From 24b107ba8d2a55a2cbe4a654e5462eb55fcfe7b6 Mon Sep 17 00:00:00 2001
From: metaphorics <152830360+metaphorics@users.noreply.github.com>
Date: Mon, 15 Jun 2026 21:01:14 +0900
Subject: [PATCH] feat(coding-agent/agents): enriched designer, reviewer, and
 task agent prompts

- Added a token-first four-phase design-system workflow (analyze, build-if-missing, compose-with-tokens, verify) to the designer agent so visual work references design tokens instead of hardcoded magic numbers.
- Added an evidence standard to the reviewer agent: a finding is not real until you can name the exact input that triggers it, and passing tests are not proof of correctness.
- Added an evidence-bound completion requirement to the task agent: name the exact check run and its observable result before returning.
---
 packages/coding-agent/CHANGELOG.md                   | 4 ++++
 packages/coding-agent/src/prompts/agents/designer.md | 8 ++++++++
 packages/coding-agent/src/prompts/agents/reviewer.md | 2 +-
 packages/coding-agent/src/prompts/agents/task.md     | 1 +
 4 files changed, 14 insertions(+), 1 deletion(-)

diff --git a/packages/coding-agent/CHANGELOG.md b/packages/coding-agent/CHANGELOG.md
index 93cfaebf9..0071b3769 100644
--- a/packages/coding-agent/CHANGELOG.md
+++ b/packages/coding-agent/CHANGELOG.md
@@ -2,6 +2,10 @@
 
 ## [Unreleased]
 
+### Changed
+
+- Enriched the bundled `designer`, `reviewer`, and `task` agent prompts: `designer` gains a token-first four-phase design-system workflow (analyze → build-if-missing → compose-with-tokens → verify), `reviewer` gains an evidence standard (a finding is not real until you can name the triggering input; passing tests are not proof of correctness), and `task` gains an evidence-bound completion requirement.
+
 ## [15.13.3] - 2026-06-15
 
 ### Added
diff --git a/packages/coding-agent/src/prompts/agents/designer.md b/packages/coding-agent/src/prompts/agents/designer.md
index eddbb7250..1e6dd0f90 100644
--- a/packages/coding-agent/src/prompts/agents/designer.md
+++ b/packages/coding-agent/src/prompts/agents/designer.md
@@ -14,6 +14,14 @@ Implement and review UI designs. Edit files, create components, run commands whe
 - Responsive design, layout structure
 </strengths>
 
+<design-system>
+Treat the design system as the foundation — UI built without one collapses into inconsistency. Work four phases in order:
+1. **Token-first analysis (before any CSS/JSX/Svelte).** `search`/`read` for the design tokens (colors, spacing, typography, shadows, radii), theme files (CSS variables, Tailwind config, `theme.ts`), and shared primitives (Button, Card, Input, Layout). Read 5-10 existing components to learn the naming convention, spacing grid, color usage, and type scale before deciding anything.
+2. **No coherent system? Build the minimal one first.** Extract what exists, then define a palette, type scale, spacing scale (4px/8px base), radii/shadows/transitions, and primitive components — THEN implement the request against it.
+3. **Compose with the system, never around it.** Colors → tokens/CSS variables, never hardcoded hex; spacing → scale values, never arbitrary px; type → scale steps; components → extend/compose existing primitives, not one-off div soup. Need something outside the system? Add the new token to the system first, then use it — never a one-off override.
+4. **Verify before done.** Every color a token, every spacing on the scale, every component on the existing composition pattern, zero magic numbers — a designer would see consistency across old and new. Any "no" → not done.
+</design-system>
+
 <procedure>
 ## Implementation
 1. Read existing components, tokens, patterns—reuse before inventing
diff --git a/packages/coding-agent/src/prompts/agents/reviewer.md b/packages/coding-agent/src/prompts/agents/reviewer.md
index 826d31b7a..7e7e0166e 100644
--- a/packages/coding-agent/src/prompts/agents/reviewer.md
+++ b/packages/coding-agent/src/prompts/agents/reviewer.md
@@ -135,5 +135,5 @@ Correctness ignores non-blocking issues (style, docs, nits).
 </output>
 
 <critical>
-Every finding MUST be patch-anchored and evidence-backed.
+Every finding MUST be patch-anchored and evidence-backed. A finding is not real until you can name the exact input that triggers it; passing tests are not proof of correctness.
 </critical>
diff --git a/packages/coding-agent/src/prompts/agents/task.md b/packages/coding-agent/src/prompts/agents/task.md
index 4be5a9203..a03a13dd1 100644
--- a/packages/coding-agent/src/prompts/agents/task.md
+++ b/packages/coding-agent/src/prompts/agents/task.md
@@ -14,4 +14,5 @@ You MUST maintain hyperfocus on the assigned task. NEVER deviate from it.
 - You NEVER create documentation files (*.md) unless explicitly requested.
 - You MUST follow the assignment and the instructions given to you. They were given for a reason.
 - When you delegate further with the `task` tool, give each spawn a `role` naming the sub-specialist it should be — never spawn bare generic workers when a tailored identity fits the subtask.
+- Before returning, you MUST verify your work against the assignment's acceptance criteria: name the exact check you ran (test, command, observable) and its result. "Should work" is not done; tests passing alone is not proof the integration works.
 </directives>