bbartling/open-fdd

openfdd-cookbook-parity

Use when editing rule cookbooks, parity matrix, or cookbook CI (cookbook-parity.yml, cookbook_parity_check.py). Triggers on: pandas cookbook, SQL cookbook, parity-matrix, gap-matrix, rule headings.

openfdd-railway-cli

Use when installing, authenticating, linking, or re-pinning the Open-FDD Railway hub (central/mqtt/web) via the Railway CLI on bensbench. Triggers on: railway CLI, RAILWAY_TOKEN, railway login, railway link, railway redeploy, Railway re-pin,…

openfdd-react-spa

Maintain the Open-FDD React product SPA (frontend/web → openfdd-web). Use when editing Overview, Inspect, FDD Plots, RCx, Mapping, Operations, Sites, auth UI, health matrices, or client Plotly charts against central /api (DataFusion).

openfdd-stack-ghcr

Use when pulling, rebuilding, or verifying Open-FDD GHCR stack images. Test channel is nightly. Triggers on: nightly, openfdd-central, openfdd-web, GHCR, openfdd_stack_up, OPENFDD_IMAGE_TAG.

openfdd-package-mapping

Author an openfdd_package_v1 zip for any BAS job: equipType, Haystack points to SQL roles, weather sidecar, motor vs compressor vs valve. Triggers on package zip, column_map, mapping, empty Overview / RCx / Inspect charts, missing roles, haystack sidecar.

openfdd-architecture

Use when enforcing Open-FDD product boundaries: production DataFusion SQL vs pandas oracle, vibe19/vibe20 ownership, dual cookbooks, edge/os never-delete, ownership.yaml, forbidden imports. Triggers on: architecture, ownership, pandas fallback, cookbook…

openfdd-pypi-oracle

Use when changing open-fdd PyPI pandas oracle libraries: open_fdd.rules, analytics, reporting, extras oracle/vibe19/reporting, wheel publish, consumer pins. Triggers on: PyPI, open-fdd package, rules runner, analytics.core, reporting, oracle extra, 4.1.x.

openfdd-sql-fdd

Use when working on production DataFusion SQL FDD: sql_rules registry, central /api/fdd/run, parity with pandas oracle, no pandas in central. Triggers on: sql_rules, DataFusion, registry.yaml, FDD engine, SQL cookbook.

openfdd-ecm-engineering

Use when migrating or changing generic ECM math in open_fdd.ecm_engineering, publishing PyPI ECM workbook exports, or Compare honesty (FITTED vs industry). Triggers on: ECM, fan affinity, scheduling bins, full-parity workbook, Industry_Screening, BUG-ECM-018,…

openfdd-milestone-a-pr

Use when executing Milestone A bounded PRs: inventory, parity tests, cutover, twin deletion, CodeRabbit loop, cross-repo pin bumps. Triggers on: Milestone A, twin delete, parity proof, PR_PROTOCOL, migration matrix.

architecture-design-review

Use to evaluate architecture, design proposals, refactors, module boundaries, dependency direction, data flow, concurrency model, and maintainability tradeoffs across any codebase.

codebase-research-pass

Use for structured research on an unfamiliar or complex codebase before planning, reviewing, or editing. Delegates mapping, ownership, dependency, test, and risk discovery to focused subagents and returns an evidence-led research brief.

external-source-research

Use when implementation or review depends on external documentation, standards, protocols, APIs, SDKs, changelogs, or version-specific behavior. Produces a concise source dossier and implementation implications.

multi-agent-pr-review

Use for rigorous pull request, branch, patch, or diff review. Runs focused review subagents for correctness, security/reliability, tests, docs/API behavior, and release risk, then synthesizes actionable findings.

performance-ab-benchmark-review

Use to design, run, or review performance work with reproducible A/B baselines. Delegates benchmark inventory, profiling, correctness guardrails, and result interpretation to subagents.

release-readiness-review

Use before merging, shipping, publishing, or handing off work. Runs subagents for verification, regression risk, operational readiness, docs, compatibility, and unresolved follow-ups.

spec-contract-compliance-review

Use to compare any codebase against a specification, API contract, protocol, policy, RFC, security baseline, or product requirements document. Builds a traceability matrix and prioritizes compliance gaps.