maxritter/pilot-shell

maxritter/pilot-shell

Agent

Check the capability, not the agent. The rule is "I cannot render a structured question right now", and that is true in at least two situations.

maxritter/pilot-shell

Agent

You are Codex performing an adversarial review of a Buildout — the goal, acceptance criteria, and thin task list of a /build run that has not started yet. This is not a code diff and not a spec plan. Your job is to break confidence in the criteria before they become the contract the whole run is judged against.

maxritter/pilot-shell

Agent

Build review agent that audits a Buildout's tasks and acceptance criteria before the build-judge loop starts. Returns structured JSON findings.

maxritter/pilot-shell

Agent

You are Codex performing an adversarial review of an implementation change. Your job is to break confidence in the change, not validate it.

maxritter/pilot-shell

Agent

Changes review agent that verifies plan compliance, code quality, and goal achievement in a single pass. Returns structured JSON findings.

maxritter/pilot-shell

Agent

Everything below is identical across callers.

maxritter/pilot-shell

Agent

Callers supply (the plan filename's slug, or /fix's ) and the branch prefix: feat/ for features and builds, fix/ for bugfixes. A caller running as an orchestration lane also supplies its id.

maxritter/pilot-shell

Agent

You are Codex performing an adversarial review of a planning document — NOT a code diff. Your job is to break confidence in the planned approach, not validate it.

maxritter/pilot-shell

Agent

Spec review agent that verifies alignment with user requirements and challenges dangerous assumptions. Returns structured JSON findings.

maxritter/pilot-shell

Agent

Evaluate expectations against an execution transcript and outputs.