governance: adopt TDD with full unit/integration tests; update system prompt and AGENTS templates\n\nplan: add TDD milestones and test coverage criteria; update proposal accordingly

collab/plan/01-codexhelper.llm.md

@@ -2,15 +2,16 @@
 
 - Scope: Phase 1 (Crawl) MVP for `CodexHelper` with subcommands, scaffolding, prompt composition, config precedence, and safety.
 
-- Milestones:
-  1) CLI skeleton + guardrails
-  2) Binary detection + pass-through flags
-  3) new-mode scaffolder (repo-only)
-  4) new-project scaffolder (outside repo)
-  5) run: compose prompts + invoke codex
-  6) Config precedence (YAML+yq)
-  7) Templates + copies (AGENTS.md, prompts/_mode)
-  8) Docs: README quickstart + wrapper usage
+- Milestones (TDD for each step):
+  0) Test harness setup (bats-core), tests/ structure, CI script (local)
+  1) CLI skeleton + guardrails (write failing tests first)
+  2) Binary detection + pass-through flags (tests first)
+  3) new-mode scaffolder (repo-only) (tests first)
+  4) new-project scaffolder (outside repo) (tests first)
+  5) run: compose prompts + invoke codex (tests first)
+  6) Config precedence (YAML+yq) (tests first)
+  7) Templates + copies (AGENTS.md, prompts/_mode) (tests first)
+  8) Docs: README quickstart + wrapper usage (ensure examples validated by tests where feasible)
 
 - Key rules honored:
   - One-way workflow; minimal chat; read `.llm.md`, write both.
@@ -23,6 +24,7 @@
   - `templates/project/_shared/AGENTS.md` (copy into project root)
   - `templates/project/<ModeName>/...` (optional mode-specific add-ons; start minimal)
   - `docs/wrapper.md` and README updates
+  - Test harness (`bats`), `tests/` with coverage of all CLI paths
 
 - Implementation details:
   - Guard where running: inside repo → only `new-mode` allowed.
@@ -38,11 +40,12 @@
   - `run` composes prompts and calls detected binary; artifacts under `runs/<ts>/`.
   - Precedence: CLI > env > project > mode > global.
   - `prompts/global/` used in composition.
+  - Tests: all features covered by unit/integration tests (bats); TDD observed (tests committed alongside implementation); CI/local test script present.
 
 - Open choices (defaulting now):
   - Include empty `prompts/style.md`: Yes.
   - Config format: YAML only; tool: yq.
   - Project `.gitignore`: include `runs/` and any `*.llm.*` if user prefers later (for now, only `runs/`).
+  - Test framework: bats-core for bash; simple runner `scripts/test.sh`.
 
 - Next: Implement per milestones; add concise README quickstart.
-