Skip to content

A Claude Code / Codex plugin that helps you learn how to build while AI writes the code.

Python

feat: frame checkpoint headings with stars

Noah Kim3e59483e8df5
diff --git a/.claude-plugin/plugin.json b/.claude-plugin/plugin.json
index 90fbbf6..77426d7 100644
--- a/.claude-plugin/plugin.json
+++ b/.claude-plugin/plugin.json
@@ -1,6 +1,6 @@
{
"name": "sensible-vibes",
- "version": "0.1.9",
+ "version": "0.1.10",
"description": "You build. AI writes. Learn how to build software while Claude writes the code.",
"author": { "name": "Noah Kim" },
"repository": "https://github.com/nykooi1/sensible-vibes",
diff --git a/README.md b/README.md
index 85aed6d..a833bb3 100644
--- a/README.md
+++ b/README.md
@@ -33,7 +33,7 @@ You: Build a reading list I can share with friends, but only I can edit.
Claude:
────────────────────────────────────────────────────────────
-✦ BUILD CHECKPOINT - Who can change a shared list
+✦ ✦ ✦ BUILD CHECKPOINT - Who can change a shared list ✦ ✦ ✦
Friends need to read the list without being able to change it.
@@ -48,7 +48,7 @@ check every request that changes the list, even if the UI hides the edit button.
────────────────────────────────────────────────────────────
-✦ DECISION REVIEW - Who can change a shared list
+✦ ✦ ✦ DECISION REVIEW - Who can change a shared list ✦ ✦ ✦
We'll check ownership on the server before allowing a change. Friends' viewing
access won't grant editing access. That means edits must pass through the server.
diff --git a/docs/development.md b/docs/development.md
index f46ca6e..f327cb0 100644
--- a/docs/development.md
+++ b/docs/development.md
@@ -68,7 +68,8 @@ Launch with `claude --plugin-dir /absolute/path/to/sensible-vibes`.
8. **Diagrams:** During orientation or a system check, confirm a compact terminal
diagram shows real components and labeled flows. Unknowns and proposals must
stay explicit; diagrams before reasoning must not silently decide the solution.
- Checkpoints and reviews should start with a divider and bold named title,
+ Checkpoints and reviews should start with a divider and bold named title
+ with three `✦` stars on each side,
followed by brief context and a bold question (or native picker), with no
trailing paragraphs obscuring the point where the learner should respond.
9. **Clarification without steering:** Ask about an unfamiliar concept mid-decision.
diff --git a/skills/learn/behavior.md b/skills/learn/behavior.md
index a0ec2d0..1380a13 100644
--- a/skills/learn/behavior.md
+++ b/skills/learn/behavior.md
@@ -26,7 +26,7 @@ drive design; learning goals shape explanations, not the architecture chosen.
and only the background needed to reason. Before their attempt, don't reveal a
recommendation, solution menu, suggested plan, or diagram that answers it.
2. **Ask.** Label every reasoning prompt, including follow-ups, with
- `✦ BUILD CHECKPOINT - <specific decision name>` and ask one question
+ `✦ ✦ ✦ BUILD CHECKPOINT - <specific decision name> ✦ ✦ ✦` and ask one question
about one problem and why. Let them form an approach before evaluating yours.
Wait for a real reply; don't answer your own question, offer
approval buttons, or write dependent code in the same turn. Read-only inspection
@@ -41,7 +41,7 @@ drive design; learning goals shape explanations, not the architecture chosen.
New consequential decisions get their own learner turn. Requested explanations,
alternatives, and skips are welcome; help isn't permission to take over later
decisions. Return the next reasoning step to the learner.
-4. **Review.** Use `✦ DECISION REVIEW - <same decision name>` to summarize the
+4. **Review.** Use `✦ ✦ ✦ DECISION REVIEW - <same decision name> ✦ ✦ ✦` to summarize the
agreed approach and main tradeoff, without adding decisions. State the next
step and call AskUserQuestion: **Use this choice** / **Discuss first** records
a design choice and continues planning. Only when prerequisites are settled,
@@ -50,7 +50,7 @@ drive design; learning goals shape explanations, not the architecture chosen.
5. **Continue.** Record confirmed design choices as chosen, not implemented, and
continue to unresolved decisions. Implementation approval covers only the
named step, not the whole feature or later choices.
- At a major milestone, occasionally use `✦ SYSTEM CHECK - <milestone>` to ask
+ At a major milestone, occasionally use `✦ ✦ ✦ SYSTEM CHECK - <milestone> ✦ ✦ ✦` to ask
how the pieces fit together.
Accept plain-English reasoning. AI writes code unless hands-on work is requested.
@@ -64,7 +64,7 @@ AskUserQuestion for setup, reviews, and requested multiple choice: one question,
2–4 options, header at most 12 characters, `multiSelect: false`. Text menus are
only a fallback when unavailable. Open-ended reasoning belongs in chat.
Every callout, including explanatory ones, uses
-`✦ <TYPE> - <description>`. Start with a Markdown divider (`---`), a blank line,
+`✦ ✦ ✦ <TYPE> - <description> ✦ ✦ ✦`. Start with a Markdown divider (`---`), a blank line,
and the **bold named title**. Follow with brief context and a diagram if useful,
then a blank line and **one bold question** (or native picker). End there when
awaiting input. No decorative boxes, simulated animation, or shell UI commands.