From dacadba07f95ec6208fafe8047ab01de29942886 Mon Sep 17 00:00:00 2001 From: Brummel Date: Tue, 7 Jul 2026 11:47:03 +0200 Subject: [PATCH] docs(fragment): stop re-seeding the spec/plan lifecycle restatement The 'Spec/plan artefacts are ephemeral' section duplicated conventions.md (sections File layout + Lifecycle) and re-seeded that restatement into every new consumer CLAUDE.md - the drift vector that let projects diverge on git-tracked vs git-ignored. The rule now lives once, in conventions.md; the fragment's documented building-block list never included this section anyway. --- templates/CLAUDE.md.fragment | 15 --------------- 1 file changed, 15 deletions(-) diff --git a/templates/CLAUDE.md.fragment b/templates/CLAUDE.md.fragment index 294514e..35069b4 100644 --- a/templates/CLAUDE.md.fragment +++ b/templates/CLAUDE.md.fragment @@ -65,21 +65,6 @@ Two rules govern who touches git history and how: when I have run into a dead end. A pushed commit has left the sandbox and is forward-only (`git revert`). -## Spec/plan artefacts are ephemeral - -`docs/specs/` and `docs/plans/` hold only the active cycle's spec and -plan, and they are **git-ignored** — never committed. This repo carries -a committed `docs/.gitignore` with the two entries `specs/` and `plans/` -(relative to `docs/`); that ignore file is the only committed part — the -spec and plan files it covers never are. If `docs/.gitignore` is missing -when the first working file is written, the writing skill creates it. -Each spec / plan is a working file: present on disk for its own cycle, -read across sessions from the working tree, and shell-`rm`'d at cycle -close by `audit` — never `git rm`'d, since it was never tracked, so no -git-history copy survives. The durable record of a past cycle is the -design ledger only, and no durable artefact cites a spec/plan by number -or path (see `~/dev/skills/docs/conventions.md` § Lifecycle). - ## Design rationale ≠ implementation effort When picking between design options, the rationale must come