diff options
| -rw-r--r-- | .claude/commands/start-work.md | 3 | ||||
| -rw-r--r-- | todo.org | 3 |
2 files changed, 4 insertions, 2 deletions
diff --git a/.claude/commands/start-work.md b/.claude/commands/start-work.md index abbee3e..0143a1f 100644 --- a/.claude/commands/start-work.md +++ b/.claude/commands/start-work.md @@ -159,7 +159,8 @@ Then produce a justification that covers all of these, concisely: 6. **Urgency and priority fit.** Does this align with current goals or an upcoming deadline? If the project has committed deadlines, explicitly check this against them. Anything not obviously on the critical path should be called out as "deferrable." 7. **Effort estimate.** S (under 1 hour), M (1 hour to 1 day), L (over 1 day). Rough is fine. 8. **Alternatives considered.** Is there a cheaper way? Can we defer? Can we address the root cause via a different path? -9. **Ticket quality check.** Is scope clear, are acceptance criteria concrete, are reproduction steps present for bugs? If **not clear**, stop and ask the user to choose one of: +9. **Reasons not to do this.** A forced devil's-advocate verdict on whether the work should happen at all — distinct from Downsides (what the change costs) and Alternatives (cheaper paths). Surface the top three objections if real ones exist; when none rise to a genuine objection, say so in one line rather than manufacturing three (e.g. "Nothing material argues against this. No reason to defer or drop it."). Building the case against the work is cheapest at this gate, which is its purpose. +10. **Ticket quality check.** Is scope clear, are acceptance criteria concrete, are reproduction steps present for bugs? If **not clear**, stop and ask the user to choose one of: - (a) Bounce to `/brainstorm` to refine the ticket first. - (b) Ping the ticket author for clarification. - (c) Supply the missing info themselves right now, if it is easy for them to do so. @@ -49,7 +49,8 @@ From an .emacs.d handoff (2026-06-02): running task-audit against a large todo.o 1. =lint-org= workflow/script (the real fix): reconcile-on-write. Before appending a run, drop entries whose finding no longer reproduces (dead link now resolves, flagged block/timestamp now clean) and dedupe against the prior run instead of re-logging. Key entries by content/finding rather than line number, so they survive edits to the target file (line numbers go stale immediately). 2. =task-audit.org= (small, narrow): in the Phase C link-hygiene step, when fixing/verifying a =file:= link, also reap any matching dead-link entry in the project's lint-followups file so the two artifacts don't drift. Scope explicitly to dead-link entries — do NOT pull general lint cleanup into the audit; that mixes two concerns and slows the audit. -** TODO [#C] start-work Justify gate: explicit "reasons not to do this" item :feature:quick:solo: +** DONE [#C] start-work Justify gate: explicit "reasons not to do this" item :feature:quick:solo: +CLOSED: [2026-06-02 Tue] :PROPERTIES: :LAST_REVIEWED: 2026-06-02 :END: |