in Python) to validate type, length, format, and range. Reject extra fields.
|
|
30
|
+
- **SQL Injection**: Always use ORMs or parameterized queries. NEVER concatenate strings into SQL.
|
|
31
|
+
- **XSS (Cross-Site Scripting)**: Sanitize output before rendering it in a browser, or rely on modern frameworks (React/Vue/Angular) which auto-escape by default.
|
|
32
|
+
|
|
33
|
+
## 4. Rate Limiting & Abuse Prevention
|
|
34
|
+
Assume your API will be attacked by bots.
|
|
35
|
+
|
|
36
|
+
- **Rate Limiting**: Apply global headers (`X-RateLimit-Remaining`).
|
|
37
|
+
- **Throttling**: Slow down responses for IPs/Tokens hitting limits before outright blocking them.
|
|
38
|
+
- **Authentication Routes**: Apply extremely strict limits to `/login` and `/forgot-password` to prevent credential stuffing and brute force.
|
|
39
|
+
|
|
40
|
+
## 5. OWASP API Top 10 Overview
|
|
41
|
+
Ensure these vulnerabilities are mitigated in every PR:
|
|
42
|
+
1. **Broken Object Level Authorization (BOLA)**
|
|
43
|
+
2. **Broken Authentication**
|
|
44
|
+
3. **Broken Object Property Level Authorization** (Mass Assignment)
|
|
45
|
+
4. **Unrestricted Resource Consumption** (Lack of Rate Limiting/Pagination)
|
|
46
|
+
5. **Broken Function Level Authorization** (Users hitting Admin routes)
|
|
47
|
+
6. **Unrestricted Access to Sensitive Business Flows**
|
|
48
|
+
7. **Server Side Request Forgery (SSRF)**
|
|
49
|
+
8. **Security Misconfiguration**
|
|
50
|
+
9. **Improper Inventory Management** (Zombie/Shadow APIs)
|
|
51
|
+
10. **Unsafe Consumption of APIs** (Trusting 3rd party APIs unconditionally)
|