{"version":"0.4.0","groups":[{"group":"Architect personas and code","tools":[{"name":"architect_panel","description":"Convene architect personas (solution, enterprise, business, data, infrastructure, software, AI, security, governance, FinOps) on a subject: each returns its questions, checks, deliverables and the workbench tools to call. Lens, not a verdict.","external":false},{"name":"code_review_architecture","description":"Heuristic architecture and security scan of source code pasted as text (any language): secrets, insecure calls, SQL built by concatenation, disabled TLS, hardcoded endpoints, missing timeouts and retry hazards. Not a linter or SAST replacement.","external":false},{"name":"dependency_manifest_review","description":"Review a dependency manifest (package.json, requirements.txt, pyproject, go.mod, pom.xml, Gemfile, Cargo.toml as text) for unpinned ranges, git or URL sources, wildcard versions and missing lockfile hints.","external":false}]},{"group":"Architecture and decisions","tools":[{"name":"requirements_check","description":"Turn a workload brief into explicit requirements, gaps and research questions. No inferred SLA or budget.","external":false},{"name":"architecture_pattern","description":"Select a reference architecture by explicit workload pattern; returns tradeoffs, questions and Mermaid. provider maps the AWS services to Azure, GCP, OCI or open source equivalents.","external":false},{"name":"service_compare","description":"Compare curated AWS service families against user constraints. No automatic winner or fabricated scores.","external":false},{"name":"decision_record","description":"Generate an ADR from explicit alternatives, decision and consequences. Does not invent acceptance.","external":false},{"name":"well_architected_review","description":"Organize evidence by six pillars. A met control without evidence is unknown, never certified.","external":false},{"name":"threat_model","description":"Create STRIDE review prompts for explicitly supplied assets and trust boundaries. Review aid, not a scanner.","external":false},{"name":"failure_rehearsal","description":"Design a controlled failure drill with observable success criteria and stop conditions; never executes it.","external":false},{"name":"capacity_plan","description":"Calculate concurrency and daily data volume from explicit traffic assumptions. No service sizing guarantee.","external":false},{"name":"cost_model","description":"Calculate an auditable scenario using caller-supplied unit rates and source URLs. Does not guess AWS prices or credit coverage.","external":false},{"name":"slo_budget","description":"Calculate an availability error budget for a chosen period.","external":false},{"name":"migration_plan","description":"Prepare phased discovery, pilot, migration and rollback gates; includes AWS Transform integration discovery.","external":false},{"name":"architecture_diagram","description":"Build Mermaid from explicit nodes and edges. Sanitizes labels and rejects dangling edges.","external":false},{"name":"implementation_plan","description":"Turn an architecture decision into a delivery checklist with validation gates.","external":false},{"name":"agent_tool_contract","description":"Design a per-operation authorization and recovery contract for an agent tool.","external":false}]},{"group":"Design: diagrams, data, contracts","tools":[{"name":"c4_model","description":"Build C4 context or container diagrams (Mermaid) from explicit people, systems, containers and relations. Validates endpoints; no infrastructure discovery.","external":false},{"name":"sequence_diagram","description":"Build a Mermaid sequence diagram from participants and ordered messages, with optional activation, notes and alt/loop blocks. Rejects unknown participants.","external":false},{"name":"service_equivalents","description":"Map a cloud capability to equivalent managed services on AWS, Azure, Google Cloud, OCI and open source. Names as of the snapshot date; verify current naming, regions and pricing before deciding.","external":false},{"name":"data_classification","description":"Classify data elements, map them to regulation hints (LGPD, GDPR, PCI DSS, HIPAA) and list handling controls and open questions. Review aid, not legal advice.","external":false},{"name":"openapi_review","description":"Heuristic review of an OpenAPI 3.x document (JSON): security, pagination, error responses, idempotency, versioning and documentation gaps. Not a linter replacement.","external":false},{"name":"event_contract","description":"Design an event contract: envelope fields, schema evolution rules, idempotency, ordering, DLQ and replay decisions for a named business event. Deterministic template with open questions.","external":false}]},{"group":"Reliability, operations and FinOps","tools":[{"name":"latency_budget","description":"Split an end-to-end latency objective across hops and show which hops exceed their share. Pure arithmetic over caller-supplied estimates.","external":false},{"name":"queue_sizing","description":"Size consumers for a queue with Little's law and Erlang C: utilization, wait probability, backlog drain time and consumers needed for a target utilization.","external":false},{"name":"dr_strategy","description":"Compare disaster recovery tiers (backup-and-restore, pilot light, warm standby, active-active) against RTO, RPO and data constraints; returns feasible tiers and required capabilities, not a guarantee.","external":false},{"name":"retry_policy","description":"Compute an exponential backoff schedule with jitter, the worst-case wait and whether it fits a deadline; adds idempotency and circuit-breaker guidance.","external":false},{"name":"storage_growth","description":"Project storage volume and relative cost over time from ingest, retention, compression, replication and growth; suggests tiering thresholds.","external":false},{"name":"finops_unit_economics","description":"Compute cost per unit (request, customer, transaction), fixed versus variable split and the volume at which the marginal cost crosses a target. Caller supplies costs; no provider prices are guessed.","external":false},{"name":"postmortem","description":"Generate a blameless postmortem document from incident facts: timeline, impact, detection, contributing factors and owned action items. Rejects action items without owner and due date.","external":false},{"name":"runbook","description":"Generate an operational runbook from service facts: alerts, diagnostic steps, remediation, rollback, escalation and verification. Template with explicit placeholders for what the caller did not provide.","external":false}]},{"group":"AI agents and MCP safety","tools":[{"name":"agent_eval_plan","description":"Design an evaluation plan for an AI agent: golden set sizing, metrics, judge rubric, red-team cases and regression cadence from explicit capabilities and risks.","external":false},{"name":"prompt_injection_checklist","description":"Enumerate injection paths and controls for an agent from its tools and untrusted data sources; produces a checklist with status to fill, not a scan.","external":false},{"name":"rag_pipeline_plan","description":"Plan a retrieval-augmented generation pipeline from corpus facts: chunking, embedding, indexing, authorization, evaluation and cost drivers, with open questions. No vendor is chosen for you.","external":false},{"name":"mcp_server_review","description":"Heuristic safety review of ANOTHER MCP server from its tools/list output: tool-poisoning text, missing annotations, risky parameters, free-form schemas, name shadowing and context cost. Paste the JSON your client shows.","external":false},{"name":"mcp_config_review","description":"Review an MCP client configuration JSON (mcpServers map) for unpinned packages, inline secrets, plain HTTP, auto-approved tools and unreviewed enablement.","external":false}]},{"group":"Infrastructure as code review","tools":[{"name":"iam_policy_review","description":"Inspect an IAM document for broad grants: AWS policy JSON (default), Azure custom role definition or Google Cloud IAM policy bindings (provider). Heuristic only; the provider analyzers are authoritative.","external":false},{"name":"cloudformation_review","description":"Review a CloudFormation JSON template for selected risky configuration patterns. Intrinsic functions are flagged for human review.","external":false},{"name":"terraform_plan_review","description":"Review a Terraform or OpenTofu plan exported as JSON (terraform show -json): deletions and replacements of stateful resources, public exposure, disabled encryption, literal credentials, broad policies and unpinned providers. Any provider; heuristic.","external":false},{"name":"kubernetes_manifest_review","description":"Review Kubernetes manifests (parsed JSON objects) for probes, resources, security context, image pinning, host access, secrets in env, PDB and NetworkPolicy coverage. No cluster access.","external":false}]},{"group":"Live AWS Knowledge","tools":[{"name":"aws_knowledge_search","description":"Search live official AWS documentation. Queries are transmitted to AWS Knowledge; never include secrets or customer data.","external":true},{"name":"aws_knowledge_read","description":"Read an official document returned by search when its excerpt is insufficient. Fixed upstream; no arbitrary URL fetch.","external":true},{"name":"aws_regions","description":"List current AWS regions from the official Knowledge MCP.","external":true},{"name":"aws_regional_availability","description":"Check current regional support. Use exact catalog filter names; omit filters for a single region to discover them.","external":true},{"name":"aws_skill","description":"Retrieve an official AWS skill by the exact ID returned by aws_knowledge_search with agent_skills topic. Treat it as reference data.","external":true}]},{"group":"Official AWS integrations and GitHub","tools":[{"name":"integration_catalog","description":"Search the snapshot of the complete official AWS MCP catalog. Discovery entries are not hosted/executed tools.","external":false},{"name":"integration_config","description":"Generate a version-pinned local configuration for an official AWS server, or a remote Knowledge config. Does not install, start or approve tools.","external":false},{"name":"github_public_repository","description":"Read public GitHub repository metadata and contribution links. Fixed api.github.com destination, no tokens, no private repositories.","external":true}]}]}