Nm Cartograph Code Communities

Detect architectural clusters in the codebase using community detection on the code knowledge graph. Shows module boundaries, cohesion, and coupling warnings

Security Scan

The skill's requests and runtime instructions are consistent with its stated purpose (detecting code communities); it does not ask for unrelated credentials or installs and uses reasonable fallbacks, though it will execute external plugin code if you choose to run the gauntlet path.

Purpose & Capability

Name/description match the instructions: the skill runs a community-detection action via a graph-query tool when available and otherwise analyzes directory structure and imports. The declared requirements (none) are proportional to an instruction-only skill that leverages other local tooling.

Instruction Scope

Instructions are focused on code-graph community detection and provide a clear fallback that scans repo files and imports. One important note: the preferred path runs an external script found at ~/.claude/plugins/.../gauntlet/graph_query.py (python3 "$GRAPH_QUERY" --action communities). Invoking that script will execute code from the gauntlet plugin (not provided by this skill) so you should only run it if you trust that plugin. The fallback commands (find, rg/grep, sed, xargs) will traverse and read repository files, which is expected but may surface sensitive files if present.

Install Mechanism

There is no install spec and no downloads. This is instruction-only, so nothing gets written or installed by the skill itself.

Credentials

The skill declares no environment variables, credentials, or config paths. All referenced paths are local discovery of an optional plugin and repository file scanning, which are proportionate to its purpose.

Persistence & Privilege

always is false and the skill is user-invocable; it does not request persistent presence or modify agent/system settings. Autonomous invocation is allowed by platform default but not elevated by this skill.

Assessment

This skill is internally coherent and does what it says: detect communities using a graph tool or, if absent, by scanning directories and imports. Before running it, decide whether you trust the local 'gauntlet' plugin it may invoke — that will execute code on your machine. If you prefer safety, run the fallback file-scanning commands manually in a controlled environment or review the gauntlet plugin's graph_query.py source first. Also be aware the fallback will read repository files (which could include sensitive data) when computing coupling/cohesion.

Night Market Skill — ported from claude-night-market/cartograph. For the full experience with agents, hooks, and commands, install the Claude Code plugin.

Code Community Detection

Identify architectural clusters and module boundaries in the codebase.

Prerequisites

This skill requires the gauntlet plugin for graph data. Discover it:

GRAPH_QUERY=$(find ~/.claude/plugins -name "graph_query.py" -path "*/gauntlet/*" 2>/dev/null | head -1)

If gauntlet is not installed: Fall back to directory structure analysis. Group files by directory and use import statements to identify module boundaries. Generate a Mermaid diagram from directory-level relationships.

If installed but no graph.db: Tell the user to run /gauntlet-graph build.

Steps

1. Run community detection (requires gauntlet):

   python3 "$GRAPH_QUERY" --action communities
   

   Fallback (no gauntlet): Analyze directory structure and cross-directory imports:

   # Directory-level grouping
   find . -name "*.py" -not -path "*/node_modules/*" | \
       sed 's|/[^/]*$||' | sort | uniq -c | sort -rn
   
   # Cross-directory imports (rg preferred, grep fallback)
   if command -v rg &>/dev/null; then
     rg "^from |^import " --type py -l . | \
       xargs -I{} rg "^from \w+ import|^import \w+" {} --no-filename
   else
     grep -rh "^from \|^import " --include="*.py" .
   fi | sort | uniq -c | sort -rn | head -20
   

   Group by top-level directories and count cross-directory imports to estimate coupling.

2. Display clusters:

   Community         | Nodes | Cohesion | Description
   auth              |    12 |    0.85  | Authentication module
   db                |     8 |    0.92  | Database access layer
   api/handlers      |    15 |    0.71  | API request handlers
   utils             |     6 |    0.45  | Shared utilities
   

3. Show coupling warnings: If communities have

   10 cross-boundary edges, highlight them:

   WARNING: High coupling between 'auth' and 'api/handlers'
   (23 cross-community edges, severity: high)
   

4. Generate Mermaid diagram:

   flowchart TB
     subgraph auth[Auth Module - cohesion 0.85]
       verify_token
       check_permissions
     end
     subgraph db[DB Layer - cohesion 0.92]
       execute_query
       connection_pool
     end
     auth -->|"23 edges"| api
     db -->|"5 edges"| api
   

5. Suggest improvements:

   • Low cohesion (<0.5): "Consider splitting this module into more focused components"
   • High coupling (>20 edges): "Consider introducing an interface to reduce direct dependencies"

Algorithm

Uses the Leiden algorithm (when igraph is available) with edge-type-specific weights. Falls back to file-based grouping otherwise.

Edge Type	Weight
CALLS	1.0
INHERITS	0.8
IMPLEMENTS	0.7
IMPORTS_FROM	0.5
TESTED_BY	0.4
CONTAINS	0.3