@ai-content-space/loopx 0.2.4 → 0.2.8

package/docs/loopx/design/loopx-skill-suite-v1-design.md

@@ -10,7 +10,7 @@ The v1 product surface is the installed and governed bundled skill suite:
 
 - `clarify`
 - `spec`
-- `plan`
+- `plan-to-exec`
 - `subagent-exec`
 - `exec`
 - `review`
@@ -33,12 +33,12 @@ The repository may retain auxiliary or compatibility skill source directories fo
 Recommended flow:
 
 ```text
-clarify -> spec? -> plan -> (subagent-exec | exec) -> final-review -> fix-review? -> finish
+clarify -> spec? -> plan-to-exec -> (subagent-exec | exec) -> final-review -> fix-review? -> finish
 ```
 
-`spec` is a conditional design gate. `clarify` may route directly to `plan` when the remaining questions are local implementation choices. It routes to `spec` when product behavior, APIs, state, data, permissions, migration, compatibility, or architecture decisions need to be fixed before implementation planning.
+`spec` is a conditional design gate. `clarify` may route directly to `plan-to-exec` when the remaining questions are local implementation choices. It routes to `spec` when product behavior, APIs, state, data, permissions, migration, compatibility, or architecture decisions need to be fixed before implementation planning.
 
-`plan` is the superpowers `writing-plans` workflow under the loopx name. It writes executable plans and offers two execution options: `subagent-exec` recommended, or `exec` inline.
+`plan-to-exec` is the superpowers `writing-plans` workflow under the loopx name. It writes executable plans and offers two execution options: `subagent-exec` recommended, or `exec` inline.
 
 `review` is the task or checkpoint code review workflow inside `subagent-exec` or `exec`. `final-review` is the top-level whole-feature runtime, integration, and test-gap review before completion. `fix-review` handles feedback from either review layer.
 

package/docs/loopx/memory/2026-06-09-stale-archive-hook-guidance.md

@@ -0,0 +1,15 @@
+# Stale Archive Hook Guidance
+
+Type: pitfall
+Domain: workflow hooks
+Date: 2026-06-09
+
+When removing a public workflow command, update generated guidance and also filter persisted runtime guidance. Old `.loopx/workflows/*/state.json` files can keep `recommended_next_action` text that outlives the current product flow.
+
+Evidence from `5285f99..1f11966`:
+
+- `scripts/codex-workflow-hook.mjs` and `scripts/claude-workflow-hook.mjs` now suppress stale `loopx archive` and `$archive` recommendations.
+- Done/archive/completed stale archive recommendations map to `$finish`.
+- Approved review stale archive recommendations map to `loopx approve <slug> --from review --to done`.
+- `test/trellis-hardening.test.mjs` covers both stale done and stale approved-review hook states.
+

package/docs/loopx/memory/README.md

@@ -0,0 +1,25 @@
+# Shared Memory
+
+`docs/loopx/memory/` is git-tracked shared memory for lightweight project knowledge that should follow a user across machines, but is not stable enough to become a spec.
+
+Use shared memory for concise, evidence-backed notes such as:
+
+- recurring project-specific pitfalls
+- agent handoff details that remain useful across sessions
+- personal or team working conventions that are not yet formal rules
+- context that helps avoid repeated investigation
+
+Do not use shared memory for:
+
+- temporary runtime state
+- raw conversation logs
+- secrets, credentials, or machine-local paths
+- stable workflow, API, migration, testing, or compatibility rules that belong in `docs/loopx/specs/`
+
+Memory layers:
+
+- `.loopx/memory/`: local memory, not tracked by git
+- `docs/loopx/memory/`: shared memory, tracked by git
+- `docs/loopx/specs/`: stable team rules, tracked by git
+
+Promote shared memory to `docs/loopx/specs/` when it becomes a durable rule that planning or review should depend on.