Agent Workflows · By alexandremendoncaalvaro

Generate AGENTS.md at the repo root by scanning the codebase first, pre-filling placeholders from observed signals, and asking only the genuine gaps.

alexandremendoncaalvaro/CorridorKey-Runtime

Lazily create or update CONTEXT.md (Layer 2 — ubiquitous language per Evans 2003) at the repo root, or CONTEXT-MAP.md plus per-context CONTEXT.md for multi-context repos.

alexandremendoncaalvaro/CorridorKey-Runtime

Interview-before-research grilling session that challenges a fuzzy ask against the existing codebase, sharpens vocabulary against CONTEXT.md, and resolves the decision tree branch by branch.

alexandremendoncaalvaro/CorridorKey-Runtime

Compact the current session into a handoff document a fresh agent can pick up from.

alexandremendoncaalvaro/CorridorKey-Runtime

Load the practitioner's global rules — the host's CLAUDE.md or AGENTS.md, symlinks resolved — and reinforce them by listing their topics in the conversation, alongside whatever the repo and the…

alexandremendoncaalvaro/CorridorKey-Runtime

Draft a new Codex custom subagent at .codex/agents/<name.toml, using the official Codex subagents format.

alexandremendoncaalvaro/CorridorKey-Runtime

Disciplined diagnosis loop for hard bugs and performance regressions per WORKFLOW §15.

alexandremendoncaalvaro/CorridorKey-Runtime

Read-only drift audit — compare AGENTS.md, ARCHITECTURE.md, and ADR statuses against what the code actually does.

alexandremendoncaalvaro/CorridorKey-Runtime