plan-wraplisted

# Clean-Context Check Read a document (ask the user for the path if not obvious) and determine whether a model with **zero prior context** — no conversation history, no other files — could read it and act on it correctly. Note this differs from `plan-review`, which checks for technical gaps. This skill checks for *self-sufficiency*: everything needed to understand and act on the document must be present inside it. ## Arguments | Arg | Required | Default | Description | |---|---|---|---| | `--autofix` | no | true (default ON) | Auto-apply fixes that don't need user judgment (missing schema summaries, bare `<id>` placeholders, operator+code splits, placeholder Condition:). Findings requiring judgment are still surfaced under "Needs your input:". | | `--no-autofix` | no | -- | Opt out of autofix. Surface ALL findings as recommendations; do not modify plan.md. For operators who want to review before applying. | --- ## Proof discipline Always cite the specific section, line, or phrase in the document that triggered the finding: - Do not state "schemas are missing" without quoting the entity name that lacks a schema. - Do not state "this term is unexplained" without quoting the term and where it first appears. - Findings without citations will be treated as unsubstantiated. Use this three-line shape for findings: ```markdown **[Severity]** §<n> — <what is missing> Found at: "<quoted phrase>" (Step N, <subsection>) Fix: <concrete suggestion> ``` ## Completion gate (run fi