codebase-analyzer-mcp 2.0.5 → 2.1.1

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
@@ -6,13 +6,13 @@
6
6
  },
7
7
  "metadata": {
8
8
  "description": "Multi-layer codebase analysis tools",
9
- "version": "2.0.5"
9
+ "version": "2.1.1"
10
10
  },
11
11
  "plugins": [
12
12
  {
13
13
  "name": "codebase-analyzer",
14
- "description": "Multi-layer codebase analysis with Gemini AI. 4 agents, 5 commands, 3 skills for architecture analysis, pattern detection, and dataflow tracing.",
15
- "version": "2.0.5",
14
+ "description": "Multi-layer codebase analysis with Gemini AI. 4 agents, 1 command, 1 skill for architecture analysis, pattern detection, and dataflow tracing.",
15
+ "version": "2.1.1",
16
16
  "author": {
17
17
  "name": "Jake Correa",
18
18
  "url": "https://github.com/jaykaycodes"
@@ -1,7 +1,7 @@
1
1
  {
2
2
  "name": "codebase-analyzer",
3
- "version": "2.0.5",
4
- "description": "Multi-layer codebase analysis with Gemini AI. 4 agents, 5 commands, 3 skills for architecture analysis, pattern detection, and dataflow tracing.",
3
+ "version": "2.1.1",
4
+ "description": "Multi-layer codebase analysis with Gemini AI. 4 agents, 1 command, 1 skill for architecture analysis, pattern detection, and dataflow tracing.",
5
5
  "author": {
6
6
  "name": "Jake Correa",
7
7
  "url": "https://github.com/jaykaycodes"
package/CLAUDE.md CHANGED
@@ -23,8 +23,8 @@ pnpm install && pnpm build
23
23
  | Component | Count | Purpose |
24
24
  |-----------|-------|---------|
25
25
  | Agents | 4 | Specialized analysis tasks |
26
- | Commands | 5 | User-invocable actions |
27
- | Skills | 3 | Context-loaded guidance |
26
+ | Commands | 1 | User-invocable actions |
27
+ | Skills | 1 | Context-loaded guidance |
28
28
  | MCP Server | 1 | Tool interface for Claude |
29
29
 
30
30
  ### Agents
@@ -40,19 +40,13 @@ pnpm install && pnpm build
40
40
 
41
41
  | Command | Usage |
42
42
  |---------|-------|
43
- | `/analyze` | Analyze a codebase |
44
- | `/patterns` | Find design patterns |
45
- | `/trace` | Trace data flow |
46
- | `/explore` | Quick exploration |
47
- | `/compare` | Compare repositories |
43
+ | `/cba:analyze` | Analyze a codebase |
48
44
 
49
45
  ### Skills
50
46
 
51
47
  | Skill | Purpose |
52
48
  |-------|---------|
53
- | `codebase-analysis` | How to use the MCP tools |
54
- | `add-mcp-tool` | Guide for adding new tools |
55
- | `debugging-analysis` | Troubleshooting analysis issues |
49
+ | `cba:codebase-analysis` | How to use the MCP tools |
56
50
 
57
51
  ## Architecture
58
52
 
@@ -77,7 +71,9 @@ See [docs/ARCHITECTURE.md](docs/ARCHITECTURE.md) for system design.
77
71
  | Tool | Purpose | Cost |
78
72
  |------|---------|------|
79
73
  | `analyze_repo` | Full analysis with expandable sections | Varies |
74
+ | `query_repo` | Ask questions about a codebase | Medium |
80
75
  | `expand_section` | Drill into specific sections | Low |
76
+ | `read_files` | Read source files from cached analysis | None |
81
77
  | `find_patterns` | Pattern detection | Medium |
82
78
  | `trace_dataflow` | Data flow tracing | Medium |
83
79
  | `get_analysis_capabilities` | List capabilities | None |
package/README.md CHANGED
@@ -13,7 +13,7 @@ Analyze any codebase with Gemini AI. Progressive disclosure keeps costs low - st
13
13
  claude /plugin install https://github.com/jaykaycodes/codebase-analyzer-mcp
14
14
  ```
15
15
 
16
- Then use `/analyze`, `/patterns`, `/trace`, or `/explore` commands.
16
+ Then use `/cba:analyze` to analyze a codebase, or just ask questions naturally.
17
17
 
18
18
  ### MCP Server
19
19
 
@@ -30,7 +30,7 @@ Add to `~/.mcp.json` (create if it doesn't exist):
30
30
  }
31
31
  ```
32
32
 
33
- Restart Claude Code, then use the `analyze_repo`, `find_patterns`, or `trace_dataflow` tools.
33
+ Restart Claude Code, then use the `analyze_repo` or `query_repo` tools.
34
34
 
35
35
  **Optional:** For semantic analysis with Gemini AI, get an API key at https://aistudio.google.com/apikey and add it:
36
36
 
@@ -51,11 +51,12 @@ Restart Claude Code, then use the `analyze_repo`, `find_patterns`, or `trace_dat
51
51
  ### CLI
52
52
 
53
53
  ```bash
54
- npx codebase-analyzer-mcp analyze . # Standard analysis
55
- npx codebase-analyzer-mcp analyze . -d surface # Fast, free overview
56
- npx codebase-analyzer-mcp analyze . -d deep -s # Full semantic analysis
57
- npx codebase-analyzer-mcp patterns . # Find design patterns
58
- npx codebase-analyzer-mcp dataflow . "user login" # Trace data flow
54
+ npx codebase-analyzer-mcp analyze . # Standard analysis
55
+ npx codebase-analyzer-mcp analyze . -d surface # Fast, free overview
56
+ npx codebase-analyzer-mcp analyze . -d deep -s # Full semantic analysis
57
+ npx codebase-analyzer-mcp query . "how is auth handled?" # Ask a question
58
+ npx codebase-analyzer-mcp patterns . # Find design patterns
59
+ npx codebase-analyzer-mcp dataflow . "user login" # Trace data flow
59
60
  ```
60
61
 
61
62
  ## What It Does
@@ -73,19 +74,31 @@ Analysis results include expandable sections - you only pay for what you drill i
73
74
  | Tool | Description |
74
75
  |------|-------------|
75
76
  | `analyze_repo` | Full analysis with progressive disclosure |
77
+ | `query_repo` | Ask questions about a codebase |
76
78
  | `expand_section` | Drill into specific sections |
79
+ | `read_files` | Read source files from a cached analysis |
77
80
  | `find_patterns` | Detect design/architecture patterns |
78
81
  | `trace_dataflow` | Trace data flow through the system |
82
+ | `get_analysis_capabilities` | List supported languages and analysis options |
79
83
 
80
- ## Plugin Commands & Agents
84
+ ## Plugin
81
85
 
82
- | Command | Agent | Purpose |
83
- |---------|-------|---------|
84
- | `/analyze` | `architecture-analyzer` | Full architecture analysis |
85
- | `/patterns` | `pattern-detective` | Find design patterns |
86
- | `/trace` | `dataflow-tracer` | Trace data flow |
87
- | `/explore` | `codebase-explorer` | Quick exploration |
88
- | `/compare` | - | Compare repositories |
86
+ ### Command
87
+
88
+ ```
89
+ /cba:analyze [source] [--depth surface|standard|deep] [--focus <paths>]
90
+ ```
91
+
92
+ ### Agents
93
+
94
+ | Agent | Purpose |
95
+ |-------|---------|
96
+ | `architecture-analyzer` | Full codebase architecture analysis |
97
+ | `pattern-detective` | Design/anti-pattern detection |
98
+ | `dataflow-tracer` | Data flow tracing through systems |
99
+ | `codebase-explorer` | Quick exploration and Q&A |
100
+
101
+ Agents are routed automatically based on your question — just ask naturally.
89
102
 
90
103
  ---
91
104
 
@@ -105,7 +118,7 @@ git clone https://github.com/jaykaycodes/codebase-analyzer-mcp.git
105
118
  cd codebase-analyzer-mcp
106
119
  bun install
107
120
  bun run dev # Watch mode
108
- bun run build:js # Build JS
121
+ bun run build # Build
109
122
  bun run cba analyze . # Test CLI
110
123
  ```
111
124
 
@@ -1,5 +1,5 @@
1
1
  ---
2
- name: architecture-analyzer
2
+ name: cba:architecture-analyzer
3
3
  description: "Use this agent when you need to understand a codebase's architecture, identify patterns, and get a high-level overview. This agent uses the codebase-analyzer MCP to perform multi-layer analysis with progressive disclosure - starting cheap and drilling down as needed.\n\n<example>Context: User wants to understand a new codebase.\nuser: \"Help me understand the architecture of this repo\"\nassistant: \"I'll use the architecture-analyzer agent to analyze the codebase structure and patterns.\"\n<commentary>Since the user wants architectural understanding, use architecture-analyzer to run progressive analysis.</commentary></example>\n\n<example>Context: User is evaluating a library.\nuser: \"What patterns does this library use?\"\nassistant: \"Let me use the architecture-analyzer agent to detect patterns in this codebase.\"\n<commentary>Pattern detection is a core capability of architecture-analyzer.</commentary></example>"
4
4
  model: haiku
5
5
  ---
@@ -1,5 +1,5 @@
1
1
  ---
2
- name: dataflow-tracer
2
+ name: cba:dataflow-tracer
3
3
  description: "Use this agent when you need to understand how data flows through a system - from entry points through transformations to outputs. Essential for debugging, security analysis, and understanding complex systems.\n\n<example>Context: User debugging data issue.\nuser: \"How does user input flow through the checkout process?\"\nassistant: \"I'll use the dataflow-tracer agent to trace the data path.\"\n<commentary>Tracing data from entry point through system is dataflow-tracer's specialty.</commentary></example>\n\n<example>Context: Security review.\nuser: \"Where does this API input go? I want to check for injection risks.\"\nassistant: \"Let me trace the dataflow from that API endpoint.\"\n<commentary>Security-focused dataflow tracing.</commentary></example>"
4
4
  model: haiku
5
5
  ---
@@ -1,5 +1,5 @@
1
1
  ---
2
- name: pattern-detective
2
+ name: cba:pattern-detective
3
3
  description: "Use this agent when you need to find specific design patterns, anti-patterns, or architectural patterns in a codebase. Specializes in pattern detection with confidence levels and location mapping.\n\n<example>Context: User suspects anti-patterns in code.\nuser: \"Are there any anti-patterns in this codebase?\"\nassistant: \"I'll use the pattern-detective agent to scan for anti-patterns.\"\n<commentary>Pattern detection with focus on anti-patterns is pattern-detective's specialty.</commentary></example>\n\n<example>Context: User wants to understand design decisions.\nuser: \"What design patterns are used in this authentication system?\"\nassistant: \"Let me use the pattern-detective agent to analyze patterns in the auth code.\"\n<commentary>Focused pattern analysis with area filtering.</commentary></example>"
4
4
  model: haiku
5
5
  ---
@@ -1,5 +1,5 @@
1
1
  ---
2
- name: codebase-explorer
2
+ name: cba:codebase-explorer
3
3
  description: "Use this agent for open-ended codebase exploration - understanding structure, finding relevant files, and answering questions about how things work. Lighter weight than full architecture analysis.\n\n<example>Context: User exploring new codebase.\nuser: \"What's in this repo?\"\nassistant: \"I'll use the codebase-explorer agent to give you a quick overview.\"\n<commentary>Quick exploration, not deep analysis.</commentary></example>\n\n<example>Context: User looking for specific functionality.\nuser: \"Where is the email sending logic?\"\nassistant: \"Let me explore the codebase to find email-related code.\"\n<commentary>Targeted exploration for specific functionality.</commentary></example>"
4
4
  model: haiku
5
5
  ---
@@ -24,10 +24,9 @@ Extract:
24
24
 
25
25
  ### Targeted Search
26
26
 
27
- For "where is X?" questions:
27
+ For "where is X?" or "how does X work?" questions:
28
28
 
29
- 1. **Surface scan** to understand structure
30
- 2. **Query the repo** for specific questions:
29
+ 1. **Query the repo** for AI-powered answers:
31
30
 
32
31
  ```
33
32
  mcp__codebase-analyzer__query_repo(
@@ -36,14 +35,21 @@ mcp__codebase-analyzer__query_repo(
36
35
  )
37
36
  ```
38
37
 
39
- ### Comparison
38
+ 2. **Read relevant files** using the analysisId from the response:
40
39
 
41
- For "how does this compare to Y?":
40
+ ```
41
+ mcp__codebase-analyzer__read_files(
42
+ analysisId: "<from query_repo result>",
43
+ paths: ["src/services/email.ts", "src/templates/"]
44
+ )
45
+ ```
46
+
47
+ 3. **Expand sections** for deeper module understanding:
42
48
 
43
49
  ```
44
- mcp__codebase-analyzer__compare_repos(
45
- sources: ["<path1>", "<path2>"],
46
- aspect: "authentication"
50
+ mcp__codebase-analyzer__expand_section(
51
+ analysisId: "<from query_repo result>",
52
+ sectionId: "module_src_services"
47
53
  )
48
54
  ```
49
55
 
@@ -95,7 +101,9 @@ mcp__codebase-analyzer__compare_repos(
95
101
  ## Guidelines
96
102
 
97
103
  **DO:**
98
- - Start with surface analysis (fast, cheap)
104
+ - Start with `query_repo` for targeted questions (fast, reuses cache)
105
+ - Use `analyze_repo` with surface depth for overviews
106
+ - Follow up with `read_files` to examine specific code
99
107
  - Give actionable summaries, not data dumps
100
108
  - Point to specific files and line numbers
101
109
  - Suggest what to explore next
@@ -1,5 +1,5 @@
1
1
  ---
2
- name: analyze
2
+ name: cba:analyze
3
3
  description: Analyze a codebase with progressive disclosure
4
4
  user-invocable: true
5
5
  ---
@@ -11,7 +11,7 @@ Analyze a repository using multi-layer progressive disclosure.
11
11
  ## Usage
12
12
 
13
13
  ```
14
- /analyze [source] [options]
14
+ /cba:analyze [source] [options]
15
15
  ```
16
16
 
17
17
  **Arguments:**
@@ -26,19 +26,19 @@ Analyze a repository using multi-layer progressive disclosure.
26
26
 
27
27
  ```bash
28
28
  # Analyze current directory
29
- /analyze
29
+ /cba:analyze
30
30
 
31
31
  # Analyze with surface depth (fast)
32
- /analyze --depth surface
32
+ /cba:analyze --depth surface
33
33
 
34
34
  # Analyze specific GitHub repo
35
- /analyze https://github.com/user/repo
35
+ /cba:analyze https://github.com/user/repo
36
36
 
37
37
  # Focus on specific module
38
- /analyze --focus src/api
38
+ /cba:analyze --focus src/api
39
39
 
40
40
  # Deep analysis with semantics
41
- /analyze --depth deep --semantics
41
+ /cba:analyze --depth deep --semantics
42
42
  ```
43
43
 
44
44
  ## Workflow
@@ -58,7 +58,7 @@ const focus = args.focus;
58
58
  const semantics = args.semantics || false;
59
59
 
60
60
  // Use architecture-analyzer agent
61
- Task("architecture-analyzer", {
61
+ Task("cba:architecture-analyzer", {
62
62
  prompt: `Analyze ${source} at ${depth} depth${focus ? `, focusing on ${focus}` : ""}${semantics ? " with semantic analysis" : ""}`
63
63
  });
64
64
  ```