review-planlisted

# /ogre:review-plan Use this skill after an execution plan exists and before implementation starts. ## Inputs Accept: - Issue number, e.g. `107` - Plan name, e.g. `issue-107` - Plan path, e.g. `.ai/.ogre/plans/issue-107.md` Optional flags: - `--reviewer claude|codex` - `--model MODEL` - `--reasoning LEVEL` (reasoning effort for the reviewer; omit to use the CLI's own default) - `--main` — run the review inline in this session instead of spawning an isolated subprocess (loses context isolation; only pass when the user explicitly wants that). - `--background` — spawn the isolated subprocess detached; returns immediately instead of waiting for the review to finish. - `--live` — opt-in, off by default. Runs the reviewer with `--json`/`--output-format stream-json --verbose` instead of plain text, writing raw JSONL to the log path. Only use when the user explicitly wants to watch the review happen live — see `/ogre:rescue`'s "Watching a `--live` rescue live" section for the Monitor+jq recipe (same recipe, against `review-plan`'s own log path). **Flags are forwarded verbatim, never reinterpreted.** `-r` is `--reviewer` and `-R` is `--reasoning` (reviewer got the lowercase letter since it's the one used regularly - this was previously swapped, a real bug, fixed). `-m`/`-M` (`--model`/`--main`) still differ only by case with unrelated meanings, so a wrong guess there is silent (no parse error, just wrong behavior). If the user's own message names an actual flag/short-form, pass