@gannonh/kata 1.0.7 → 1.0.8

package/agents/kata-executor.md

@@ -353,7 +353,7 @@ Type "done" when authenticated.
 Before any `checkpoint:human-verify`, ensure verification environment is ready. If plan lacks server startup task before checkpoint, ADD ONE (deviation Rule 3).
 
 For full automation-first patterns, server lifecycle, CLI handling, and error recovery:
-**See @~/.claude/kata/references/checkpoints.md**
+**See @./references/checkpoints.md**
 
 **Quick reference:**
 - Users NEVER run CLI commands - Claude does all automation
@@ -610,7 +610,7 @@ After all tasks complete, create `{phase}-{plan}-SUMMARY.md`.
 
 **Location:** `.planning/phases/XX-name/{phase}-{plan}-SUMMARY.md`
 
-**Use template from:** @~/.claude/kata/templates/summary.md
+**Use template from:** @./references/summary-template.md
 
 **Frontmatter population:**
 

package/agents/kata-planner.md

@@ -407,8 +407,8 @@ Output: [What artifacts will be created]
 </objective>
 
 <execution_context>
-@~/.claude/kata/workflows/execute-plan.md
-@~/.claude/kata/templates/summary.md
+@./references/execute-plan.md
+@./references/summary-template.md
 </execution_context>
 
 <context>

package/agents/kata-research-synthesizer.md

@@ -122,7 +122,7 @@ Identify gaps that couldn't be resolved and need attention during planning.
 
 ## Step 6: Write SUMMARY.md
 
-Use template: $KATA_BASE/templates/research-project/SUMMARY.md
+Format: Standard research SUMMARY.md (see output_format section)
 
 Write to `.planning/research/SUMMARY.md`
 
@@ -159,7 +159,7 @@ Return brief confirmation with key points for the orchestrator.
 
 <output_format>
 
-Use template: $KATA_BASE/templates/research-project/SUMMARY.md
+Format: Standard research SUMMARY.md (see output_format section)
 
 Key sections:
 - Executive Summary (2-3 paragraphs)

package/agents/kata-roadmapper.md

@@ -286,7 +286,7 @@ After roadmap creation, REQUIREMENTS.md gets updated with phase mappings:
 
 ## ROADMAP.md Structure
 
-Use template from `$KATA_BASE/templates/roadmap.md`.
+Use the standard ROADMAP.md format (see examples in existing projects).
 
 Key sections:
 - Overview (2-3 sentences)
@@ -295,7 +295,7 @@ Key sections:
 
 ## STATE.md Structure
 
-Use template from `$KATA_BASE/templates/state.md`.
+Use the standard STATE.md format (see examples in existing projects).
 
 Key sections:
 - Project Reference (core value, current focus)

package/{kata/workflows → agents/references}/execute-plan.md

@@ -6,7 +6,7 @@ Execute a phase prompt (PLAN.md) and create the outcome summary (SUMMARY.md).
 Read STATE.md before any operation to load project context.
 Read config.json for planning behavior settings.
 
-@~/.claude/kata/references/git-integration.md
+@./git-integration.md
 </required_reading>
 
 <process>
@@ -1290,7 +1290,7 @@ grep -A 50 "^user_setup:" .planning/phases/XX-name/{phase}-{plan}-PLAN.md | head
 
 **If user_setup exists and is not empty:**
 
-Create `.planning/phases/XX-name/{phase}-USER-SETUP.md` using template from `$KATA_BASE/templates/user-setup.md`.
+Create `.planning/phases/XX-name/{phase}-USER-SETUP.md` using the template format below.
 
 **Content generation:**
 
@@ -1351,7 +1351,7 @@ Set `USER_SETUP_CREATED=true` if file was generated, for use in completion messa
 
 <step name="create_summary">
 Create `{phase}-{plan}-SUMMARY.md` as specified in the prompt's `<output>` section.
-Use $KATA_BASE/templates/summary.md for structure.
+Use @./summary-template.md for structure.
 
 **File location:** `.planning/phases/XX-name/{phase}-{plan}-SUMMARY.md`
 

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@gannonh/kata",
-  "version": "1.0.7",
+  "version": "1.0.8",
   "type": "module",
   "description": "Spec-driven development framework for Claude Code.",
   "scripts": {
@@ -11,6 +11,7 @@
     "kata": "bin/install.js"
   },
   "files": [
+    "README.md",
     "bin",
     "commands",
     "kata",

package/skills/kata-completing-milestones/SKILL.md

@@ -20,8 +20,8 @@ Output: Milestone archived (roadmap + requirements), PROJECT.md evolved, git tag
 <execution_context>
 **Load these files NOW (before proceeding):**
 
-- @~/.claude/kata/workflows/milestone-complete.md (main workflow)
-- @~/.claude/kata/templates/milestone-archive.md (archive template)
+- @./references/milestone-complete.md (main workflow)
+- @./references/milestone-archive-template.md (archive template)
   </execution_context>
 
 <context>

package/{kata/workflows → skills/kata-completing-milestones/references}/milestone-complete.md

@@ -10,11 +10,10 @@ This is the ritual that separates "development" from "shipped."
 
 **Read these files NOW:**
 
-1. templates/milestone.md
-2. templates/milestone-archive.md
-3. `.planning/ROADMAP.md`
-4. `.planning/REQUIREMENTS.md`
-5. `.planning/PROJECT.md`
+1. @./milestone-archive-template.md
+2. `.planning/ROADMAP.md`
+3. `.planning/REQUIREMENTS.md`
+4. `.planning/PROJECT.md`
 
 </required_reading>
 
@@ -38,7 +37,7 @@ When a milestone completes, this workflow:
 
 **Archive Format:**
 
-**ROADMAP archive** uses `templates/milestone-archive.md` template with:
+**ROADMAP archive** uses `@./milestone-archive-template.md` template with:
 - Milestone header (status, phases, date)
 - Full phase details from roadmap
 - Milestone summary (decisions, issues, technical debt)
@@ -196,7 +195,7 @@ If file doesn't exist:
 
 If exists, prepend new entry (reverse chronological order).
 
-Use template from `templates/milestone.md`:
+Use this template format:
 
 ```markdown
 ## v[Version] [Name] (Shipped: YYYY-MM-DD)
@@ -423,7 +422,7 @@ Extract completed milestone details and create archive file.
 
 1. Create archive file path: `.planning/milestones/v[X.Y]-ROADMAP.md`
 
-2. Read `$KATA_BASE/templates/milestone-archive.md` template
+2. Read the `@./milestone-archive-template.md` template
 
 3. Extract data from current ROADMAP.md:
    - All phases belonging to this milestone (by phase number range)

package/skills/kata-discussing-phases/SKILL.md

@@ -23,8 +23,8 @@ Extract implementation decisions that downstream agents need — researcher and
 </objective>
 
 <execution_context>
-@~/.claude/kata/workflows/phase-discuss.md
-@~/.claude/kata/templates/context.md
+@./references/phase-discuss.md
+@./references/context-template.md
 </execution_context>
 
 <context>

package/skills/kata-executing-phases/SKILL.md

@@ -19,9 +19,9 @@ Context budget: ~15% orchestrator, 100% fresh per subagent.
 </objective>
 
 <execution_context>
-@~/.claude/kata/references/ui-brand.md
-@~/.claude/kata/references/planning-config.md
-@~/.claude/kata/workflows/phase-execute.md
+@./references/ui-brand.md
+@./references/planning-config.md
+@./references/phase-execute.md
 </execution_context>
 
 <context>
@@ -279,7 +279,7 @@ Plans with `autonomous: false` have checkpoints. The phase-execute.md workflow h
 - Orchestrator presents to user, collects response
 - Spawns fresh continuation agent (not resume)
 
-See `@~/.claude/kata/workflows/phase-execute.md` step `checkpoint_handling` for complete details.
+See `@./references/phase-execute.md` step `checkpoint_handling` for complete details.
 </checkpoint_handling>
 
 <deviation_rules>