com um clique
are-rebuild
Reconstruct project from specification documents (experimental)
Instalar com Codex ou Claude Copie este prompt, cole no Codex, Claude ou outro assistente e deixe que ele revise a página da skill e instale para você.
Menu
Reconstruct project from specification documents (experimental)
Instalar com Codex ou Claude Copie este prompt, cole no Codex, Claude ou outro assistente e deixe que ele revise a página da skill e instale para você.
Baseado na classificação ocupacional SOC
Show available ARE commands and usage guide
Show telemetry dashboard (costs, tokens, traces) (experimental)
Execute implementation with and without ARE documentation (experimental)
Compare AI planning quality with and without ARE documentation (experimental)
Generate project specification from AGENTS.md docs (experimental)
Delete all generated documentation artifacts (.sum, AGENTS.md, plan)
| name | are-rebuild |
| description | Reconstruct project from specification documents (experimental) |
| disable-model-invocation | true |
Reconstruct a project from specification documents using agents-reverse-engineer.
Run the rebuild command in the background and monitor progress in real time.Read version: Read .claude/ARE-VERSION → store as $VERSION. Show the user: agents-reverse-engineer v$VERSION
Run the rebuild command in the background using run_in_background: true:
npx agents-reverse-engineer@$VERSION rebuild --backend claude $ARGUMENTS
Monitor progress by polling the latest progress log:
sleep 15 in Bash), then use Glob to find the latest .agents-reverse-engineer/progress-*.log file, and Read it (use the offset parameter to read only the last ~20 lines for long files)TaskOutput with block: falseOn completion, read the full background task output and summarize:
This reads spec files from specs/, partitions them into ordered rebuild units, and processes each via AI to generate source files.
Options:
--dry-run: Show rebuild plan without making AI calls--output <path>: Output directory (default: rebuild/)--force: Wipe output directory and start fresh--concurrency N: Control number of parallel AI calls (default: auto)--fail-fast: Stop on first failure--debug: Show AI prompts and backend details--trace: Enable concurrency tracing to .agents-reverse-engineer/traces/Exit codes: 0 (success), 1 (partial failure), 2 (total failure)