claude-context-plugin 1.0.0

package/.claude-plugin/plugin.json

@@ -0,0 +1,23 @@
+{
+  "name": "claude-context-engineering",
+  "version": "1.0.0",
+  "displayName": "Context Engineering",
+  "description": "RPI workflow and context optimization for Claude Code - Research, Plan, Implement with file:line precision",
+  "author": {
+    "name": "SireJeff"
+  },
+  "license": "MIT",
+  "repository": {
+    "type": "git",
+    "url": "https://github.com/SireJeff/claude-context-engineering-template"
+  },
+  "keywords": [
+    "context-engineering",
+    "rpi-workflow",
+    "documentation",
+    "productivity"
+  ],
+  "claudeCode": {
+    "minVersion": "1.0.33"
+  }
+}

package/README.md

@@ -0,0 +1,104 @@
+# claude-context-plugin
+
+Claude Code plugin for context engineering - RPI workflow and documentation optimization.
+
+## Installation
+
+### Via Plugin Manager
+
+```bash
+/plugin install claude-context-engineering
+```
+
+### Via CLI
+
+```bash
+npx claude-plugins install claude-context-engineering
+```
+
+## Skills
+
+### /context-eng:research
+
+Systematic codebase exploration for feature/fix analysis.
+
+```
+/context-eng:research user-authentication
+```
+
+Creates a research document with:
+- Relevant files and line numbers
+- Call chain analysis
+- Dependency mapping
+- Test coverage gaps
+
+### /context-eng:plan
+
+Create implementation blueprint with file:line precision.
+
+```
+/context-eng:plan user-authentication
+```
+
+Creates a plan document with:
+- Exact file:line modifications
+- Risk assessment
+- Test strategy
+- Rollback plan
+
+### /context-eng:implement
+
+Execute plan with atomic changes and continuous testing.
+
+```
+/context-eng:implement user-authentication
+```
+
+Follows the golden rule: ONE CHANGE → ONE TEST → ONE COMMIT
+
+### /context-eng:validate
+
+Run complete validation suite.
+
+```
+/context-eng:validate
+```
+
+Checks:
+- Directory structure
+- JSON schemas
+- Markdown links
+- Placeholder completion
+- Line number accuracy
+
+### /context-eng:verify-docs
+
+Verify documentation line numbers match code.
+
+```
+/context-eng:verify-docs path/to/file.py
+```
+
+## Agents
+
+### @context-eng:context-engineer
+
+Initialize and maintain context engineering documentation.
+
+```
+@context-eng:context-engineer "Discover workflows for this codebase"
+```
+
+## Requirements
+
+- Claude Code v1.0.33+
+- Context engineering setup (use `npx create-claude-context` first)
+
+## License
+
+MIT
+
+## Links
+
+- [GitHub](https://github.com/SireJeff/claude-context-engineering-template)
+- [create-claude-context](https://www.npmjs.com/package/create-claude-context)

package/agents/context-engineer.md

@@ -0,0 +1,67 @@
+---
+name: context-engineer
+description: Initialize and maintain context engineering documentation for any codebase
+capabilities:
+  - Codebase analysis and workflow discovery
+  - Documentation generation with file:line references
+  - Index creation and maintenance
+  - Tech stack detection
+---
+
+# Context Engineer Agent
+
+I specialize in setting up and maintaining context engineering systems for codebases.
+
+## Primary Functions
+
+### 1. Initial Setup
+When asked to initialize or set up context engineering:
+- Analyze codebase structure
+- Detect technology stack
+- Discover major workflows (8-15)
+- Create workflow documentation with file:line references
+- Build index hierarchy
+
+### 2. Workflow Discovery
+When asked to discover or find workflows:
+- Scan for entry points (API routes, CLI commands, event handlers)
+- Trace call chains 3 levels deep
+- Document in `.claude/context/workflows/`
+- Update `WORKFLOW_INDEX.md`
+
+### 3. Re-indexing
+When asked to re-scan or update indexes:
+- Find new or changed files
+- Update line numbers in documentation
+- Add new workflows if discovered
+- Validate existing references
+
+### 4. Documentation Maintenance
+When documentation drift is detected:
+- Update line numbers
+- Fix broken references
+- Add missing workflows
+- Archive outdated docs
+
+## Output Format
+
+All documentation follows these standards:
+- File references: `path/to/file.py:123`
+- Line ranges: `file.py:100-150`
+- Markdown tables for structured data
+- Mermaid diagrams for flows
+
+## Context Budget
+
+- Initial setup: 40-50% utilization
+- Re-indexing: 20-30% utilization
+- Maintenance: 15-20% utilization
+
+## Example Invocations
+
+```
+@context-engineer "Initialize context engineering for this repository"
+@context-engineer "Discover workflows for the authentication module"
+@context-engineer "Re-scan and update indexes for recent changes"
+@context-engineer "Update line numbers in workflow documentation"
+```

package/package.json

@@ -0,0 +1,32 @@
+{
+  "name": "claude-context-plugin",
+  "version": "1.0.0",
+  "description": "Claude Code plugin for context engineering - RPI workflow and documentation optimization",
+  "keywords": [
+    "claude-code",
+    "plugin",
+    "context-engineering",
+    "rpi-workflow",
+    "documentation"
+  ],
+  "author": "SireJeff",
+  "license": "MIT",
+  "repository": {
+    "type": "git",
+    "url": "git+https://github.com/SireJeff/claude-context-engineering-template.git",
+    "directory": "packages/claude-context-plugin"
+  },
+  "bugs": {
+    "url": "https://github.com/SireJeff/claude-context-engineering-template/issues"
+  },
+  "homepage": "https://github.com/SireJeff/claude-context-engineering-template#readme",
+  "files": [
+    ".claude-plugin/",
+    "skills/",
+    "agents/",
+    "README.md"
+  ],
+  "peerDependencies": {
+    "claude-code": ">=1.0.33"
+  }
+}

package/skills/implement/SKILL.md

@@ -0,0 +1,71 @@
+---
+description: RPI Implement Phase - Execute plan with atomic changes and continuous testing
+---
+
+# Context Engineering: Implement Phase
+
+When invoked, execute the approved implementation plan:
+
+## Prerequisites
+- Approved plan at `.claude/plans/active/[feature]_plan.md`
+- If not found, run `/context-eng:plan $ARGUMENTS` first
+
+## Golden Rule
+
+```
+ONE CHANGE → ONE TEST → ONE COMMIT
+```
+
+## Process
+
+1. **Load Plan Document**
+   - Read `.claude/plans/active/[feature]_plan.md`
+   - Verify plan status is APPROVED
+
+2. **For Each Step in Plan:**
+   a. Make the single, atomic change
+   b. Run the specified test immediately
+   c. If test passes: commit with descriptive message
+   d. If test fails: STOP, investigate, fix before proceeding
+   e. Update documentation if needed
+
+3. **Documentation Updates (MANDATORY)**
+   - Check `CODE_TO_WORKFLOW_MAP.md` for affected workflows
+   - Update workflow files with new line numbers
+   - Update function signatures if changed
+
+4. **Context Reset (Every 3 Steps)**
+   - Update progress checklist in plan
+   - Re-read plan document
+   - Verify scope alignment
+   - Compact if >35% utilization
+
+5. **Finalize**
+   - Move plan to `.claude/plans/completed/`
+   - Move research to `.claude/research/completed/`
+   - Run `/context-eng:validate` to verify
+
+## Error Handling
+
+| Error Type | Response |
+|------------|----------|
+| Syntax Error | STOP. Fix immediately. |
+| Import Error | Check file paths, verify imports. |
+| Test Failure | Do NOT add more code. Investigate first. |
+| 3+ Failures | STOP. Start new session. |
+
+## Context Budget
+- Plan: 15k tokens
+- Active code: 30k tokens
+- Test results: 15k tokens
+- Total: 60k tokens (30%)
+
+## Commit Format
+```
+feat/fix/refactor(scope): description
+
+- Detail 1
+- Detail 2
+
+Implements: [feature]
+```

package/skills/plan/SKILL.md

@@ -0,0 +1,66 @@
+---
+description: RPI Plan Phase - Create implementation blueprint with file:line precision
+---
+
+# Context Engineering: Plan Phase
+
+When invoked, create a detailed implementation plan:
+
+## Prerequisites
+- Research document exists at `.claude/research/active/[feature]_research.md`
+- If not found, run `/context-eng:research $ARGUMENTS` first
+
+## Process
+
+1. **Load Research Document**
+   - Read the research document for $ARGUMENTS
+   - Extract relevant files and line numbers
+
+2. **Design Implementation**
+   - For each change required:
+     - Specify exact file and line numbers
+     - Show current code snippet
+     - Show proposed change
+     - Assign risk level (LOW/MEDIUM/HIGH)
+
+3. **Plan Test Strategy**
+   - Identify which tests to run after each change
+   - Note any new tests needed
+
+4. **Document Rollback Plan**
+   - Safe commit to revert to
+   - Commands to undo changes
+
+5. **Create Plan Document**
+   - Save to `.claude/plans/active/[feature]_plan.md`
+   - Include verification checklist
+
+## Plan Format
+
+```markdown
+# Implementation Plan: [Feature]
+
+## Files to Modify
+| File | Lines | Change | Risk |
+|------|-------|--------|------|
+
+## Step-by-Step
+### Step 1: [Action]
+**File:** path/to/file.ext
+**Lines:** X-Y
+**Current:** [code block]
+**Proposed:** [code block]
+**Test:** [command]
+
+## Rollback
+- Safe commit: [hash]
+- Command: git revert HEAD
+```
+
+## Context Budget
+- Research doc: 20k tokens
+- Plan creation: 15k tokens
+- Total: 35k tokens (17.5%)
+
+## Next Step
+After approval, run `/context-eng:implement $ARGUMENTS`

package/skills/research/SKILL.md

@@ -0,0 +1,43 @@
+---
+description: RPI Research Phase - Systematic codebase exploration for feature/fix analysis
+---
+
+# Context Engineering: Research Phase
+
+When invoked, perform systematic codebase exploration:
+
+## Process
+
+1. **Initialize Research Document**
+   - Create `.claude/research/active/[feature]_research.md`
+   - Use template from `.claude/research/RESEARCH_TEMPLATE.md`
+
+2. **Entry Point Discovery**
+   - Search for API routes, CLI commands, event handlers related to $ARGUMENTS
+   - Use parallel exploration for efficiency (up to 3 agents)
+
+3. **Call Chain Tracing**
+   - Trace 3 levels deep from entry points
+   - Record exact file:line references for each function
+
+4. **Dependency Mapping**
+   - Internal: services, models, utilities used
+   - External: APIs, databases, third-party services
+
+5. **Test Coverage Analysis**
+   - Find existing tests for affected code
+   - Identify coverage gaps
+
+6. **Generate Summary**
+   - 150-word summary for Plan phase
+   - List 3-20 relevant files with line numbers
+
+## Context Budget
+- Target: 25% of 200k tokens (50k)
+- Final output: ~20k tokens (research doc only)
+
+## Output
+Research document saved to `.claude/research/active/`
+
+## Next Step
+After completion, run `/context-eng:plan $ARGUMENTS`

package/skills/validate/SKILL.md

@@ -0,0 +1,62 @@
+---
+description: Run complete validation suite on context engineering documentation
+---
+
+# Context Engineering: Validation
+
+Run comprehensive validation on the context engineering setup.
+
+## Validation Checks
+
+### 1. Structure Validation
+- All required directories exist in `.claude/`
+- Required files are present
+- Settings file is valid JSON
+
+### 2. Schema Validation
+- JSON files validate against their schemas
+- Frontmatter in markdown files is valid
+
+### 3. Link Validation
+- All internal markdown links resolve
+- No broken references to files or anchors
+
+### 4. Placeholder Detection
+- Find remaining `{{PLACEHOLDER}}` values
+- Report files that need manual completion
+
+### 5. Line Number Accuracy
+- Sample referenced line numbers in documentation
+- Verify they match actual code
+- Target: ≥60% accuracy
+
+## Output
+
+```
+Validation Results
+==================
+✓ Structure: PASS (12/12 directories)
+✓ Schemas: PASS (5/5 files valid)
+✓ Links: PASS (45/45 links resolve)
+⚠ Placeholders: WARN (3 remaining in 2 files)
+✓ Line Accuracy: PASS (78% accurate)
+
+Overall: PASS with warnings
+```
+
+## Usage
+
+Run validation:
+- Full suite: `/context-eng:validate`
+- Specific check: `/context-eng:validate --links`
+- With fix: `/context-eng:validate --fix`
+
+## Thresholds
+
+| Check | Pass | Warn | Fail |
+|-------|------|------|------|
+| Structure | 100% | - | <100% |
+| Schemas | 100% | - | <100% |
+| Links | 100% | <100% | <90% |
+| Placeholders | 0 | 1-5 | >5 |
+| Line Accuracy | ≥60% | 50-60% | <50% |

package/skills/verify-docs/SKILL.md

@@ -0,0 +1,77 @@
+---
+description: Verify documentation line numbers match current code state
+---
+
+# Context Engineering: Verify Documentation
+
+Check if documentation line numbers still match the actual code.
+
+## Purpose
+
+After code changes, line numbers in documentation may drift. This skill:
+1. Finds all `file:line` references in `.claude/` documentation
+2. Verifies the referenced lines exist and match described content
+3. Reports accuracy and suggests fixes
+
+## Process
+
+1. **Scan Documentation**
+   - Find all patterns like `file.py:123` or `[file.py:123]`
+   - Extract file path and line number
+
+2. **Verify References**
+   - Check if file exists
+   - Check if line number is within file bounds
+   - Sample content to verify it matches description
+
+3. **Calculate Accuracy**
+   - Total references found
+   - Valid references
+   - Accuracy percentage
+
+4. **Generate Report**
+   ```
+   Documentation Accuracy Report
+   =============================
+   Total References: 156
+   Valid: 142
+   Invalid: 14
+   Accuracy: 91%
+
+   Invalid References:
+   - context/workflows/auth.md:45 → src/auth.py:230 (line moved to 245)
+   - context/workflows/api.md:12 → src/api.py:100 (file renamed)
+   ```
+
+## Usage
+
+Check specific file:
+```
+/context-eng:verify-docs path/to/changed/file.py
+```
+
+Check all documentation:
+```
+/context-eng:verify-docs
+```
+
+Auto-fix (update line numbers):
+```
+/context-eng:verify-docs --fix
+```
+
+## Target Accuracy
+
+| Level | Accuracy | Action |
+|-------|----------|--------|
+| Excellent | ≥80% | No action needed |
+| Good | 60-80% | Update when convenient |
+| Warning | 40-60% | Update soon |
+| Critical | <40% | Update immediately |
+
+## When to Run
+
+- After refactoring
+- After adding/removing significant code
+- Before creating a PR
+- Weekly maintenance