dino-spec 20.4.0 → 21.1.0

package/.claude/rules/dino/change-categories.md

@@ -1,56 +1,56 @@
-# Change Categories
-
-## File Classification
-
-Files are classified into categories based on path and name:
-
-### dependency (High Significance)
-Files that affect project dependencies:
-- `package.json`, `bun.lockb`, `package-lock.json`
-
-**Pending Action:** Run package manager install command
-
-### structural (High Significance)
-Files that affect project structure:
-- Entry points: `index.ts`, `main.ts`, `app.ts`
-- Configuration: `tsconfig.json`, `webpack.config.js`
-- Build configs: `build.js`, `vite.config.ts`
-- Directory additions/removals
-
-**Pending Action:** Verify import paths
-
-### config (Medium Significance)
-Configuration files:
-- `.env`, `.env.*`
-- `*.config.js`, `*.config.ts`
-- `.eslintrc`, `.prettierrc`
-- CI/CD files: `.github/`, `.gitlab-ci.yml`
-
-### test (Medium Significance)
-Test files:
-- `*.test.ts`, `*.test.js`
-- `*.spec.ts`, `*.spec.js`
-- `test/`, `tests/`, `__tests__/` directories
-
-### code (Low Significance)
-Source code files:
-- `src/`, `lib/` directories
-- Main programming language files
-- Utility and helper files
-
-### documentation (Low Significance)
-Documentation files:
-- `*.md`, `README*`
-- `docs/` directory
-- Code comments (when detected)
-
-## Impact on Workflow
-
-| Category | Run Tests | Run Build | Review |
-|----------|-----------|-----------|--------|
-| dependency | After install | Yes | Changelog |
-| structural | Yes | Yes | Imports |
-| config | Maybe | Maybe | Side effects |
-| test | Yes | No | Coverage |
-| code | Yes | Yes | Normal |
-| documentation | No | No | Spelling |
+# Change Categories
+
+## File Classification
+
+Files are classified into categories based on path and name:
+
+### dependency (High Significance)
+Files that affect project dependencies:
+- `package.json`, `bun.lockb`, `package-lock.json`
+
+**Pending Action:** Run package manager install command
+
+### structural (High Significance)
+Files that affect project structure:
+- Entry points: `index.ts`, `main.ts`, `app.ts`
+- Configuration: `tsconfig.json`, `webpack.config.js`
+- Build configs: `build.js`, `vite.config.ts`
+- Directory additions/removals
+
+**Pending Action:** Verify import paths
+
+### config (Medium Significance)
+Configuration files:
+- `.env`, `.env.*`
+- `*.config.js`, `*.config.ts`
+- `.eslintrc`, `.prettierrc`
+- CI/CD files: `.github/`, `.gitlab-ci.yml`
+
+### test (Medium Significance)
+Test files:
+- `*.test.ts`, `*.test.js`
+- `*.spec.ts`, `*.spec.js`
+- `test/`, `tests/`, `__tests__/` directories
+
+### code (Low Significance)
+Source code files:
+- `src/`, `lib/` directories
+- Main programming language files
+- Utility and helper files
+
+### documentation (Low Significance)
+Documentation files:
+- `*.md`, `README*`
+- `docs/` directory
+- Code comments (when detected)
+
+## Impact on Workflow
+
+| Category | Run Tests | Run Build | Review |
+|----------|-----------|-----------|--------|
+| dependency | After install | Yes | Changelog |
+| structural | Yes | Yes | Imports |
+| config | Maybe | Maybe | Side effects |
+| test | Yes | No | Coverage |
+| code | Yes | Yes | Normal |
+| documentation | No | No | Spelling |

package/.claude/rules/dino/confidence.md

@@ -1,147 +1,147 @@
-# Confidence & Validation
-
-Consolidated from: confidence-handling, spec-kit, research-validation
-
----
-
-## Confidence Gate
-
-Implementation BLOCKED until confidence threshold reached.
-
-### Thresholds
-
-| Task Type | Required | Reason |
-|-----------|----------|--------|
-| Standard | 80% | Typical implementation |
-| Complex (Ralph-eligible) | 90% | Multi-story work |
-
-### Confidence Factors
-
-| Factor | Impact |
-|--------|--------|
-| Vague verbs | -5% each |
-| Missing target | -5% |
-| Unclear success | -5% |
-| Security-related | -15% |
-| Data-related | -10% |
-| Breaking change | -10% |
-| Package recommendation | -15% |
-| API usage from training | -10% |
-
-### Gate Flow
-
-```
-Task → Analyze Confidence → [>= threshold?]
-                              ↓ no
-                    [ambiguity > 40?] → Research
-                              ↓ no
-                    Clarification → Re-check
-```
-
-### Max Rounds
-
-| Phase | Max |
-|-------|-----|
-| Research | 2 |
-| Clarification | 5 |
-
-After max rounds: User must validate assumptions explicitly.
-
----
-
-## Spec Analysis
-
-### Auto-Trigger
-
-Triggers when:
-- Ambiguity > 40 (vague verbs, missing details)
-- Implementation request ("add", "create", "build", "fix")
-
-Does NOT trigger for:
-- Status checks
-- Simple queries
-- Explicit skip (`--skip-spec`)
-
-### Modes
-
-| Mode | When | Behavior |
-|------|------|----------|
-| Skip | complexity < 30, ambiguity < 20 | Proceed directly |
-| Lightweight | complexity < 30, ambiguity >= 20 | Quick check |
-| Full | complexity >= 30 | Thorough analysis |
-
-### Multi-Part Requests
-
-1. Split into discrete tasks
-2. Present recommended order
-3. Analyze first task only
-4. Queue remaining tasks
-
-### Routing After Spec
-
-| Complexity | Route |
-|------------|-------|
-| < 30 points | Direct action |
-| 30-70 points | EnterPlanMode |
-| > 70 points | /ralph-gate |
-
----
-
-## Research Validation
-
-Validates packages, APIs, and libraries for security and quality.
-
-### Trigger Points
-
-| Trigger | Validated |
-|---------|-----------|
-| `bun add <pkg>` | Package before install |
-| `/validate-deps` | All dependencies |
-| `/ralph-gate` | PRD dependencies |
-| Research output | Package recommendations |
-
-### Security Checks
-
-| Check | Action |
-|-------|--------|
-| Critical vulnerability | BLOCK |
-| High vulnerability | BLOCK + require override |
-| Deprecated | Warn with alternative |
-| Malicious | BLOCK |
-
-### Quality Checks
-
-| Check | Threshold | Action |
-|-------|-----------|--------|
-| Size | > 100KB gzipped | Warn |
-| Downloads | < 1000/week | Info |
-| Last update | > 2 years | Warn |
-| No maintainers | - | Block |
-
-### Severity Levels
-
-| Level | Action |
-|-------|--------|
-| critical | BLOCK |
-| high | BLOCK + override |
-| moderate | WARN |
-| low | Note |
-| info | Note only |
-
-### MCP Tools
-
-- `dino_validate_package` - Single package
-- `dino_validate` (action: deps) - Batch validation
-- `dino_validate` (action: scan) - Security-only
-
----
-
-## Bypassing
-
-Not recommended, but available:
-
-- `--force` flag
-- Explicit validation after max rounds
-- `DINO_SKIP_VALIDATION=true`
-
-All bypasses logged in session.md.
+# Confidence & Validation
+
+Consolidated from: confidence-handling, spec-kit, research-validation
+
+---
+
+## Confidence Gate
+
+Implementation BLOCKED until confidence threshold reached.
+
+### Thresholds
+
+| Task Type | Required | Reason |
+|-----------|----------|--------|
+| Standard | 80% | Typical implementation |
+| Complex (Ralph-eligible) | 90% | Multi-story work |
+
+### Confidence Factors
+
+| Factor | Impact |
+|--------|--------|
+| Vague verbs | -5% each |
+| Missing target | -5% |
+| Unclear success | -5% |
+| Security-related | -15% |
+| Data-related | -10% |
+| Breaking change | -10% |
+| Package recommendation | -15% |
+| API usage from training | -10% |
+
+### Gate Flow
+
+```
+Task → Analyze Confidence → [>= threshold?]
+                              ↓ no
+                    [ambiguity > 40?] → Research
+                              ↓ no
+                    Clarification → Re-check
+```
+
+### Max Rounds
+
+| Phase | Max |
+|-------|-----|
+| Research | 2 |
+| Clarification | 5 |
+
+After max rounds: User must validate assumptions explicitly.
+
+---
+
+## Spec Analysis
+
+### Auto-Trigger
+
+Triggers when:
+- Ambiguity > 40 (vague verbs, missing details)
+- Implementation request ("add", "create", "build", "fix")
+
+Does NOT trigger for:
+- Status checks
+- Simple queries
+- Explicit skip (`--skip-spec`)
+
+### Modes
+
+| Mode | When | Behavior |
+|------|------|----------|
+| Skip | complexity < 30, ambiguity < 20 | Proceed directly |
+| Lightweight | complexity < 30, ambiguity >= 20 | Quick check |
+| Full | complexity >= 30 | Thorough analysis |
+
+### Multi-Part Requests
+
+1. Split into discrete tasks
+2. Present recommended order
+3. Analyze first task only
+4. Queue remaining tasks
+
+### Routing After Spec
+
+| Complexity | Route |
+|------------|-------|
+| < 30 points | Direct action |
+| 30-70 points | EnterPlanMode |
+| > 70 points | /ralph-gate |
+
+---
+
+## Research Validation
+
+Validates packages, APIs, and libraries for security and quality.
+
+### Trigger Points
+
+| Trigger | Validated |
+|---------|-----------|
+| `bun add <pkg>` | Package before install |
+| `/validate-deps` | All dependencies |
+| `/ralph-gate` | PRD dependencies |
+| Research output | Package recommendations |
+
+### Security Checks
+
+| Check | Action |
+|-------|--------|
+| Critical vulnerability | BLOCK |
+| High vulnerability | BLOCK + require override |
+| Deprecated | Warn with alternative |
+| Malicious | BLOCK |
+
+### Quality Checks
+
+| Check | Threshold | Action |
+|-------|-----------|--------|
+| Size | > 100KB gzipped | Warn |
+| Downloads | < 1000/week | Info |
+| Last update | > 2 years | Warn |
+| No maintainers | - | Block |
+
+### Severity Levels
+
+| Level | Action |
+|-------|--------|
+| critical | BLOCK |
+| high | BLOCK + override |
+| moderate | WARN |
+| low | Note |
+| info | Note only |
+
+### MCP Tools
+
+- `dino_validate_package` - Single package
+- `dino_validate` (action: deps) - Batch validation
+- `dino_validate` (action: scan) - Security-only
+
+---
+
+## Bypassing
+
+Not recommended, but available:
+
+- `--force` flag
+- Explicit validation after max rounds
+- `DINO_SKIP_VALIDATION=true`
+
+All bypasses logged in session.md.

package/.claude/rules/dino/quality.md

@@ -1,112 +1,112 @@
-# Testing & Quality
-
-Consolidated from: smart-tests, mandatory-review, auto-memory-capture, confidence-gate
-
----
-
-## 80% Confidence Gate
-
-**Confidence Gate**: See `.claude/rules/dino/confidence.md` for thresholds, factors, and flow.
-
----
-
-## Smart Test Optimization
-
-Reduce test run times by 60-80% through intelligent scope detection.
-
-### Test Scopes
-
-| Scope | When | Duration |
-|-------|------|----------|
-| SKIP | No changes since passing | Instant |
-| TARGETED | Single feature changes | Fast |
-| FULL | Cross-cutting changes | Complete |
-
-### Decision Tree
-
-```
-No changes since passing → SKIP
-Dependency/config changes → FULL
-Shared code (utils/, core/) → FULL
-Single feature changes → TARGETED
-Documentation only → SKIP
-```
-
-### Full Test Triggers
-
-- `package.json`, lock files
-- `tsconfig.json`, `vitest.config.ts`
-- Entry points (`index.ts`, `main.ts`)
-- Shared modules (`src/utils/`, `src/core/`, `src/lib/`)
-
-### Targeted Patterns
-
-| Focus | Pattern |
-|-------|---------|
-| `src/hooks/` | `hooks` |
-| `src/core/ralph/` | `ralph` |
-| `src/commands/*.ts` | `commands` |
-| Multiple features | FULL |
-
-### Usage in Skills
-
-**`/dino.aging`**: Uses smart test workflow to analyze scope before running tests.
-
-**`/dino.release`**: Uses smart test detection to optimize release verification.
-
-**`/dino.hunt`**: Uses incremental testing during implementation.
-
-### Performance Targets
-
-| Scenario | Target Duration |
-|----------|-----------------|
-| SKIP (no changes) | 0s |
-| TARGETED (single feature) | 10-30s |
-| FULL (must run all) | < 3 min |
-
----
-
-## Mandatory Review
-
-Set `DINO_MANDATORY_REVIEW=true` to enable code review gate. Disabled by default.
-
----
-
-## Auto-Memory Capture
-
-Preserve learnings after significant work.
-
-### When to Capture
-
-| Event | Source |
-|-------|--------|
-| /spec completes | Analysis decisions |
-| /hunt task completes | Implementation learnings |
-| Tests pass after fix | What fixed the issue |
-| User confirms decision | Decision text |
-| Ralph iteration | Iteration learnings |
-
-### How to Capture
-
-```
-dino_memory_auto_capture({
-  text: "Summary of decision or learning",
-  source: "spec-complete" | "test-fix" | "ralph-iteration",
-  focusArea: "src/core/"
-})
-```
-
-### Detection Patterns
-
-| Type | Keywords |
-|------|----------|
-| Decisions | "decided", "chose", "selected" |
-| Learnings | "didn't work", "failed", "learned" |
-| Patterns | "pattern", "convention", "prefer" |
-
-### Skip Capture When
-
-- Trivial task (typo fix)
-- No decisions made
-- Only reading/exploring
-- Already captured recently
+# Testing & Quality
+
+Consolidated from: smart-tests, mandatory-review, auto-memory-capture, confidence-gate
+
+---
+
+## 80% Confidence Gate
+
+**Confidence Gate**: See `.claude/rules/dino/confidence.md` for thresholds, factors, and flow.
+
+---
+
+## Smart Test Optimization
+
+Reduce test run times by 60-80% through intelligent scope detection.
+
+### Test Scopes
+
+| Scope | When | Duration |
+|-------|------|----------|
+| SKIP | No changes since passing | Instant |
+| TARGETED | Single feature changes | Fast |
+| FULL | Cross-cutting changes | Complete |
+
+### Decision Tree
+
+```
+No changes since passing → SKIP
+Dependency/config changes → FULL
+Shared code (utils/, core/) → FULL
+Single feature changes → TARGETED
+Documentation only → SKIP
+```
+
+### Full Test Triggers
+
+- `package.json`, lock files
+- `tsconfig.json`, `vitest.config.ts`
+- Entry points (`index.ts`, `main.ts`)
+- Shared modules (`src/utils/`, `src/core/`, `src/lib/`)
+
+### Targeted Patterns
+
+| Focus | Pattern |
+|-------|---------|
+| `src/hooks/` | `hooks` |
+| `src/core/ralph/` | `ralph` |
+| `src/commands/*.ts` | `commands` |
+| Multiple features | FULL |
+
+### Usage in Skills
+
+**`/dino.aging`**: Uses smart test workflow to analyze scope before running tests.
+
+**`/dino.release`**: Uses smart test detection to optimize release verification.
+
+**`/dino.hunt`**: Uses incremental testing during implementation.
+
+### Performance Targets
+
+| Scenario | Target Duration |
+|----------|-----------------|
+| SKIP (no changes) | 0s |
+| TARGETED (single feature) | 10-30s |
+| FULL (must run all) | < 3 min |
+
+---
+
+## Mandatory Review
+
+Set `DINO_MANDATORY_REVIEW=true` to enable code review gate. Disabled by default.
+
+---
+
+## Auto-Memory Capture
+
+Preserve learnings after significant work.
+
+### When to Capture
+
+| Event | Source |
+|-------|--------|
+| /spec completes | Analysis decisions |
+| /hunt task completes | Implementation learnings |
+| Tests pass after fix | What fixed the issue |
+| User confirms decision | Decision text |
+| Ralph iteration | Iteration learnings |
+
+### How to Capture
+
+```
+dino_memory_auto_capture({
+  text: "Summary of decision or learning",
+  source: "spec-complete" | "test-fix" | "ralph-iteration",
+  focusArea: "src/core/"
+})
+```
+
+### Detection Patterns
+
+| Type | Keywords |
+|------|----------|
+| Decisions | "decided", "chose", "selected" |
+| Learnings | "didn't work", "failed", "learned" |
+| Patterns | "pattern", "convention", "prefer" |
+
+### Skip Capture When
+
+- Trivial task (typo fix)
+- No decisions made
+- Only reading/exploring
+- Already captured recently