@su-record/vibe 4.1.19 → 4.1.20

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@su-record/vibe",
-  "version": "4.1.19",
+  "version": "4.1.20",
   "description": "An AX/FDE harness for Claude Code, Codex CLI and ChatGPT desktop. Say what you need, approve the scenarios once; the harness proves the work by running the checks itself. Memory in plain files, human tokens for irreversible actions, a ledger instead of claims.",
   "type": "module",
   "bin": {

package/skills/vibe-build/SKILL.md

@@ -9,8 +9,8 @@ user-invocable: false
 ## Procedure
 
 1. Take scenarios in the order of `remaining` from `vibe state --json` — parents before their `needs` dependents (`vibe state --graph` shows the edges). Put scenarios marked `irreversible` last.
-   - Scenarios with no edge between them may be built by parallel agents, each in its own worktree, merged before `vibe check --all`. Never two agents in one working tree.
-2. Build only what that scenario needs — code, a script, a document, configuration, whatever. Make sure the check itself (`check.cmd`, `check.path`) can actually run.
+   - Scenarios with no edge between them may be built by parallel agents, each in its own worktree, merged before `vibe check --all`. Never two agents in one working tree. Batch scenarios of one shape into one dispatch; never a nested subagent (a reviewer's reviewer counts for nothing). Hand artifacts to an agent as files, never pasted. When the context is nearly full, start a new session from `.vibe/` instead of compacting.
+2. Read `vibe context {id}` first — the files and symbols the check touches, the decisions and regressions that touched them, the conventions — then build only what that scenario needs. Make sure the check itself (`check.cmd`, `check.path`) can actually run.
    - Orientation reads ("what does this module do", "where is X handled") go through `vibe read <files> --ask "<question>"` — a low-reasoning model reads and answers with line numbers; read the file yourself only to edit or debug it.
 3. Run `vibe check {id} --json`.
    - Pass (`code 0`): next scenario.

package/skills/vibe-discover/SKILL.md

@@ -8,6 +8,8 @@ user-invocable: false
 
 ## Procedure
 
+Order the questions by impact: scope first, then security and privacy, then the reader's or user's experience, then technical detail. A question further down the list is asked only when the earlier ones are settled.
+
 1. Read what the user attached through the harness, so every client sees the same thing:
    - table (csv · tsv · jsonl · json · xlsx) → `vibe profile {file} --json` [`--sheet`]: columns, types, missing counts, duplicates, up to three anomalies with numbers
    - document (xlsx · docx · pptx · pdf · hwp · hwpx · html) → `vibe read {file} --json` [`--sheet` · `--pages`]; it says which reader it used (pdf: `pdftotext` when installed, else built-in)

package/skills/vibe-prove/SKILL.md

@@ -17,3 +17,5 @@ user-invocable: false
 ## What DONE means
 
 DONE means every gate scenario passed on this exact tree. Changing any file sends the state back to RUNNING; run `vibe check --all` again.
+
+On STUCK, read `vibe context {id}` before touching anything — the decisions and regressions around that scenario are usually the reason.

package/skills/vibe-scope/SKILL.md

@@ -21,7 +21,7 @@ user-invocable: false
 3. Save with `vibe intent draft --stdin --json`, sending `{"intent": "...", "scenarios": "..."}` (both in English).
    - On rejection (`code 1`) fix the reasons and save again. Do not pass by deleting a rejected scenario — bind a check to it.
    - On success the response contains `token` when the project's token policy is `strict`; otherwise `token` is null and a plain yes in chat is enough.
-4. Research and proposals, once, before the approval message: `vibe research --from-intent --json` (up to five candidates with an action each, what moved in the last 30 days first — `--days N` for another window; skip silently on exit 2 and say "no network") and `vibe skill suggest --json` (up to three). Show both in the approval message. Do not install anything — the user says "add 1" and you run the printed `vibe skill add …` (preview first, `--yes` after they have seen the commands).
+4. Run `vibe intent analyze` and resolve every `uncovered` bullet (add a scenario or cut the bullet) before asking; an `unrequested` scenario is cut or the bullet is written. Then research and proposals, once, before the approval message: `vibe research --from-intent --json` (up to five candidates with an action each, what moved in the last 30 days first — `--days N` for another window; skip silently on exit 2 and say "no network") and `vibe skill suggest --json` (up to three). Show both in the approval message. Do not install anything — the user says "add 1" and you run the printed `vibe skill add …` (preview first, `--yes` after they have seen the commands). `vibe status` lists the tools vibe would use if present; when the project would use one (a large repository → a symbol graph; a design review → a screenshot tool) put its one-line install in the approval message. A project-local skill is kept only if removing a line of it would make the model err.
 5. Send **one** approval message:
 
 ```