bbartling

Use when working on Open FDD Vibe Coder Streamlit FDD demo: streamlit_app.py, 50-rule pandas cookbook, building folder browse, Haystack-like column map JSON, RCx Plots, analytics, occupancy calendar, unit toggle. Triggers on: Streamlit, streamlit_app, BUILDING tree, Haystack points, column map, RCx, 50 rules.

Use when onboarding HVAC CSV data for App 19: DATA_ROOT layout, manifest.json, grid_minutes, validate_data.py, data_paths.local.yaml, BUILDING_* switching, weather parity, VAV folders. Triggers on: import, CSV tree, manifest, poll interval, HVAC_DATA_ROOT, validate data, new building, sidecar export.

Use when implementing HVAC fault rules in pandas for App 19 with Open-FDD cookbook parity: confirm_fault, poll_seconds, operational gates, ECON free-cool (web weather), VAV fixed flow, CW wet-bulb. Triggers on: FDD, fault, rule, cookbook, confirm_fault, economizer, ECON-3, VAV-7, CW-OPT, OAT-METEO, pandas rule.

Use for Plotly charts in the Streamlit demo: rule fault plots, RCx multi-equipment overlays, box plots, OAT scatters, mech-cooling histograms. Triggers on: Plotly, chart, RCx, zone temps, duct static box, scatter, Streamlit figure.

Use when validating MQTT→cloud telemetry, calling Vibe12 Dashboard Lambda APIs for commissioning status, BRICK time-series refs, points registry, or auth from Codex/Cursor/OpenClaw. Triggers on: commissioning API, cloud_ingest_ok, telemetry flow, brick_timeseries_ref, external_ref, validate_cloud_pipeline, series_flowing, DashboardUrl, Bearer token, demo bens-office.

Use when deploying Vibe12 to Raspberry Pi or gateway via Ansible, vibe12-bacnet-read, points.csv, AWS IoT certs, GPIO DS18B20, or bacnet_pi host vars. Triggers on: ansible deploy, bacnet_pi, read driver, 192.168.204.12, points.csv, enable_bacnet_read_driver.

Use when configuring Codex CLI, OpenClaw, or scheduled agent wakes for vibe12_agent_spec. Triggers on: Codex CLI, OpenClaw, agent wake, vibe12_agent_spec, BUILD_CHECKPOINTS, memory bootstrap, cron agent.

Use when building or validating BRICK graphs, canonical data models, SparkQL prep, brick_timeseries_ref, entity_id, or data-model import/TTL APIs. Triggers on: BRICK, SparkQL, data-model, brick graph, canonical model, timeseries ref, external_ref.

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

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.

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.

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.

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

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

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.