Manager behavior for Codex Mission Control projects. Use when the manager needs to restate a project idea, run an interview, refine plans, create worker tasks, route follow-up…
Design, build, or audit MCP servers and tool/resource/prompt contracts through Mission Control. Use for MCP schemas, stdio startup, auth boundaries, plugin packaging, and smoke…
Define memory, state, checkpoints, resumability, and retention policy for Mission Control workflows and agents.
Use Mission Control to plan bounded TensorFlow model optimization work such as quantization or pruning with explicit tradeoffs.
Inspect or update Mission Control model-assignment policy. Use when the user wants to understand or change cost-saving, balanced, best-quality, local-first, or custom model…
Coordinate Nsight-based GPU profiling through Mission Control with safe evidence capture and approval-aware command use.
Use or prefer Ollama or local models through Mission Control. Use when the user explicitly wants Ollama or local-model preference and Codex should verify availability rather than…
Generate a guided onboarding tour for a codebase using Mission Control's project map, domains, commands, risks, and recommended reading order.
Use when Codex should route a workspace task through Mission Control instead of acting like the Manager AI.
Show file and path ownership and conflicts in Mission Control. Use when the user wants to know which paths are locked, which agent owns them, which tasks are waiting, or how to…
Pause Mission Control orchestration safely. Use when the user wants to pause after the current task, pause immediately, or stop assigning new work without discarding the current…
Ask Mission Control Manager to create or revise a plan. Use when the user asks for a plan, scope changes, imported codebases need planning, or the next milestone and validation…
Run a Mission Control plugin, daemon, and bridge health check. Use when the user wants to verify daemon status, MCP connectivity, skills availability, runner registry, local…
Ask only a few high-impact Mission Control clarifying questions. Use when the user wants speed, the repo already explains most things, or the task is urgent and only 3–6 targeted…
Design retrieval, indexing, chunking, ranking, and RAG workflows through Mission Control. Use for docs search, code search, semantic recall, and context-pack construction.
Ask Mission Control Manager for recovery guidance after a failure. Use when the user wants a failure summary, likely causes, recovery options, recommendation, and risks without…
Generate a rollback or restore plan from Mission Control state. Use when the user wants to know what would be reverted, what evidence would be preserved, and which destructive…
Use when a new Codex chat needs to reconnect to a recent Mission Control orchestration safely.
Resume paused Mission Control agents or projects when safe. Use when the user wants paused work restarted but approvals, safety conditions, and current status should be checked…
Use when Codex should retrieve Mission Control status, evidence, and final handoff notes for review with the user.
Show or update the Mission Control risk register. Use when the user wants top risks, severity, likelihood, mitigation, owners, or current risk status summarized through Mission…
Ask Mission Control to run or plan validation. Use when the user wants build, tests, typecheck, lint, smoke, docs check, or manual verification routed through Mission Control with…
Design LangChain-style runnable chains, model pipelines, and composable agent steps inside Mission Control without requiring LangChain as a runtime dependency.
Use when the user wants Mission Control to operate in a stricter approval-heavy safety posture.
Ask Mission Control whether the project is drifting beyond approved scope. Use when the task list is growing, the user asks for more work midstream, or you need a Manager…
Build, audit, or package Mission Control skills and plugin skill bundles. Use when the user wants reusable skills, skill metadata, skill tests, marketplace packaging, or…
Skip the Mission Control interview and proceed with assumptions. Use when speed matters more than full intake and the user accepts that the Manager will proceed with explicit…
Route spatial and 3D asset-pipeline work through Mission Control with explicit ingest, conversion, validation, and evidence boundaries.
Use when the user wants a compact Mission Control status summary, blocker report, or agent activity check.
Stop or retire Mission Control orchestration safely. Use when the user wants no new work assigned, current state preserved, partial results summarized, and unsafe process-kill…
Recommend or review Mission Control Codex subagent bursts for bounded read-heavy work. Use when the user wants parallel exploration, review, planning, handoff audit, or failure…
Use when the user wants to inspect or adjust Mission Control swarm strategy from Codex chat.
Use Mission Control to turn TensorBoard logs and training curves into explicit validation evidence.
Route TensorFlow SavedModel and serving-export work through Mission Control with explicit artifact and API validation.
Use Mission Control to plan or repair TFX-style production ML pipelines with explicit component and validation boundaries.
Inspect or update Mission Control tool-routing and permission policy. Use when the user wants to see allowed tools, blocked tools, approval-required tools, or per-agent archetype…
Design or audit tool registries, tool schemas, permissions, and runner capabilities through Mission Control.
Use when Codex should remove the Mission Control plugin bundle, synced skills, and managed Codex MCP registration.
Use when Codex should refresh an existing Mission Control install, resync the plugin and skills, and rerun headless repair/bootstrap.
Route OpenUSD and Houdini/Solaris workflow planning through Mission Control with explicit scene-graph, interchange, and validation boundaries.
Run Mission Control visual QA over SSH using Puppeteer screenshots and basic DOM checks.
Decompose a validated parent mission into sub-missions with guided scaffolding, templates, and validation.
Author, preflight, and execute aurora-agent missions — validated DAGs of MCP tool calls. Use when asked to build or run a mission, when a mission is refused with invalid_mission…
Lifecycle orchestrator that auto-detects project state and routes to the correct development phase.
Execute a single task with Pathfinder/Builder/Inspector crew. Self-fetches work from Beads.
Sub-skill of the `mission` orchestrator. The Mission Judge — reviews the accumulated diff against the original objective + active steers, runs broader verification, and decides…
Parallel multi-agent mission loop using yamtam-rt — decompose task into subtasks with deps, dispatch waves, collect reports, apply changes.
HOUSTON executes feature tasks directly. No agents. Best for small features (1-3 tasks).
Missive integration. Manage Organizations. Use when the user wants to interact with Missive data.
Automate Missive tasks via Rube MCP (Composio). Always search tools first for current schemas. — from general/automation
Automate Mistral AI operations -- manage files and libraries, upload documents for fine-tuning, batch processing, and OCR, track fine-tuning jobs, and build RAG pipelines — from…
Execute Mistral AI chat completions with streaming, multi-turn, and guardrails. Use when implementing chat interfaces, building conversational AI, or integrating Mistral for text…
Execute Mistral AI embeddings, function calling, and RAG pipelines. Use when implementing semantic search, RAG applications, tool-augmented LLM interactions, or code embeddings.
Optimize Mistral AI costs through model selection, token management, and usage monitoring. Use when analyzing Mistral billing, reducing API costs, or implementing usage m — from…
Optimize Mistral AI costs through model selection, token management, and usage monitoring. Use when analyzing Mistral billing, reducing API costs, or implementing usage m — from…
Implement Mistral AI PII handling, data retention, and GDPR/CCPA compliance patterns. Use when handling sensitive data, implementing data redaction, configuring retention…
Configure Mistral AI enterprise access control and workspace management. Use when implementing role-based API key scoping, managing team access, or setting up organization-level…
Execute Mistral AI incident response procedures with triage, mitigation, and postmortem. Use when responding to Mistral AI-related outages, investigating errors, or running…
Install and configure the Mistral AI SDK with authentication. Use when setting up a new Mistral integration, configuring API keys, or initializing Mistral AI in your project.
Set up comprehensive observability for Mistral AI with metrics, traces, and alerts. Use when implementing monitoring for Mistral AI operations, setting up dashboards, or…