Skip to content

The design language that makes your AI harness better at design.

JavaScript

Name craft-floor in the launcher fallback; keep bans out of the brief override (#1153)

Paul Bakaus719a8fa9426f
diff --git a/skill/SKILL.src.md b/skill/SKILL.src.md
index de0316613..2aedc373d 100644
--- a/skill/SKILL.src.md
+++ b/skill/SKILL.src.md
@@ -22,7 +22,7 @@ Core principles:
2. Load the request's playbook: its Commands-table reference for an explicit/implied sub-command, or [reference/new-work.md](reference/new-work.md) for a new surface or replacement visual world. Inspect target and incumbent visual truth before editing. When the app cannot run, start with committed visual-regression goldens or screenshot fixtures; verify target and freshness against current tokens, CSS, components, or assets, resolve conflicts, and compare theme/variant captures. <!-- rule:skill-setup-command-ref --> <!-- rule:skill-setup-read-project -->
3. After resolving analysis and direction, read [reference/craft-floor.md](reference/craft-floor.md) immediately before any UI edit, including small refinements. It carries the quality floor, the absolute bans, and the reflexes no detector catches. Do not load it for planning-only work. <!-- rule:skill-craft-floor-load -->
-**Launcher unavailable:** On refusal or failure, send a separate message **before the next tool call**: “Context loading did not run; I’ll read the existing project context directly.” Then read existing PRODUCT.md and DESIGN.md without inventing missing context, follow applicable steps 2–3, and continue through permitted tools. This applies to planning and editing; launcher failure alone does not block either.
+**Launcher unavailable:** On refusal or failure, send a separate message **before the next tool call**: “Context loading did not run; I’ll read the existing project context directly.” Then read existing PRODUCT.md and DESIGN.md without inventing missing context, follow applicable steps 2–3, including reading [reference/craft-floor.md](reference/craft-floor.md) immediately before any UI edit, and continue through permitted tools. This applies to planning and editing; launcher failure alone does not block either.
## How to design
diff --git a/skill/reference/craft-floor.md b/skill/reference/craft-floor.md
index 30b63c7b3..3331f4845 100644
--- a/skill/reference/craft-floor.md
+++ b/skill/reference/craft-floor.md
@@ -1,6 +1,6 @@
# Craft floor
-Load this after the direction is settled, and build without announcing the checklist. A pinned brief or the committed visual world overrides anything here; your own habit does not. When the design hook is active it already enforces the mechanical checks below as you edit: act on its findings instead of re-auditing each rule. <!-- rule:skill-craft-floor -->
+Load this after the direction is settled, and build without announcing the checklist. A pinned brief or the committed visual world overrides anything here except a line marked as a ban; your own habit does not. When the design hook is active it already enforces the mechanical checks below as you edit: act on its findings instead of re-auditing each rule. <!-- rule:skill-craft-floor -->
## Verify
diff --git a/tests/skill-behavior/README.md b/tests/skill-behavior/README.md
index 617ee7e98..7426b8fa8 100644
--- a/tests/skill-behavior/README.md
+++ b/tests/skill-behavior/README.md
@@ -478,6 +478,15 @@ These are single samples per case and candidate, not reliability estimates.
This API harness starts with the skill loaded and readable references. It
does not measure activation, reproduce Windows command parsing, or establish
fallback behavior when the host also denies required file reads or writes.
+
+### Named craft-floor read (2026-10-23, #744)
+
+An outside measurement in acceptEdits mode found 0 of 21 craft-floor reads
+before the first UI edit on the denied-launcher path: "follow applicable steps
+2–3" did not get the agent into `reference/`. The fallback now names
+`reference/craft-floor.md` and the pre-edit timing explicitly. Scenario 19's
+assertions are unchanged. Not yet rerun: one combined `test:skill-behavior`
+run is planned after #1114 and #1118 land, so there is no new result here.
Keep #744 open; evaluate activation separately with #375.
To repeat only these cases (provider keys and an engine binary required):