mindshare

MAPS Phase 3 Build skill that merges base /build-agent, incremental implementation, and test-driven development into one implementation workflow.

Run MAPS Phase 6 Deploy by wrapping /deploy-agent with GitHub Actions environments and Cloudflare deployment automation. Use when Codex needs GitHub to deploy a Cloudflare Pages, Workers, or Agents project; replace manual Wrangler deploys; configure workflow gates, encrypted secrets, smoke tests, release evidence, and rollback records.

Create the MAPS Design phase artifact for an agent or multi-agent system. Use when defining roles, workflows, handoffs, memory, context, guardrails, approvals, escalation paths, test-first proof requirements, and system boundaries from an agent brief.

Run enhanced MAPS M8 Experience Design for websites, SaaS products, dashboards, landing pages, and agent-facing product surfaces. Use when Codex needs to wrap /design-experience with website design references, component-system choices, accessibility primitives, UX/service-design reasoning, responsive layout, page hierarchy, and production-ready UI handoffs.

Run MAPS M8 Experience Design for multi-agent products, or optional A2 Experience Design for single-agent products without an M layer. Use when Codex needs to turn product intent, orchestration behavior, agent behavior, and product constraints into user journeys, surfaces, information architecture, interaction states, accessibility requirements, and system-evaluation handoffs.

Run MAPS Phase 5 Evaluate by wrapping the base Evaluate process with LangSmith, Inspect AI, and Phoenix. Use when Codex needs to create eval suites, trace-backed eval runs, safety/tool-use checks, regression evidence, eval reports, or Phase 7 observability handoff for an equipped agent.

Create the MAPS Evaluate phase artifact for an agent or multi-agent system. Use when designing scenario tests, eval datasets, rubrics, scorecards, regression checks, red-team prompts, safety checks, and release evidence.

Start M0 Project Foundation for a MAPS project or instantiate a MAPS framework/org scaffold. Use when kicking off a new agent, multi-agent project, MAPS+Org project, reusable MAPS framework, or replacing /scaffold by creating project intent, portable path layer settings, notes/source/memory/RAG scaffold, Git and remote readiness, env/secrets scaffold, source inventory, assumptions, decisions, evidence index, RAG-readiness plan, and optional full MAPS repo structure before system shape or APS phase work begins.

Create MAPS M5 Agent Buildout for a multi-agent system. Use after M4 Coordination to plan which agents, roles, tools, adapters, and child APS builds are needed, in what order, with tests, proof gates, runtime-neutral decisions, and no-build decisions before capability integration.

Create MAPS M6 Capabilities for a multi-agent system. Use after M5 Agent Buildout to map shared tools, MCP servers, APIs, data sources, memory stores, credentials, permissions, limits, fallbacks, audit needs, and capability ownership before orchestration build.

Create MAPS M3 Contracts for a multi-agent system. Use after M2 Roster to define participant contracts, inputs, outputs, authority, memory, tools, handoffs, escalation, stop conditions, acceptance evidence, and contract gaps before coordination design.

Create MAPS M4 Coordination for a multi-agent system. Use after M3 Contracts to define workflow lanes, handoff routes, supervisor/router pattern, peer handoffs, queues, approvals, exception paths, retries, and coordination evidence before agent buildout.

Create MAPS M10 Deploy/Observe for a multi-agent system. Use after M9 System Evaluate to define runtime packaging, release approval, configuration, secrets, rollout, smoke checks, observability, alerting, incident triggers, rollback, and production review loops.

Create MAPS M9 System Evaluate for a multi-agent system. Use after M8 Experience Design to test the whole system across participant contracts, coordination, orchestration, shared capabilities, user journeys, approvals, guardrails, observability, and release gates.

Create MAPS M11 Improve for a multi-agent system. Use after M10 Deploy/Observe to classify evidence, incidents, traces, eval failures, user feedback, and operator findings into routed improvements across M2-M10 and child APS phases.

Create MAPS M7 Orchestration for a multi-agent system. Use after M6 Capabilities to define runtime topology, routing, handoff protocol, state, queues, schedules, supervisor/society pattern, observability, human override, rollback, and M8 experience handoff.

Create MAPS M2 Roster for a multi-agent system. Use after M1 System Shape selects Multi-Agent / MAPS to define participants, human owners, roles, candidate agents, tools/services, responsibilities, authority category, memory scope, and the evidence needed before contracts.

Run MAPS Phase 7 Observe with Langfuse. Use when Codex needs to apply the base observe-agent workflow through Langfuse traces, sessions, scores, datasets, prompt versions, metrics, feedback, or self-hostable/open-source LLM observability.

Run MAPS Phase 7 Observe with Phoenix. Use when Codex needs to apply the base observe-agent workflow through Phoenix traces, OpenInference/OpenTelemetry instrumentation, datasets, experiments, LLM/RAG eval analysis, or open trace/eval workbench review.

Run MAPS Phase 7 Observe with LangSmith. Use when Codex needs to apply the base observe-agent workflow through LangSmith traces, runs, datasets, feedback, annotations, monitoring views, experiments, or eval-to-observe continuity.

Create the MAPS Phase 00 Alignment artifact. Use when agreeing on lifecycle phase names, phase order, scope, scaffolding, repo structure, curriculum structure, naming decisions, templates, catalogs, and where future work belongs before defining or building agents.

Build role agents for a root organization or multi-agent corporation. Use when the user wants to create an organizational role such as CEO, CFO, advisor, operator, manager, support lead, data steward, research lead, or functional department voice, and needs to decide role mode, engagement type, authority, implementation form, learning behavior, and whether the role should be advisory, workflow-owned, skill-backed, loop-backed, autonomous, human-in-the-loop, or only a lightweight prompt/persona.

Implement the MAPS Build phase for an agent or multi-agent system. Use when turning a design into a runnable agent loop, prompts, state, routing, orchestration, project files, local run commands, and basic tests.

Create an agent brief for the MAPS Define phase from an existing role. Use when turning an approved role artifact into an agent brief with goals, users, authorization, scope, non-goals, success criteria, failure criteria, escalation points, risks, and assumptions.

Create the MAPS Deploy phase artifact for an agent or multi-agent system. Use when preparing release plans, runtime configuration, secrets, identities, approvals, rollout strategy, rollback plans, and post-deploy verification.

Create the MAPS Equip phase artifact for an agent or multi-agent system. Use when mapping tools, APIs, MCP servers, data sources, retrieval, memory, credentials, permissions, audit needs, and integration risks.

Create the MAPS Improve phase artifact for an agent or multi-agent system. Use when turning eval results, traces, failures, incidents, user feedback, and observations into prioritized prompt, tool, memory, policy, design, and eval improvements.

Create the MAPS Observe phase artifact for an agent or multi-agent system. Use when designing telemetry, traces, dashboards, quality signals, cost and latency monitoring, drift review, failure logs, and operator review loops.

Instantiate the MAPS scaffold template. Use when the user invokes /scaffold or asks to create a Multi-Agent Pipeline Skills repo from templates/maps-scaffold-template.md with phase docs, phase skills, templates, catalogs, docs page placeholders, README, gitignore, and MIT license.

Run M1 System Shape for a MAPS project. Use after M0 Project Foundation to scope the workflow and choose Unknown / Scope First, Single-Agent / APS, or Multi-Agent / MAPS before defining an agent roster, contracts, or implementation plan.

Create an agent brief for the MAPS Define phase from an existing role. Use when turning an approved role artifact into an agent brief with goals, users, authorization, scope, non-goals, success criteria, failure criteria, escalation points, risks, and assumptions.

Run enhanced MAPS M8 Experience Design for websites, SaaS products, dashboards, landing pages, and agent-facing product surfaces. Use when Codex needs to wrap /design-experience with website design references, component-system choices, accessibility primitives, UX/service-design reasoning, responsive layout, page hierarchy, and production-ready UI handoffs.

Run MAPS M8 Experience Design for multi-agent products, or optional A2 Experience Design for single-agent products without an M layer. Use when Codex needs to turn product intent, orchestration behavior, agent behavior, and product constraints into user journeys, surfaces, information architecture, interaction states, accessibility requirements, and system-evaluation handoffs.

Start M0 Project Foundation for a MAPS project or instantiate a MAPS framework/org scaffold. Use when kicking off a new agent, multi-agent project, MAPS+Org project, reusable MAPS framework, or replacing /scaffold by creating project intent, portable path layer settings, notes/source/memory/RAG scaffold, Git and remote readiness, env/secrets scaffold, source inventory, assumptions, decisions, evidence index, RAG-readiness plan, and optional full MAPS repo structure before system shape or APS phase work begins.

Create MAPS M10 Runtime Readiness for a multi-agent system. Use after M9 System Evaluate to coordinate release authority, runtime configuration, child APS deployment evidence, smoke checks, hold conditions, rollback, and handoff into M11 live observation.

Create MAPS M9 System Evaluate for a multi-agent system. Use after M8 Experience Design to test the whole system across participant contracts, coordination, orchestration, shared capabilities, user journeys, approvals, guardrails, observability, and release gates.

Create MAPS M11 Observe/Improve for a multi-agent system. Use after M10 Runtime Readiness to observe live system signals, classify evidence, incidents, traces, eval failures, user feedback, and operator findings, and route improvements across M2-M10 and child APS phases.

Create MAPS M7 Orchestration for a multi-agent system. Use after M6 Capabilities to define runtime topology, routing, handoff protocol, state, queues, schedules, supervisor/society pattern, observability, human override, rollback, and M8 experience handoff.

Build role agents for a root organization or multi-agent corporation. Use when the user wants to create an organizational role such as CEO, CFO, advisor, operator, manager, support lead, data steward, research lead, or functional department voice, and needs to decide role mode, engagement type, authority, implementation form, learning behavior, and whether the role should be advisory, workflow-owned, skill-backed, loop-backed, autonomous, human-in-the-loop, or only a lightweight prompt/persona.

Deprecated compatibility alias for older /scaffold requests. Use /foundation instead when creating or auditing MAPS project foundations, portable path settings, or full MAPS framework/org scaffolds.