MCP server Claude CodeCodexCursor +2
Graph-powered code intelligence for Claude Code. Semantic search + knowledge graph for better AI code understanding. Runs locally from the codeseeker npm package. Needs 1 environment variable to run.
Instructions file
Claude Code instructions for jghiringhelli/codeseeker: Smart Claude Code CLI — semantic search, graph analysis, token-optimized code intelligence. Read .claude/index.md before any task. Load .claude/core.md always.
Plugin Claude Code
CodeSeeker - Intelligent code understanding with semantic search, knowledge graphs, and auto-detected coding standards.
Command
Read a file with its semantically related code context.
Command
Initialize CodeSeeker semantic search and knowledge graph for the current project.
Command
Trigger a full reindex of the project after major changes.
Command
Explore dependencies and relationships for a file or code pattern.
Command
Search the codebase using semantic understanding to find relevant code.
Command
Retrieve auto-detected coding standards and patterns from this project.
Agent Claude Code
Reviews structural changes (new modules, refactors, schema changes) for architecture conformance, naming conventions, layer violations, and missing ADRs. Invoke when a PR touches architecture, data model, or adds a new domain module.
Agent Claude Code
Reviews code changes for security issues: credential leaks, auth bypass, missing input validation, unsafe operations, and violations of operation-classification.md. Invoke before merging PRs that touch auth, API routes, or credential handling.
Agent Claude Code
Verifies the codebase is in sync with the spec (PRD.md, use-cases.md, ADRs, data-model.md). Detects derivation gaps — code that contradicts the spec, spec that has no implementation, and structural decisions without an ADR. Invoke before cutting a release or when drift is suspected.
Agent Claude Code
Generates adversarial tests for a module or feature. Does NOT write happy-path tests — that is the author's job. Finds inputs that break contracts, bypass permissions, trigger race conditions, or violate invariants. Invoke when a module has a base suite and needs adversarial hardening, before merging a sensitive…
Command Claude Code
Create a new API endpoint. $ARGUMENTS should describe the endpoint (e.g., "POST /api/users - create a user").
Command Claude Code
Test the API endpoint specified in $ARGUMENTS.
Command Claude Code
Review the code changes in this project. For each file changed.
Command Claude Code
Debug the following error. $ARGUMENTS should contain the error message or stack trace.
Command Claude Code
Refactor the file specified in $ARGUMENTS following project conventions.
Command Claude Code
Run the project's test suite and analyze the results.
Command Claude Code
Implement the behavior described in $ARGUMENTS using strict TDD. Follow this exact sequence. Do not collapse phases. Each gate requires actual test runner output.
Hook Claude Code
Runs before the agent uses a tool for run_in_terminal tool calls, executing pre-exec-safety.sh and pre-exec-health-injector.sh via bash (2 commands). From jghiringhelli/forgecraft-mcp.
Hook Claude Code
Runs after a tool call finishes for create_file, write_file, edit_file, replace_string, multi_replace and create_directory tool calls, executing post-edit-commit-reminder.sh and post-tool-session-log.sh via bash (2 commands). From jghiringhelli/forgecraft-mcp.
Hook Claude Code
Runs when the agent finishes a response, executing stop-session-summary.sh via bash. From jghiringhelli/forgecraft-mcp.
Settings file Claude Code
MCP configuration declaring 2 servers: forgecraft, context7.