Staff Engineer Mode

Staff-level engineering judgment for coding agents, from design to production.

Give Staff Engineer Mode a design, diff, rollout, incident, migration, or maintenance problem. One router selects one of 64 focused specialists. The agent works through relevant failure modes and verification checks before it ships code or changes production.

You get concrete decisions, risks, checks, and next steps across architecture, reliability, security, delivery, data, platform, and operations.

How It Works

Ask a normal engineering question. You never need to name a specialist.

The router classifies the requested artifact, lifecycle phase, engineering surface, and risk. It chooses one primary specialist and adds a secondary only when the request needs a separate artifact.

Supported tools list only the native staff-engineer-mode router. The 64 specialist files stay under specialists/ and load only after routing.

For commits and amends, Staff Engineer Mode calls agent-pr-review against the exact staged diff. For releases, tags, version bumps, packages, artifacts, and promotions, it calls release-build-reproducibility and production-readiness-review together.

Installation

Commands labeled "terminal" are run in your shell. Commands labeled "agent chat" are typed inside that tool's interactive agent session.

Claude Code

Terminal:

claude plugin marketplace add https://github.com/sirmarkz/staff-engineer-mode.git
claude plugin install staff-engineer-mode@staff-engineer-mode

Agent chat:

/plugin marketplace add https://github.com/sirmarkz/staff-engineer-mode.git

/plugin install staff-engineer-mode@staff-engineer-mode

Codex

Terminal:

codex plugin marketplace add https://github.com/sirmarkz/staff-engineer-mode.git
codex plugin add staff-engineer-mode@staff-engineer-mode

Cursor

Terminal:

git clone https://github.com/sirmarkz/staff-engineer-mode.git ~/.cursor/staff-engineer-mode-src
mkdir -p ~/.cursor/plugins
ln -s ~/.cursor/staff-engineer-mode-src ~/.cursor/plugins/staff-engineer-mode

OpenCode

Terminal:

opencode plugin 'staff-engineer-mode@git+https://github.com/sirmarkz/staff-engineer-mode.git'

GitHub Copilot CLI

Terminal:

copilot plugin marketplace add https://github.com/sirmarkz/staff-engineer-mode.git

Install the plugin:

copilot plugin install staff-engineer-mode@staff-engineer-mode

Gemini CLI

Terminal:

gemini extensions install https://github.com/sirmarkz/staff-engineer-mode

Try It

Start a fresh session inside any open repo and try one of these prompts:

• "Before implementing partner webhooks, design delivery retries, replay, and dead-letter handling."
• "For a new inventory dependency call, decide timeout, retry, and fallback."
• "Review my last commit."

The agent should load the router, choose one specialist, and respond with concrete decisions, risks, checks, owners, supporting details, and next steps.

For more coverage, see the sample prompts.

What's Inside

Staff Engineer Mode ships one native router skill. It keeps 64 specialist files under specialists/ and loads them after routing.

The concern groups below help you browse. Runtime routing still follows the requested artifact, phase, surface, and risk.

| Engineering concern | Specialist files | | --- | --- | | Architecture & interfaces | architecture-decisions, api-design-and-compatibility, data-contracts, event-workflows, resilience-requirements, persistent-connection-systems | | Verification & evaluation | state-machine-correctness, testing-and-quality-gates, test-data-engineering, agent-pr-review, experimentation-and-metric-guardrails | | Reliability & resilience | slo-and-error-budgets, high-availability-design, dependency-resilience, backup-and-recovery, resilience-experiments, performance-and-capacity, cost-aware-reliability, multi-region-and-data-residency, scheduled-job-reliability | | Data, storage & privacy | distributed-data-and-consistency, database-operations, data-pipeline-reliability, caching-and-derived-data, privacy-and-data-lifecycle, data-lineage-and-provenance | | Delivery & change safety | progressive-delivery, feature-flag-lifecycle, release-build-reproducibility, fleet-upgrades, migration-and-deprecation, configuration-and-automation-safety, dev-environment-parity, service-decommission-and-sunset | | Code quality & maintainability | code-readability-for-agents, dependency-and-code-hygiene | | Operations & incident response | observability-and-alerting, incident-response-and-postmortems, oncall-health, operational-ownership-transfer | | Security | secure-sdlc-and-threat-modeling, identity-and-secrets, cryptography-and-key-lifecycle, software-supply-chain-security, vulnerability-management, tenant-isolation, edge-traffic-and-ddos-defense, llm-application-security, input-validation-and-injection-defense, client-application-security | | Platform & infrastructure | infrastructure-and-policy-as-code, internal-service-networking, platform-golden-paths, container-runtime-and-orchestration | | Client applications & accessibility | web-release-gates, mobile-release-engineering, accessibility-gates | | AI/ML evaluation & serving | llm-evaluation, ml-reliability-and-evaluation, llm-serving-cost-and-latency | | Engineering controls & readiness | ai-coding-governance, documentation-lifecycle, engineering-control-evidence, production-readiness-review |

Sources

The practice library uses first-party engineering publications from Amazon, Google, Meta, Microsoft, Apple, and Netflix. Standards and guidance come from NIST, CISA, OWASP, OpenSSF, IETF, and W3C.

The library covers public incident records from AWS, Azure, Google Cloud, Google Workspace, Meta, and Netflix.

See the source index for the full reference set. Staff Engineer Mode is independent and is not endorsed by or affiliated with these organizations.

Contributing

Patches are welcome. New practices should come from authoritative sources: first-party engineering publications, official documentation, standards bodies, peer-reviewed papers, or widely cited practitioner references.

Contributors must keep new specialists technology-agnostic. Do not endorse vendors. Maintain authoritative sources in the shared index and read CONTRIBUTING.md before opening a PR. Repository checks enforce this voice.

License

MIT