claude-sprint-gate 1.4.0 → 1.5.0

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "claude-sprint-gate",
-  "version": "1.4.0",
+  "version": "1.5.0",
   "description": "Claude Code Sprint Gate — sprint lifecycle manager with verification gates",
   "bin": {
     "ccsg": "bin/ccsg.js"

package/plugin/commands/sprint.md

@@ -1,34 +1,53 @@
 ---
-description: "Start working on the current sprint"
+description: "Start autonomous sprint cycle — work continuously until the product is ready"
 allowed-tools: ["Read", "Edit", "Write", "Bash", "Glob", "Grep"]
 hide-from-slash-command-tool: "true"
 ---
 
-# Sprint — Start Working
+# Sprint — Autonomous Product Development
 
-You are now in sprint mode. The stop hook will prevent you from stopping until all items are done.
+You are entering an autonomous sprint cycle.
 
-## Your task
+## Step 1 — Load your context
 
-1. Check `goals-open/` for the active goal file (the most recent `goal-*.md`)
-2. If a `mission.md` exists, read it — that is your persona and objective
-3. Read the goal file completely
-4. Work through every unchecked item (`- [ ]`) in order
-5. As you complete each item, check it off (`- [x]`) in the goal file
-6. When all items are checked, the stop hook will handle what comes next:
-   - If it's a regular sprint: a verification sprint is auto-generated
-   - If it's a verification sprint: the sprint is archived
-   - If a mission is active: the next sprint is prompted
+1. Read `mission.md` — this defines who you are, what you're building, and your constraints. Adopt the persona and objectives defined there. If no mission file exists, your objective is to complete the current sprint.
+2. Read `CLAUDE.md` if it exists — these are rules that carry forward to every sprint.
+3. Check `goals-open/` for the active goal file (most recent `goal-*.md`).
+
+## Step 2 — Execute
+
+- **If a goal file exists**: read it, execute every unchecked item, check them off (`- [x]`) as you complete and verify each one.
+- **If no goal file exists**: read `goals-completed/` to understand what has been delivered so far, then create the next sprint file based on your mission objectives. Define concrete, verifiable deliverables as checkboxes. Then execute it.
+
+## Step 3 — The cycle
+
+When you try to stop, the stop hook will:
+- **Block** if unchecked items remain — re-prompting you with the full goal
+- **Generate a verification sprint** when all items are checked — you must prove everything works end-to-end
+- **Prompt the next sprint** after verification if a mission is active — you plan it based on your mission, then execute it
+- **Allow stop** only when the mission's sprint cap is reached or no mission is active
+
+This cycle repeats autonomously: build, verify, plan, build, verify, plan.
+
+## Sprint planning guidance
+
+When creating a new sprint, decide what the product needs most right now:
+- Early sprints: foundation, architecture, core data model
+- Middle sprints: features that users interact with
+- Late sprints: polish, error handling, edge cases, documentation
+- Every sprint should leave the product in a state you would demonstrate
+- Write concrete deliverables, not vague goals — "Add error states to all forms" not "improve UX"
 
 ## Rules
 
-- Do NOT stop or pause to ask for confirmation. Execute continuously.
-- Do NOT skip items. Work through them in order.
-- Test each deliverable the way its end user would use it — compilation is not verification.
-- If you get stuck on an item, try a different approach. Do not abandon it.
-- Check items off (`- [x]`) only AFTER you have completed and verified them.
-- When you try to stop, the hook will re-prompt you if work remains. This is by design.
+- Execute continuously. Do not pause to ask for confirmation.
+- Do not skip items. Work through them in order.
+- Test each deliverable the way its end user would use it.
+- Constraints from `CLAUDE.md` and `mission.md` carry forward to every sprint.
+- Never trade correctness for speed.
+- No sprint should leave the product in a state you would not demonstrate.
+- If stuck on an item, try a different approach. Do not abandon it.
 
 ## Begin
 
-Read the active goal file now and start executing.
+Read `mission.md`, then `CLAUDE.md`, then the active goal file. Start executing. Go.