k-harness 0.5.0 → 0.6.0

package/README.md

@@ -59,7 +59,7 @@ npx k-harness init --ide antigravity
 | **Augment Code** | `.augment/rules/core.md` | `.augment/rules/*.md` | `.augment/skills/*/SKILL.md` | `.augment/skills/*/SKILL.md` |
 | **Google Antigravity** | `.agent/rules/core.md` | `.agent/rules/*.md` | `.agent/skills/*/SKILL.md` | `.agent/skills/*/SKILL.md` |
 
-All IDEs also get `project-state.md`, `project-brief.md`, `features.md`, `failure-patterns.md`, and `dependency-map.md` at the project root.
+All IDEs also get state files (`project-state.md`, `project-brief.md`, `features.md`, `failure-patterns.md`, `dependency-map.md`) in the `docs/` directory.
 
 ## What Gets Installed
 
@@ -125,7 +125,7 @@ See [docs/reference.md](docs/reference.md) for detailed descriptions of every sk
 | | BMAD v6.2.2 | gstack v0.15.1 | K-Harness |
 |---|---|---|---|
 | Focus | Enterprise SDLC methodology | 1-person software factory | Project direction management |
-| Files | 200+ | ~40 | 15 |
+| Files | 200+ | ~40 | ~20 |
 | Dependencies | Node 20+ | Bun + Node + Playwright | Zero |
 | IDE support | 20+ (installer) | 5 (setup --host) | 7 (native format) |
 | Direction management | ❌ | ❌ | ✅ (Direction Guard + pivot + Decision Log) |

package/harness/agents/planner.md

@@ -42,9 +42,9 @@ If `docs/project-brief.md` alone is empty → Warn the user but proceed (the pla
 
 1. Read `docs/project-brief.md` to understand project vision, goals, **non-goals**, and **Decision Log**
 2. **Direction Alignment**: Verify the requested feature against three checkpoints:
-   - **Goal Alignment**: Does it serve a listed Goal? If no clear link, warn the user.
-   - **Non-Goal Violation**: Does it fall into Non-Goals? If yes, **stop and ask** — this may be a pivot.
-   - **Decision Consistency**: Does it contradict any Decision Log entry? If yes, warn that a previous decision conflicts — recommend running the `pivot` skill before proceeding.
+   - **Goal Alignment**: Does it serve a listed Goal? If no clear link → **warn but proceed**. Include the warning in the plan output.
+   - **Non-Goal Violation**: Does it fall into Non-Goals? If yes → **stop and ask the user**. Do not proceed until the user confirms this is intentional (may need `pivot` skill).
+   - **Decision Consistency**: Does it contradict any Decision Log entry? If yes → **stop and warn**. Recommend running the `pivot` skill before proceeding.
    If the request represents a clear direction change → recommend running the `pivot` skill instead of proceeding with planning.
 3. Read `docs/features.md` to understand what already exists
 4. Read `docs/dependency-map.md` to understand current architecture

package/harness/agents/reviewer.md

@@ -75,6 +75,7 @@ Verify that state file updates actually happened. Check each:
 - [ ] **docs/dependency-map.md**: If new modules were created, are they registered? If dependencies changed, are relationships updated?
 - [ ] **docs/failure-patterns.md**: If a bug was fixed that matched a pattern, was frequency incremented?
 - [ ] **docs/project-brief.md**: If a technology or architectural decision was made, is it in Decision Log?
+- [ ] **docs/agent-memory/*.md**: If an agent (reviewer/planner/sprint-manager) was used this session, was its memory updated by the learn skill?
 
 For each missing update: flag as `[STATE-AUDIT]` in the output and provide the exact update that should be made.
 

package/harness/failure-patterns.md

@@ -14,6 +14,12 @@ Keep resolved patterns for regression prevention.
 - **Applied in**: testing rules, test-integrity skill, reviewer agent
 - **Status**: Template — activate when first occurrence is logged
 
+<!-- Activation example: When this pattern first occurs, update like this:
+- **Occurred**: S1-2
+- **Frequency**: 1
+- **Status**: Active
+On subsequent occurrences, increment Frequency and append to Occurred (e.g., S1-2, S2-1) -->
+
 ---
 
 ## FP-002: Type confusion (enum vs union, wrong parameter count)

package/harness/skills/bootstrap.md

@@ -41,6 +41,7 @@ Ask the user these questions (skip any already answered by Phase 1):
 3. "What is explicitly OUT of scope? (non-goals)"
 4. "What architecture pattern are you using?" (show detected pattern if found)
 5. "Are there any type decisions or conventions the AI should know about?"
+6. "What is your test command?" (show detected command if found, e.g., `npm test`, `pytest`, `go test ./...`)
 
 ### Phase 3: Fill State Files
 

package/harness/skills/impact-analysis.md

@@ -61,7 +61,7 @@ Plan: 4 files to update, all within S3-2 scope
 
 After completing the analysis, update these files:
 
-- [ ] **docs/dependency-map.md**: Update the Interface Change Log table with: Date, Module, Change description, Affected Modules, Status.
+- [ ] **docs/dependency-map.md**: Update the Interface Change Log table with: Date, Module, Change description, Affected Modules, Status. **This is mandatory for ALL interface changes** — do not skip even if the change seems minor.
 - [ ] **docs/project-state.md**: If scope exceeds current Story, add a note to Recent Changes.
 
 ## Related Failure Patterns

package/harness/skills/learn.md

@@ -8,11 +8,13 @@ This is K-Harness's memory mechanism — without it, the same mistakes repeat ac
 
 ## When to Apply
 
-- Before ending a chat session (recommended as the LAST skill invoked)
+- Before ending a chat session (recommended as the LAST skill invoked, **once per session**)
 - After a debugging session where a non-obvious fix was found
 - After a review revealed a repeated mistake
 - When the user explicitly asks to record a lesson
 
+> **Timing**: Invoke this skill **once at session end**, not after each individual skill. It aggregates the entire session's work into state files.
+
 ## Procedure
 
 ### Step 1: Review Session Activity
@@ -63,7 +65,10 @@ For each issue/error that occurred in this session:
 If an agent (reviewer, planner, sprint-manager) was used in this session, update its memory file in `docs/agent-memory/`:
 
 1. Read `docs/agent-memory/{agent-name}.md`
-2. Add session-specific learnings to the appropriate section:
+2. If the file only contains placeholder comments (`<!-- 예시:... -->`), initialize it by replacing the comments with actual entries. Example:
+   - Before: `<!-- 예시: Wave 1 추정: 정확 -->`
+   - After: `- [S1-2] Wave 1 추정: 정확 (3 tasks, 실제 소요 1일)`
+3. Add session-specific learnings to the appropriate section:
    - **reviewer.md**: Review patterns, frequently missed items, statistics
    - **planner.md**: Estimation accuracy, architecture insights, repeated patterns
    - **sprint-manager.md**: Velocity data, scope drift incidents, sizing recommendations

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "k-harness",
-  "version": "0.5.0",
+  "version": "0.6.0",
   "description": "LLM Development Harness — IDE-agnostic rules, skills, and agents that prevent common AI coding failures",
   "keywords": [
     "llm",