ryanmaclean

Use when designing or refactoring bop runtime/storage paths to maximize APFS COW/compression and prefer standard Rust crates over custom infrastructure.

Use when agents must write to .bop bundles safely and consistently without corruption.

Use when bop execution needs Auto-Claude MCP-style progress/status/discovery tracking.

Use when you need to map Auto-Claude MCP server logic to bop stages, workflows, and commands.

Use when a card or request includes a persona emoji (for example `🎯`, `🔒`, or `🚨`) and you need role-specific execution behavior with minimal token overhead.

Use when a bop stage needs external library/framework documentation lookup.

Use for desktop UI validation in bop QA stage when the target app is Electron.

Use when bop stages need cross-session memory for discoveries, attempts, and constraints.

Almanac reference for dates, holidays, time zones, business days, and astronomical events. Use when checking if a date is a business day, calculating date differences, converting time zones, looking up holidays, or checking for astronomical events like solstices, equinoxes, and moon phases. Also for seasonal calculations, workday schedules, and calendar arithmetic.

Toyota Production System (TPS) and Toyota Way for software engineering — lean thinking, waste elimination, root cause analysis, and continuous improvement. Use when identifying waste (muda/muri/mura), running blameless postmortems, doing 5 Whys, writing A3 problem statements, or connecting lean philosophy to TRIZ contradiction resolution.

Local multilingual translation via Ollama — 119 languages, no API key, no network, no data leaves the machine. Use when translating to/from Japanese, Chinese, Korean, French, Spanish, German, Portuguese, Russian, Arabic, or any other language. Also for localization, i18n text, and roundtrip validation. Qwen3:32b on Apple Silicon — faster and cheaper than cloud APIs.

TRIZ contradiction matrix oracle for software and systems design. Use when improving one quality worsens another — speed vs correctness, isolation vs sharing, autonomy vs control, simplicity vs completeness. Trigger phrases: "tradeoff", "tension between", "can't have both", "worsens when", "at the cost of", "faster but less reliable", "more isolated but harder to share". Not for bugs, merge conflicts, or tool choices. Prerequisite: triz binary must be installed (run `triz doctor` to verify).

Deploy and manage software on Linux/BSD fleet hosts (Pis, NAS, workstations) via Ansible. Use when user mentions deploy, ansible, fleet, hosts, inventory, or deployment.

Use when operating, debugging, or deploying the elixir-gastown Elixir/BEAM fleet — cluster federation, release builds, worker deploys, seccomp fixes, sname/name distribution issues, rate limiter, or any gastown service on Pi workers or coordinator nodes.

Use when communicating with fleet agents, checking agent status, or sending commands via IRC. The fleet runs TLS IRC on 10.0.3.203; agents listen in

Use when operating the fleet of Raspberry Pis, NAS hosts, and workstations via irclaw IRC bots, Ansible, Ollama (kimi-k2.5:cloud), or long-running deploys. Covers IRC DM protocol, bot security policy, zellij for long tasks, OS upgrades, and gastown/polecat deployments.

Apple Silicon optimization for VMs, ML inference, and compression. Covers Metal GPU acceleration, MLX model inference, CoreML conversion, M-series zstd compression, Apple Virtualization Framework, and performance tuning.

Query Datadog APM traces, logs, metrics, SLOs, security signals, and service catalog. Create monitors, dashboards, and synthetic tests. Manage incidents and workflows. Use when investigating performance issues, searching logs, checking SLOs, analyzing costs, or automating Datadog operations.

Helm and Kubernetes deployment operations for ACR/AKS production, KIND local development, and resource management. Use for deploying charts, managing pods/services, configuring ingress, and troubleshooting K8s workloads.

Find and test free OpenRouter models. Lists available free models, tests their availability, and selects the best working model for code generation tasks. Use this before spawning agents to select cost-effective models.

Run Datadog Code Security scans — SAST, SAIST (AI-native SAST), SCA, secrets, IaC scanning, plus supply-chain protection (GuardDog, Supply-Chain Firewall) and IDE runtime defense (IDE Shepherd). Integrates via Code Security MCP Server for real-time scanning in Claude Code, Cursor, and VS Code. Use when asked to scan code for vulnerabilities, run a security audit, find bugs via static analysis, check dependencies for known CVEs, or protect against supply-chain attacks.

Editorial quality gate for i18n translations. Validates translation completeness, placeholder parity, terminology consistency, and wiring coverage across all locale files. Run before any PR that touches UI to prevent translation drift. Use when: adding new UI strings, modifying pages/components, or before releases.

VibeCode project conventions, patterns, and critical warnings. Preload into any agent working on this codebase.

VibeCode test conventions, Jest configuration, mock patterns, and known issues. Preload into test-fixer and quality-sweep agents.

Use the `at` CLI to create, execute, monitor, and complete tasks on the Auto-Tundra daemon. Covers the full bead lifecycle from sling to done.

Use when troubleshooting build failures, test failures, daemon connectivity issues, or integration errors in Auto-Tundra.

Use the Auto-Tundra HTTP API directly (via curl) for operations not exposed in the CLI, such as task updates, terminal management, GitLab/Linear queries, and Kanban board manipulation.

Use when adding features, fixing bugs, or refactoring code in any Auto-Tundra crate. Covers build, test, lint, and validation workflows.

Use for GitHub/GitLab/Linear wiring in rust-harness to remove stub-token paths, enforce env-driven credential resolution, and add regression tests for real-client behavior with safe fallbacks.

Use for local Ollama-first execution with queued multi-agent CLI workflows. Configures auto-tundra for one-human-overseer and many-agent-subscriber code refinery mode.

Use when developing or refactoring at-cli. Runs deterministic smoke checks for run/agent/skill/doctor commands, including --dry-run and --out artifact paths.

Use for multi-lane implementation waves in rust-harness when coordinating sub-agents, sequencing risk, and enforcing compile/test gates before reporting completion.

Comprehensive Datadog operations: query APM/logs/metrics/RUM/database, create monitors/dashboards/synthetics, manage incidents, trigger workflows, analyze costs and LLM usage. 73% platform coverage including service catalog, uptime monitoring, and frontend performance. Use for debugging, automation, incident response, and cost optimization.

Query Datadog APM traces, logs, metrics, SLOs, security signals, and service catalog. Create monitors, dashboards, and synthetic tests. Manage incidents and workflows. Use when investigating performance issues, searching logs, checking SLOs, analyzing costs, or automating Datadog operations.