Clarify mode
Frame the question, decision, or workflow before producing output so the deliverable serves the real business need.
Ambiguous requests, incomplete data, stakeholder alignment
Modes
Choose the operating surface before choosing the prompt.
CodexKit is built around the idea that most work mistakes start from using the wrong mode: drafting before clarifying the decision, reviewing without a risk model, or delegating work that should have stayed on the critical path.
Execute mode
Turn inputs into a concrete deliverable such as a plan, brief, analysis, template, operating pack, or code change with scoped verification.
Drafting, synthesis, implementation, analysis
Review mode
Audit a document, workflow, metric pack, deliverable, or code change with a findings-first risk model.
QA, approvals, red-team checks, release readiness
Decision mode
Reduce options, compare tradeoffs, and recommend a path leaders or operators can act on quickly.
Budget, vendor, policy, project, and strategy choices
Delegation mode
Break a larger problem into bounded Codex jobs or parallel workstreams with explicit ownership and integration points.
Parallelizable work that does not share a write scope
Automations
Schedule recurring Codex work with prompts, cadence, owners, and low-noise guardrails.
Recurring reporting, risk checks, documentation drift, routine analysis
Install skills
Attach reusable operating knowledge to the modes your team uses most.
Use playbooks
Bring the same structure to ChatGPT or other non-local workflows.