Use when existing project documentation must be discovered and converted into colony context
Structured code debugging through hypothesis formation and falsification planning. Use when diagnosing bugs, unexpected behaviour, or system failures where the root cause is…
Use when an external PRD, roadmap, spec, or plan must be imported into colony planning safely
Use when a phase involves LLMs, AI agents, RAG, ML inference, or prompt/tool integration design
Use when producing command output, handling state transitions, or routing users to the next action in the colony workflow
Use when Codex is asked to plan, build, continue, or seal an Aether colony and must mirror wrapper orchestration safely
Use when verified work is ready to become a clean pull request and release-ready branch
Use before planning to surface hidden assumptions that could cause expensive wrong turns
Use when starting, completing, archiving, or transitioning milestones between project stages
Use when external library, framework, API, or architecture research must be isolated from implementation context
Use when frontend work needs an explicit UI, interaction, accessibility, and responsive design contract before implementation
Use when producing any user-facing output including banners, progress indicators, section headers, or command results
Use when acceptance criteria need unit, integration, or end-to-end tests generated from implementation context
Use when phase or task ordering needs dependency, overlap, or blast-radius analysis
Use when reading or writing JSON state files including COLONY_STATE.json, pheromones.json, constraints.json, or session.json
Use when delivered functionality needs acceptance-criteria verification before a phase advances
Use when completed work needs evaluation coverage audited across correctness, security, performance, and quality dimensions
Use when Codex is asked to run Aether Oracle or discuss flows and should refine scope before research or clarification
Colony health diagnostics and repair — healthy state specifications for all colony data files, failure modes, and remedies
Use when reverting phase or implementation work requires dependency-aware rollback and recovery planning
Use when a plan or high-risk approach needs independent review from another model or CLI
Use when pheromone signals are present in your assembled context and you need to interpret and comply with them
Use when a phase, build, continue, or colony workflow failed and needs evidence-based post-mortem analysis
Use when GitHub issues and pull requests need triage against colony priorities before planning
Use when starting work as a spawned worker to understand what context you have been given and how to use it
Use when a future idea should be captured with trigger conditions rather than forced into the active phase
Use when acceptance criteria or UAT gaps need to be scanned across phases before milestone closure
Use when Codex is asked to initialize or set up an Aether colony and should refine intent before running init
Use when performing any pheromone operation including creating, reinforcing, expiring, or auto-emitting signals during builds and continues
Use when a phase needs falsifiable requirements or ambiguity reduction before planning or building
Use when a worker needs a quick targeted codebase scan before planning or implementation
Use when a session needs a concise report of work completed, outcomes, and follow-up state
Use when a rough idea needs structured exploration before it becomes a plan, spike, backlog item, or quick task
Use when the colony needs a complete multi-perspective map of a complex codebase
Use when implemented frontend work needs a visual, accessibility, responsiveness, performance, and interaction audit
Use when executing commands that involve major decisions, plan commits, build starts, verifications, or phase advances
Use when stale or completed colony artifacts need safe archival, cleanup, or retrieval without losing evidence
Use when a phase needs implementation context, file inventory, or gray-area analysis before work proceeds
Use when completed work should produce reusable decisions, lessons, surprises, and patterns for future phases
Use when a technical unknown needs a small throwaway experiment before committing to a plan
Use when a milestone audit reveals gaps that need to become concrete follow-up phases
Use when implementation exists but tests or validation evidence are missing or incomplete
Use before sealing a milestone to compare original intent with delivered work, quality, and remaining gaps
Use when cross-cutting investigations or decisions need a persistent thread across sessions and phases
Use when an operation fails, an error occurs, or a warning needs to be communicated to the user
Use when UI or interaction ideas need throwaway visual prototypes before implementation decisions are locked