feat: add Qoder platform support

.gitignore

@@ -43,6 +43,10 @@ code-review-graph-vscode/dist/
 .claude/
 .claude-plugin/
 
+# Qoder
+.qoder/
+QODER.md
+
 # Coverage
 htmlcov/
 .coverage

CLAUDE.md

@@ -113,3 +113,42 @@ uv run code-review-graph eval               # Run evaluation benchmarks
 - **type-check**: mypy
 - **security**: bandit scan
 - **test**: pytest matrix (3.10, 3.11, 3.12, 3.13) with 50% coverage minimum
+
+<!-- code-review-graph MCP tools -->
+## MCP Tools: code-review-graph
+
+**IMPORTANT: This project has a knowledge graph. ALWAYS use the
+code-review-graph MCP tools BEFORE using Grep/Glob/Read to explore
+the codebase.** The graph is faster, cheaper (fewer tokens), and gives
+you structural context (callers, dependents, test coverage) that file
+scanning cannot.
+
+### When to use graph tools FIRST
+
+- **Exploring code**: `semantic_search_nodes` or `query_graph` instead of Grep
+- **Understanding impact**: `get_impact_radius` instead of manually tracing imports
+- **Code review**: `detect_changes` + `get_review_context` instead of reading entire files
+- **Finding relationships**: `query_graph` with callers_of/callees_of/imports_of/tests_for
+- **Architecture questions**: `get_architecture_overview` + `list_communities`
+
+Fall back to Grep/Glob/Read **only** when the graph doesn't cover what you need.
+
+### Key Tools
+
+| Tool | Use when |
+|------|----------|
+| `detect_changes` | Reviewing code changes — gives risk-scored analysis |
+| `get_review_context` | Need source snippets for review — token-efficient |
+| `get_impact_radius` | Understanding blast radius of a change |
+| `get_affected_flows` | Finding which execution paths are impacted |
+| `query_graph` | Tracing callers, callees, imports, tests, dependencies |
+| `semantic_search_nodes` | Finding functions/classes by name or keyword |
+| `get_architecture_overview` | Understanding high-level codebase structure |
+| `refactor_tool` | Planning renames, finding dead code |
+
+### Workflow
+
+1. The graph auto-updates on file changes (via hooks).
+2. Use `detect_changes` for code review.
+3. Use `get_affected_flows` to understand impact.
+4. Use `query_graph` pattern="tests_for" to check coverage.

README.md

@@ -36,7 +36,7 @@ code-review-graph build            # parse your codebase
 One command sets up everything. `install` detects which AI coding tools you have, writes the correct MCP configuration for each one, and injects graph-aware instructions into your platform rules. It auto-detects whether you installed via `uvx` or `pip`/`pipx` and generates the right config. Restart your editor/tool after installing.
 
 <p align="center">
-  <img src="diagrams/diagram8_supported_platforms.png" alt="One Install, Every Platform: auto-detects Codex, Claude Code, Cursor, Windsurf, Zed, Continue, OpenCode, and Antigravity" width="85%" />
+  <img src="diagrams/diagram8_supported_platforms.png" alt="One Install, Every Platform: auto-detects Codex, Claude Code, Cursor, Windsurf, Zed, Continue, OpenCode, Antigravity, Qwen, and Qoder" width="85%" />
 </p>
 
 To target a specific platform:
@@ -331,5 +331,5 @@ MIT. See [LICENSE](LICENSE).
 <br>
 <a href="https://code-review-graph.com">code-review-graph.com</a><br><br>
 <code>pip install code-review-graph && code-review-graph install</code><br>
-<sub>Works with Codex, Claude Code, Cursor, Windsurf, Zed, Continue, OpenCode, and Antigravity</sub>
+<sub>Works with Codex, Claude Code, Cursor, Windsurf, Zed, Continue, OpenCode, Antigravity, Qwen, and Qoder</sub>
 </p>

code_review_graph/cli.py

@@ -38,6 +38,12 @@
 
 logger = logging.getLogger(__name__)
 
+# Shared platform choices for install and init commands
+_PLATFORM_CHOICES = [
+    "codex", "claude", "claude-code", "cursor", "windsurf", "zed",
+    "continue", "opencode", "antigravity", "qwen", "qoder", "all",
+]
+
 
 def _get_version() -> str:
     """Get the installed package version."""
@@ -211,6 +217,7 @@ def _handle_init(args: argparse.Namespace) -> None:
         inject_platform_instructions,
         install_git_hook,
         install_hooks,
+        install_qoder_skills,
     )
 
     if not skip_skills:
@@ -237,9 +244,17 @@ def _handle_init(args: argparse.Namespace) -> None:
     elif skip_instructions:
         print("Skipped instruction injection (--no-instructions).")
 
-    if not skip_hooks and target in ("claude", "all"):
-        install_hooks(repo_root)
-        print(f"Installed hooks in {repo_root / '.claude' / 'settings.json'}")
+
+    # Install Qoder skills (global user-level skills directory)
+    if not skip_skills and target in ("qoder", "all"):
+        qoder_skills_dir = install_qoder_skills(repo_root)
+        if qoder_skills_dir:
+            print(f"Installed Qoder skills to {qoder_skills_dir}")
+    if not skip_hooks and target in ("claude", "qoder", "all"):
+        platforms_to_install = [target] if target != "all" else ["claude", "qoder"]
+        for plat in platforms_to_install:
+            install_hooks(repo_root, platform=plat)
+            print(f"Installed hooks in {repo_root / f'.{plat}' / 'settings.json'}")
         git_hook = install_git_hook(repo_root)
         if git_hook:
             print(f"Installed git pre-commit hook in {git_hook}")
@@ -293,10 +308,7 @@ def main() -> None:
                              help=argparse.SUPPRESS)
     install_cmd.add_argument(
         "--platform",
-        choices=[
-            "codex", "claude", "claude-code", "cursor", "windsurf", "zed",
-            "continue", "opencode", "antigravity", "qwen", "all",
-        ],
+        choices=_PLATFORM_CHOICES,
         default="all",
         help="Target platform for MCP config (default: all detected)",
     )
@@ -331,10 +343,7 @@ def main() -> None:
                              help=argparse.SUPPRESS)
     init_cmd.add_argument(
         "--platform",
-        choices=[
-            "codex", "claude", "claude-code", "cursor", "windsurf", "zed",
-            "continue", "opencode", "antigravity", "qwen", "all",
-        ],
+        choices=_PLATFORM_CHOICES,
         default="all",
         help="Target platform for MCP config (default: all detected)",
     )

code_review_graph/skills.py

@@ -100,6 +100,14 @@ def _zed_settings_path() -> Path:
         "format": "object",
         "needs_type": True,
     },
+    "qoder": {
+        "name": "Qoder",
+        "config_path": lambda root: root / ".qoder" / "mcp.json",
+        "key": "mcpServers",
+        "detect": lambda: True,
+        "format": "object",
+        "needs_type": True,
+    },
 }
 
 
@@ -481,16 +489,20 @@ def install_git_hook(repo_root: Path) -> Path | None:
     return hook_path
 
 
-def install_hooks(repo_root: Path) -> None:
-    """Write hooks config to .claude/settings.json.
+def install_hooks(repo_root: Path, platform: str = "claude") -> None:
+    """Write hooks config to platform-specific settings.json.
 
     Merges with existing settings if present, preserving non-hook
     configuration.
 
     Args:
         repo_root: Repository root directory.
+        platform: Target platform ("claude" or "qoder").
     """
-    settings_dir = repo_root / ".claude"
+    if platform == "qoder":
+        settings_dir = repo_root / ".qoder"
+    else:
+        settings_dir = repo_root / ".claude"
     settings_dir.mkdir(parents=True, exist_ok=True)
     settings_path = settings_dir / "settings.json"
 
@@ -591,6 +603,7 @@ def inject_claude_md(repo_root: Path) -> None:
     "GEMINI.md": ("antigravity",),
     ".cursorrules": ("cursor",),
     ".windsurfrules": ("windsurf",),
+    "QODER.md": ("qoder",),
 }
 
 
@@ -615,3 +628,43 @@ def inject_platform_instructions(repo_root: Path, target: str = "all") -> list[s
         if _inject_instructions(path, _CLAUDE_MD_SECTION_MARKER, _CLAUDE_MD_SECTION):
             updated.append(filename)
     return updated
+
+
+def install_qoder_skills(repo_root: Path) -> Path | None:
+    """Install skills to Qoder's project-level skills directory.
+
+    Qoder expects skills in .qoder/skills/{skillName}/SKILL.md format within the project.
+    This function copies the project's skills/ directory contents to that location.
+
+    Args:
+        repo_root: Repository root directory (where the skills/ folder is located).
+
+    Returns:
+        Path to the Qoder skills directory, or None if installation failed.
+    """
+    # Qoder skills directory (project-level)
+    qoder_skills_dir = repo_root / ".qoder" / "skills"
+    qoder_skills_dir.mkdir(parents=True, exist_ok=True)
+
+    # Source skills directory in the project
+    source_skills_dir = repo_root / "skills"
+    if not source_skills_dir.exists():
+        logger.warning("No skills/ directory found in %s", repo_root)
+        return None
+
+    installed_count = 0
+    for skill_dir in source_skills_dir.iterdir():
+        if skill_dir.is_dir():
+            skill_file = skill_dir / "SKILL.md"
+            if skill_file.exists():
+                target_dir = qoder_skills_dir / skill_dir.name
+                target_dir.mkdir(parents=True, exist_ok=True)
+                target_file = target_dir / "SKILL.md"
+                target_file.write_text(skill_file.read_text(encoding="utf-8"), encoding="utf-8")
+                logger.info("Installed Qoder skill: %s", skill_dir.name)
+                installed_count += 1
+
+    if installed_count > 0:
+        logger.info("Installed %d skill(s) to %s", installed_count, qoder_skills_dir)
+        return qoder_skills_dir
+    return None

diagrams/generate_diagrams.py

@@ -595,6 +595,8 @@ def d8():
         ("Continue",     "~/.continue/config.json",              YLW, YLW_BG),
         ("OpenCode",     ".opencode.json",                       RED, RED_BG),
         ("Antigravity",  "~/.gemini/antigravity/mcp_config.json",GRY, GRY_BG),
+        ("Qwen Code",    "~/.qwen/settings.json",                BLU, PRP_BG),  # blue-purple
+        ("Qoder",        ".qoder/mcp.json",                      GRN, ORG_BG),  # green-orange
     ]
 
     # Central "install" node
@@ -604,8 +606,8 @@ def d8():
 
     # Fan out to platforms
     cols = len(platforms)
-    card_w, card_h = 140, 80
-    total_w = cols * card_w + (cols-1) * 20
+    card_w, card_h = 120, 80  # narrower cards for 9 platforms
+    total_w = cols * card_w + (cols-1) * 15  # tighter spacing
     x0 = center_x - total_w/2
     card_y = 360
 

docs/USAGE.md

@@ -30,7 +30,10 @@ code-review-graph install --platform claude-code
 | **Windsurf** | `.windsurf/mcp.json` |
 | **Zed** | `.zed/settings.json` |
 | **Continue** | `.continue/config.json` |
-| **OpenCode** | `.opencode/config.json` |
+| **OpenCode** | `.opencode.json` |
+| **Antigravity** | `~/.gemini/antigravity/mcp_config.json` |
+| **Qwen Code** | `~/.qwen/settings.json` |
+| **Qoder** | `.qoder/mcp.json` |
 
 ## Core Workflow
 

skills/debug-issue/SKILL.md

@@ -0,0 +1,27 @@
+---
+name: Debug Issue
+description: Systematically debug issues using graph-powered code navigation
+---
+
+## Debug Issue
+
+Use the knowledge graph to systematically trace and debug issues.
+
+### Steps
+
+1. Use `semantic_search_nodes` to find code related to the issue.
+2. Use `query_graph` with `callers_of` and `callees_of` to trace call chains.
+3. Use `get_flow` to see full execution paths through suspected areas.
+4. Run `detect_changes` to check if recent changes caused the issue.
+5. Use `get_impact_radius` on suspected files to see what else is affected.
+
+### Tips
+
+- Check both callers and callees to understand the full context.
+- Look at affected flows to find the entry point that triggers the bug.
+- Recent changes are the most common source of new issues.
+
+## Token Efficiency Rules
+- ALWAYS start with `get_minimal_context(task="<your task>")` before any other graph tool.
+- Use `detail_level="minimal"` on all calls. Only escalate to "standard" when minimal is insufficient.
+- Target: complete any review/debug/refactor task in ≤5 tool calls and ≤800 total output tokens.

skills/explore-codebase/SKILL.md

@@ -0,0 +1,28 @@
+---
+name: Explore Codebase
+description: Navigate and understand codebase structure using the knowledge graph
+---
+
+## Explore Codebase
+
+Use the code-review-graph MCP tools to explore and understand the codebase.
+
+### Steps
+
+1. Run `list_graph_stats` to see overall codebase metrics.
+2. Run `get_architecture_overview` for high-level community structure.
+3. Use `list_communities` to find major modules, then `get_community` for details.
+4. Use `semantic_search_nodes` to find specific functions or classes.
+5. Use `query_graph` with patterns like `callers_of`, `callees_of`, `imports_of` to trace relationships.
+6. Use `list_flows` and `get_flow` to understand execution paths.
+
+### Tips
+
+- Start broad (stats, architecture) then narrow down to specific areas.
+- Use `children_of` on a file to see all its functions and classes.
+- Use `find_large_functions` to identify complex code.
+
+## Token Efficiency Rules
+- ALWAYS start with `get_minimal_context(task="<your task>")` before any other graph tool.
+- Use `detail_level="minimal"` on all calls. Only escalate to "standard" when minimal is insufficient.
+- Target: complete any review/debug/refactor task in ≤5 tool calls and ≤800 total output tokens.

skills/refactor-safely/SKILL.md

@@ -0,0 +1,28 @@
+---
+name: Refactor Safely
+description: Plan and execute safe refactoring using dependency analysis
+---
+
+## Refactor Safely
+
+Use the knowledge graph to plan and execute refactoring with confidence.
+
+### Steps
+
+1. Use `refactor_tool` with mode="suggest" for community-driven refactoring suggestions.
+2. Use `refactor_tool` with mode="dead_code" to find unreferenced code.
+3. For renames, use `refactor_tool` with mode="rename" to preview all affected locations.
+4. Use `apply_refactor_tool` with the refactor_id to apply renames.
+5. After changes, run `detect_changes` to verify the refactoring impact.
+
+### Safety Checks
+
+- Always preview before applying (rename mode gives you an edit list).
+- Check `get_impact_radius` before major refactors.
+- Use `get_affected_flows` to ensure no critical paths are broken.
+- Run `find_large_functions` to identify decomposition targets.
+
+## Token Efficiency Rules
+- ALWAYS start with `get_minimal_context(task="<your task>")` before any other graph tool.
+- Use `detail_level="minimal"` on all calls. Only escalate to "standard" when minimal is insufficient.
+- Target: complete any review/debug/refactor task in ≤5 tool calls and ≤800 total output tokens.

skills/review-changes/SKILL.md

@@ -0,0 +1,29 @@
+---
+name: Review Changes
+description: Perform a structured code review using change detection and impact
+---
+
+## Review Changes
+
+Perform a thorough, risk-aware code review using the knowledge graph.
+
+### Steps
+
+1. Run `detect_changes` to get risk-scored change analysis.
+2. Run `get_affected_flows` to find impacted execution paths.
+3. For each high-risk function, run `query_graph` with pattern="tests_for" to check test coverage.
+4. Run `get_impact_radius` to understand the blast radius.
+5. For any untested changes, suggest specific test cases.
+
+### Output Format
+
+Provide findings grouped by risk level (high/medium/low) with:
+- What changed and why it matters
+- Test coverage status
+- Suggested improvements
+- Overall merge recommendation
+
+## Token Efficiency Rules
+- ALWAYS start with `get_minimal_context(task="<your task>")` before any other graph tool.
+- Use `detail_level="minimal"` on all calls. Only escalate to "standard" when minimal is insufficient.
+- Target: complete any review/debug/refactor task in ≤5 tool calls and ≤800 total output tokens.