fix(respond-to-cj-comments): keep top/second-level tasks as DONE

Only third-level and deeper tasks get the dated-heading rewrite. Top and second-level stay task-shaped so they remain visible in the agenda.

1 files changed, 7 insertions, 2 deletions

diff --git a/.claude/commands/respond-to-cj-comments.md b/.claude/commands/respond-to-cj-comments.md
index 01a76ac..0f05455 100644
--- a/.claude/commands/respond-to-cj-comments.md
+++ b/.claude/commands/respond-to-cj-comments.md
@@ -1,5 +1,5 @@
 ---
-description: Scan a target file for inline `cj:` annotations (Craig's in-line questions and instructions; multi-line continuations recognized across most comment markers) and process each via subagent-delegated accuracy. Each item is classified instruction / question / both, then dispatched to an instruction subagent (proposes a file:line patch) or a question subagent (researches with explicit scope, reports answer + evidence + confidence). Main thread reviews proposals before editing — subagents don't write to the source file. Org-mode TODO parents flip to DOING; new content lands under timestamped subheadings one level deeper; completed tasks get their heading rewritten to a dated action description (no DONE keyword) so they become an in-place event log. Public-facing writing (commits, PRs, Slack, email, public docs) gets `/voice personal`; private writing skips the voice pass. Summary lists handled instructions, answered questions with evidence + confidence, follow-ups, unresolved items, and an explicit clean / N-remain verdict. Anything needing Craig's input becomes a `STALLED` task in `todo.org` under the relevant parent (he answers inline with `cj:`) rather than a separate summary file. File/URL references render as clickable org-mode links. Use when a file accumulates inline `cj:` comments. Do NOT use for general code review (`/review-code`), new work without inline comments, or trivial items.
+description: Scan a target file for inline `cj:` annotations (Craig's in-line questions and instructions; multi-line continuations recognized across most comment markers) and process each via subagent-delegated accuracy. Each item is classified instruction / question / both, then dispatched to an instruction subagent (proposes a file:line patch) or a question subagent (researches with explicit scope, reports answer + evidence + confidence). Main thread reviews proposals before editing — subagents don't write to the source file. Org-mode TODO parents flip to DOING; new content lands under timestamped subheadings one level deeper; on completion, top and second-level tasks advance to `DONE` while third-level-and-deeper tasks get their heading rewritten to a dated action description (no DONE keyword) so they become an in-place event log. Public-facing writing (commits, PRs, Slack, email, public docs) gets `/voice personal`; private writing skips the voice pass. Summary lists handled instructions, answered questions with evidence + confidence, follow-ups, unresolved items, and an explicit clean / N-remain verdict. Anything needing Craig's input becomes a `STALLED` task in `todo.org` under the relevant parent (he answers inline with `cj:`) rather than a separate summary file. File/URL references render as clickable org-mode links. Use when a file accumulates inline `cj:` comments. Do NOT use for general code review (`/review-code`), new work without inline comments, or trivial items.
 disable-model-invocation: true
 ---
 
@@ -128,7 +128,12 @@ For **instructions**:
 
 4. **Surface URLs.** If the subagent's output includes URLs, file paths, or external references, list them under the updated task content. After applying the edit, offer to convert them into explicit org-mode links (`[[url][label]]` or `[[file:path][label]]`) at the location where the `cj:` comment originated, or elsewhere in the task if that fits better.
 
-5. If the comment is inside an org-mode `TODO` heading, mark that `TODO` as `DOING` when work begins. **When the work is complete, do not advance it to `DONE`** — rewrite the heading itself into a timestamped action description and drop the keyword: `** YYYY-MM-DD Day @ HH:MM:SS -ZZZZ <what was decided / done>` (generate the timestamp with `date "+%Y-%m-%d %a @ %H:%M:%S %z"`). The CLOSED line and the keyword go away; the task heading becomes a permanent event-log entry in place. Keep the task's body/sub-headers as the record of what it was. This is Craig's convention for all `todo.org` files (and his prep docs) — finished tasks turn into a dated log automatically. (Feedback memory: `feedback_done_tasks_become_dated_log_headings`.) Leave a still-in-progress task as `DOING` for the user; only the *completed* ones get the dated-heading rewrite.
+5. If the comment is inside an org-mode `TODO` heading, mark that `TODO` as `DOING` when work begins. **When the work is complete, the form depends on heading depth:**
+
+   - **Top-level (`*`) and second-level (`**`)** tasks advance to `DONE` with a `CLOSED: [YYYY-MM-DD Day HH:MM]` line under the heading. The keyword and original task name stay visible so the task remains in the agenda.
+   - **Third-level (`***`) and deeper** tasks get the dated-heading rewrite: replace the heading line with `*** YYYY-MM-DD Day @ HH:MM:SS -ZZZZ <what was decided / done>` (generate the timestamp with `date "+%Y-%m-%d %a @ %H:%M:%S %z"`); drop the keyword and CLOSED line. The body/sub-headers stay as the record of what was done. These deeper tasks become an in-place event log under their parent.
+
+   Craig's convention for `todo.org` and prep docs: top and second-level remain task-shaped so they stay visible in the agenda; only sub-tasks under a parent flip into a dated log. (Feedback memory: `feedback_done_tasks_become_dated_log_headings`.) Leave a still-in-progress task as `DOING` for the user; only the *completed* ones get the `DONE`-or-dated-rewrite.
 
 6. Remove the `cj:` comment from the file (the entire contiguous block, including continuation lines).