@gonrocca/zero-pi 0.1.19 → 0.1.20

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@gonrocca/zero-pi",
-  "version": "0.1.19",
+  "version": "0.1.20",
   "description": "zero-pi — an installable layer for pi (pi.dev): the zero spec-driven development workflow, skill auto-learning, and an animated ZERO startup banner. Adds capability to pi without modifying pi.",
   "type": "module",
   "keywords": [

package/prompts/forge.md

@@ -14,4 +14,10 @@ claim success unless veredicto returned `pasa`.
 If the request begins with `--continue [slug]`, resume that unfinished run from
 its `.sdd/<slug>/` artifacts instead of starting fresh.
 
+**Work quietly.** Emit one short status line per phase (`explore → …`, the
+verdict, the round count) — no step-by-step narration, no reasoning out loud,
+and do not echo tool output or agent listings back into the chat. The four
+`zero-*` sub-agents already exist; delegate to them directly without running a
+`subagent` listing. The user wants progress and the final verdict, not a log.
+
 Feature request: $ARGUMENTS

package/prompts/phases/build.md

@@ -18,3 +18,5 @@ change within the plan's scope — do not expand it on your own initiative.
 
 Run the test suite and make it pass before reporting the phase complete. Report
 what you changed so the veredicto phase has something concrete to review.
+
+**Work quietly.** Report only your phase's outcome — concise findings, plan, result, or verdict. No step-by-step narration, no reasoning out loud, no echoing tool output.

package/prompts/phases/explore.md

@@ -20,3 +20,5 @@ what is relevant to the request, and what to watch out for.
 If the orchestrator includes prior-run memory in your brief, use it: past runs
 record what already broke in this code and which plans were sent back. Fold the
 relevant points into the findings under a "Prior runs" heading.
+
+**Work quietly.** Report only your phase's outcome — concise findings, plan, result, or verdict. No step-by-step narration, no reasoning out loud, no echoing tool output.

package/prompts/phases/plan.md

@@ -80,3 +80,5 @@ means the same number on every run.
   the tasks above it), the **bold total** computed as the literal sum of the
   per-task estimates, and the over-budget exceptions list — state "none" when
   there are no exceptions.
+
+**Work quietly.** Report only your phase's outcome — concise findings, plan, result, or verdict. No step-by-step narration, no reasoning out loud, no echoing tool output.

package/prompts/phases/veredicto.md

@@ -28,3 +28,5 @@ Never return `pasa` unless the evidence supports it.
 State the verdict's reasoning concretely — the specific defects for `corregir`,
 the specific plan flaw for `replantear`. The orchestrator persists that
 reasoning to the run's memory trace, so future runs depend on it being precise.
+
+**Work quietly.** Report only your phase's outcome — concise findings, plan, result, or verdict. No step-by-step narration, no reasoning out loud, no echoing tool output.