AI Agent Workflow Collection

Route 3D visual-regression and render-diff work through Mission Control with explicit evidence targets and scene-aware validation.

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 conditions, or escalation rules.

Design graph-style agent workflows with nodes, edges, gates, retries, checkpoints, and human approvals through Mission Control.

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.

Use when Codex should generate or review AGENTS.md through Mission Control context and explicit user 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 configured secret storage rather than chat-provided keys will be used.

Use when Mission Control needs a user approval or manager-question answer relayed through Codex chat.

Compare before-and-after performance evidence through Mission Control without turning benchmark claims into theater.

Route Blender headless render and validation work through Mission Control with explicit external-runtime blockers and evidence loops.

Coordinate brand-guideline, internal-communications, announcement, and stakeholder-message work through Mission Control with tone, audience, and evidence constraints.

Use when Codex should relay user intent to Mission Control instead of acting as the Manager itself.

Route capture, reconstruction, and spatial-ingest workflows through Mission Control with explicit data quality, reconstruction, and evidence boundaries.

Run a post-handoff or mid-project Mission Control change request flow. Use when the user wants additional work classified, impact-estimated, task-created, validated, and folded into the current handoff or milestone safely.

Use or prefer Claude CLI runner mode through Mission Control. Use when the user explicitly wants Claude CLI if configured and Codex should verify availability and fallback rather than assuming setup exists.

Use when Mission Control should recommend a read-only codebase intake burst with Repo Mapper, Test Finder, Docs Reader, Risk Scanner, and Dependency Mapper.

Build or inspect a Mission Control codebase knowledge graph. Use for file/function/class maps, dependency relationships, architectural layers, guided tours, and searchable understanding.

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 subscription auth and API-based providers kept clear.

Request compiler and autotuning guidance for GPU code through Mission Control with bounded iteration and evidence requirements.

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 hidden reassignment.

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, and where context coverage is still missing.

Continue work after a Mission Control handoff without losing continuity. Use when the user wants another iteration, wants limitations preserved, or needs the next change request to build on the previous handoff and evidence.

Plan creative web artifacts, themed pages, demos, and visual prototypes through Mission Control while preserving project guardrails and validation.

Route CUDA kernel generation or repair through Mission Control with GPU-aware validation and infrastructure checks.

Use when CUDA Tile or tile-shaped GPU refactors need Mission Control planning, validation, and benchmark discipline.