mcpField
R
reindex

reindex

github.com/terrylicaDevelopment280 installsUpdated 2d ago
Repository

About reindex

GitNexus Reindex is a CLI-oriented skill for rebuilding or updating the GitNexus knowledge graph for a repository and checking the resulting status and statistics. It is intended for developers refreshing an index after substantial changes or when it is reported as stale.

Key features

  1. 01Check index status against HEAD
  2. 02Run incremental analysis
  3. 03Force a full index rebuild
  4. 04Verify updated index status
  5. 05Report index statistics

Use cases

  1. 01Refresh after a large refactor
  2. 02Update after merging a large pull request
  3. 03Resolve a reported stale index

MCP support

The skill explicitly states that no MCP server exists and uses the GitNexus CLI rather than `gitnexus://` MCP resources.

Install

Copy the command and run it in a terminal.

$npx skills add https://github.com/terrylica/cc-skills --skill reindex

After installing, type/reindexin Claude Code to confirm it loaded.

Details

From the project README

GitNexus Reindex

CLI ONLY — no MCP server exists. Never use readMcpResource with gitnexus:// URIs.

Re-index the current repository's GitNexus knowledge graph and verify the updated stats.

Self-Evolving Skill: This skill improves through use. If instructions are wrong, parameters drifted, or a workaround was needed — fix this file immediately, don't defer. Only update for real, reproducible issues.

When to Use

  • After significant refactors (5+ files changed)
  • When staleness hook reports index is behind
  • After merging a large PR
  • "Refresh the knowledge graph"

Workflow

Step 0: Pre-flight — Ensure CLI Is Callable

The gitnexus binary is installed via npm/mise. The mise shim may fail if node isn't active in the current project. Run this pre-flight before any gitnexus command:

# Test if gitnexus is actually callable (not just a broken shim)
gitnexus --version 2>/dev/null || mise use [email protected]

All commands below run from the repo root. If multiple repos are indexed in the workspace, add --repo <repo-name> to specify the target. Otherwise --repo is optional.

Step 1: Check Current Status
gitnexus status

If already current (lastCommit matches HEAD), report "Index is up to date" and stop.

Step 2: Run Indexer
gitnexus analyze

Use --force if the index appears corrupted or if a normal analyze doesn't pick up changes:

gitnexus analyze --force

This may take 30–120 seconds depending on codebase size.

Step 3: Verify New Index
gitnexus status
Step 4: Report Stats

Present the updated stats:

## GitNexus Reindex Complete

| Metric      | Before | After |
| ----------- | ------ | ----- |
| Nodes       | ...    | ...   |
| Edges       | ...    | ...   |
| Communities | ...    | ...   |
| Flows       | ...    | ...   |
| Last Commit | ...    | ...   |

Index is now current with HEAD.

Notes

  • The analyze command runs locally — no network calls
  • KuzuDB database is stored in .gitnexus/ at the repo root
  • Large codebases (10k+ files) may take 2+ minutes
  • The --force flag rebuilds from scratch; without it, incremental analysis is used

Post-Execution Reflection

After this skill completes, reflect before closing the task:

  1. Locate yourself. — Find this SKILL.md's canonical path before editing.
  2. What failed? — Fix the instruction that caused it.
  3. What worked better than expected? — Promote to recommended practice.
  4. What drifted? — Fix any script, reference, or dependency that no longer matches reality.
  5. Log it. — Evolution-log entry with trigger, fix, and evidence.

Do NOT defer. The next invocation inherits whatever you leave behind.

Comments

Markdown supported