humanize-rlcr: Скилл для улучшения кода

--- name: humanize-rlcr description: Start RLCR (Ralph-Loop with Codex Review) with hook-equivalent enforcement from skill mode by reusing the existing stop-hook logic. type: flow user-invocable: false disable-model-invocation: true --- # Humanize RLCR Loop (Hook-Equivalent) Use this flow to run RLCR in environments without native hooks. Do not re-implement review logic manually. Always call the RLCR stop gate wrapper: ```bash "{{HUMANIZE_RUNTIME_ROOT}}/scripts/rlcr-stop-gate.sh" ``` The wrapper executes `hooks/loop-codex-stop-hook.sh`, so skill-mode behavior stays aligned with hook-mode behavior. ## Runtime Root The installer hydrates this skill with an absolute runtime root path: ```bash {{HUMANIZE_RUNTIME_ROOT}} ``` All commands below assume `{{HUMANIZE_RUNTIME_ROOT}}`. ## Required Sequence ### 1. Setup Start the loop with the setup script: ```bash "{{HUMANIZE_RUNTIME_ROOT}}/scripts/setup-rlcr-loop.sh" $ARGUMENTS ``` If setup exits non-zero, stop and report the error. ### 2. Work Round For each round: 1. Read current loop prompt from `.humanize/rlcr/<timestamp>/round-<N>-prompt.md` (or `finalize` prompt files when in finalize phase). 2. Implement required changes. 3. Commit changes. 4. Write required summary file: - Normal phase: `.humanize/rlcr/<timestamp>/round-<N>-summary.md` - Finalize phase: `.humanize/rlcr/<timestamp>/finalize-summary.md` 5. Run gate command: ```bash GATE_CMD=("{{HUMANIZE_RUNTIME_ROOT}}/scripts/rlcr-stop-gate.sh") [[ -n "${CLAUDE_SESSION_ID:-}" ]] && GATE_CMD+=(--session-id "$CLAUDE_SESSION_ID") [[ -n "${CLAUDE_TRANSCRIPT_PATH:-}" ]] && GATE_CMD+=(--transcript-path "$CLAUDE_TRANSCRIPT_PATH") "${GATE_CMD[@]}" GATE_EXIT=$? ``` 6. Handle gate result: - `0`: loop is allowed to exit (done). - `10`: blocked by RLCR logic. Follow returned instructions exactly, continue next round. - `20`: infrastructure error (wrapper/hook/runtime). Report error, do not fake completion. ## What This Enforces By routing through the stop-hook logic, this skill enforces: - state/schema validation (`current_round`, `max_iterations`, `review_started`, `base_branch`, etc.) - branch consistency checks - plan-file integrity checks (when applicable) - incomplete Task/Todo blocking - git-clean requirement before exit - `--push-every-round` unpushed-commit blocking - summary presence checks - max-iteration handling - full-alignment rounds (`--full-review-round`) - strict `COMPLETE`/`STOP` marker handling - review-phase transition guard (`.review-phase-started` marker) - code-review gating on `[P0-9]` markers - hard blocking on codex review failure or empty output - open-question handling when `ask_codex_question=true` ## Critical Rules 1. Never manually edit `state.md` or `finalize-state.md`. 2. Never skip a blocked gate result by declaring completion manually. 3. Never run ad-hoc `codex exec` / `codex review` in place of the gate for phase transitions. 4. Always use files generated by the loop (`round-*-prompt.md`, `round-*-review-result.md`) as source of truth. ## Options Pass these through `setup-rlcr-loop.sh`: | Option | Description | Default | |--------|-------------|---------| | `path/to/plan.md` | Plan file path | Required unless `--skip-impl` | | `--plan-file <path>` | Explicit plan path | - | | `--track-plan-file` | Enforce tracked plan immutability | false | | `--max N` | Maximum iterations | 42 | | `--codex-model MODEL:EFFORT` | Codex model and effort for `codex exec` | gpt-5.4:high | | `--codex-timeout SECONDS` | Codex timeout | 5400 | | `--base-branch BRANCH` | Base for review phase | auto-detect | | `--full-review-round N` | Full alignment interval | 5 | | `--skip-impl` | Start directly in review path | false | | `--push-every-round` | Require push each round | false | | `--claude-answer-codex` | Let Claude answer open questions directly | false | | `--agent-teams` | Enable agent teams mode | false | | `--yolo` | Skip quiz and enable --claude-answer-codex | false | | `--skip-quiz` | Skip Plan Understanding Quiz (implicit in skill mode) | false | Review phase `codex review` runs with `gpt-5.4:high`. ## Usage ```bash # Start with plan file /flow:humanize-rlcr path/to/plan.md # Review-only mode /flow:humanize-rlcr --skip-impl # Load skill without auto-execution /skill:humanize-rlcr ``` ## Cancel ```bash "{{HUMANIZE_RUNTIME_ROOT}}/scripts/cancel-rlcr-loop.sh" ```