Use when Mission Control orchestration is stuck, failed, degraded, or unclear from Codex chat.
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…
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…
Use when the user wants to inspect or adjust Mission Control swarm strategy from Codex chat.
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…
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…
Show or request Mission Control agent contracts. Use when the user wants to inspect a worker mission, allowed paths, forbidden paths, tools, validation obligations, stop…
Design LangChain-style runnable chains, model pipelines, and composable agent steps inside Mission Control without requiring LangChain as a runtime dependency.
Resolve Mission Control agent or merge conflicts safely. Use when paths overlap, outputs disagree, or Mission Control needs a user-visible conflict-resolution path instead of…
Run a full Mission Control Manager interview. Use when the project is ambiguous, project-specific intake matters, or the user wants the Manager to ask clarifying questions with…
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…
Use or prefer Codex CLI runner mode through Mission Control. Use when the user wants Codex CLI as the runner, needs its status explained, or wants the distinction between…
Switch the project toward documentation-heavy Mission Control work. Use when the user wants the swarm or plan to prioritize README, guides, examples, docs review, or public-facing…
Diagnose a stuck Mission Control agent. Use when an agent shows no output, repeats errors, times out, asks for the same approval repeatedly, or stops making progress events.
Build or inspect a graph-style map of docs, wiki pages, claims, entities, and relationships through Mission Control.
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 CUDA Tile or tile-shaped GPU refactors need Mission Control planning, validation, and benchmark discipline.
Design or run evaluation, tracing, callback, telemetry, and regression-observability workflows for Mission Control agents.
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…
Use when a new Codex chat needs to reconnect to a recent Mission Control orchestration safely.
Route TensorFlow Lite export and edge-readiness checks through Mission Control with explicit artifact and constraint validation.
Design retrieval, indexing, chunking, ranking, and RAG workflows through Mission Control. Use for docs search, code search, semantic recall, and context-pack construction.
Use when Codex should refresh an existing Mission Control install, resync the plugin and skills, and rerun headless repair/bootstrap.
Switch Mission Control toward local-first behavior. Use when the user wants local files, local models, no cloud deployment, and no external APIs unless explicitly approved.
Route KerasTuner and other bounded hyperparameter searches through Mission Control with explicit budgets and evidence.
Route TensorFlow and Keras project scaffolding through Mission Control with explicit validation, export, and product-readiness expectations.
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…
Use when the user wants the final Mission Control handoff, evidence summary, and next steps.
Generate a guided onboarding tour for a codebase using Mission Control's project map, domains, commands, risks, and recommended reading order.
Show important Mission Control decisions and assumptions. Use when the user wants to review user decisions, Manager assumptions, auto-decisions, rejected options, or approval…
Use or explain API-provider mode through Mission Control. Use when the user explicitly wants API-backed execution, needs billing implications explained, or wants confirmation that…
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…
Prepare Mission Control docs for public GitHub. Use when documentation should be cleaned for publication, internal AI notes removed, secrets and private paths scrubbed, and…
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…
Diagnose Mission Control daemon, MCP, plugin, runtime, and runner health from Codex chat.
Use when the user wants Mission Control to operate in a stricter approval-heavy safety posture.
Route capture, reconstruction, and spatial-ingest workflows through Mission Control with explicit data quality, reconstruction, and evidence boundaries.
Ask Mission Control for a security review. Use when the user wants secrets risk, auth risk, dependency risk, command safety, file permission risk, deployment exposure, risky code…
Route TensorFlow SavedModel and serving-export work through Mission Control with explicit artifact and API validation.
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…
Coordinate Nsight-based GPU profiling through Mission Control with safe evidence capture and approval-aware command use.
Use Mission Control to design or repair tf.data pipelines with explicit throughput, caching, and validation evidence.
Coordinate document, PDF, Word, slide, spreadsheet, and report workflows through Mission Control. Use for document generation, conversion plans, extraction, validation, and…
Plan creative web artifacts, themed pages, demos, and visual prototypes through Mission Control while preserving project guardrails and validation.
Plan or run web application testing through Mission Control. Use for local browser smoke tests, console errors, accessibility checks, screenshots, and regression validation.
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…
Show or build Mission Control context packs for agents. Use when the user wants to know which files, docs, and constraints are being packaged for a task, why they were selected,…
Use when Codex should remove the Mission Control plugin bundle, synced skills, and managed Codex MCP registration.
Use when Codex should retrieve Mission Control status, evidence, and final handoff notes for review with the user.
Build or inspect a Mission Control codebase knowledge graph. Use for file/function/class maps, dependency relationships, architectural layers, guided tours, and searchable…
Analyze the impact of current changes or a pull request through Mission Control. Use for ripple effects, affected tests, ownership, risk, and review focus.
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…
Run a safe Mission Control refactor workflow. Use when the user wants non-trivial refactors that need codebase understanding, snapshots, path locks, contracts, validation…
Use when Mission Control should recommend a read-only failure diagnosis burst across logs, recent changes, tests, dependencies, and recovery planning.
Explain an unfamiliar codebase from Mission Control understanding. Use when the user wants stack detection, structure, entry points, how it likely runs, how tests work, risky…
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…
Install or repair Mission Control for headless Codex use from a repo checkout or GitHub clone.
Route spatial and 3D asset-pipeline work through Mission Control with explicit ingest, conversion, validation, and evidence boundaries.
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…
Review Mission Control testing coverage and status. Use when the user wants to know what tests exist, what ran, what failed, what was skipped, or where validation coverage is…