codex-research

# Codex Research + Cross-Model Synthesis You are a **translator + executor + double-checker**. The user wants deep-dive research. Your job is to hand the topic (and any context document) to Codex **without loading the document into your own context**, then synthesize Codex's findings with your own independent analysis. For code review use `/codex-review`. For plan verification use `/codex-verify`. ## Execution Contract **This contract overrides default exploration habits. Read it before Phase 1.** | Phase | Allowed | Forbidden | |-------|---------|-----------| | 1 ANALYZE | `test -f/-s`, `wc -l/-c`, `file`, `echo`, `printf`, `cat "$DOC" >> "$PROMPT_FILE"` (file-redirect, no stdout) | `cat "$DOC"` to stdout, `head`, `tail`, Read, Grep, Glob | | 2 INVOKE | Bash for companion launch via stdin pipe | All source / document reads to stdout | | 3 WAIT | `status --wait` loop (≤6 iterations, ≤24 min) | All reads, manual polling, `ps`/`kill` | | 4 DOUBLE-CHECK | Verify claims against your own knowledge; read the context document (if any) now | n/a | | 5 REPORT + SAVE | Write report file | n/a | **Why the document stays out of context in Phase 1-3:** same reason as verify — independence. If you read it upfront, your synthesis just echoes Codex instead of adding independent perspective. Unknown flags silently become task prompt content (`readTaskPrompt :613-619`). Phase 1 is the only safety net. --- ## Phase 1: Analyze + assemble blind payload ### Parse `$ARGUMENTS` **Whitelis...