agentleFS
Sign inStart free
metagit-aimetagit-ai/metagit-cli/skills/metagit-gitnexus/SKILL.md

metagit-gitnexus

Skill4 starsChanged 12 days agoMITView on GitHub

Run gitnexus analysis for a target workspace and selected project repositories before graph-dependent tasks. Use when index staleness is detected or cross-repo graph results are needed.

The file

We split this skill into the rules it gives an agent

4 rules. About 0 are common, 3 are distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈3

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 1

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Use this skill whenever GitNexus context is stale or missing for target repositories.

    line 8
  2. Very specific:

    Run npx gitnexus analyze in each local repository path found.

    line 18
  3. Distinctive:

    After sync, use GitNexus directly:

    line 62
  4. Distinctive:

    Do not mutate repo content.

    line 80

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Running GitNexus Analysis

Use this skill whenever GitNexus context is stale or missing for target repositories.

Local Wrapper (Use First)

  • ./skills/metagit-gitnexus/scripts/analyze-targets.sh <workspace_root> [project_name]

Workflow

  1. Analyze the current repository where the command is run.
  2. Resolve target project repositories from .metagit.yml.
  3. Run npx gitnexus analyze in each local repository path found.
  4. Report per-repository success/failure and next actions.

Manual workspace graph (.metagit.yml → Cypher)

CLI flags: script -c and metagit config graph export -c .metagit.yml point at the manifest. --workspace-root is only the scan root for suggest; global metagit -c is appconfig.

Promote inferred edges first (see metagit-graph-maintain skill), then ingest:

./skills/metagit-gitnexus/scripts/ingest-workspace-graph.sh -c .metagit.yml
./skills/metagit-gitnexus/scripts/ingest-workspace-graph.sh -c .metagit.yml --gitnexus-repo my-umbrella --dry-run

Manual export + MCP:

metagit config graph export -c .metagit.yml --format tool-calls --output /tmp/graph-tool-calls.json
uv run python ./skills/metagit-gitnexus/scripts/ingest_workspace_graph.py /tmp/graph-tool-calls.json
# MCP export: metagit_export_workspace_graph_cypher

Schema DDL (MetagitEntity / MetagitLink) runs once per index; pass --gitnexus-repo when the umbrella index name differs from manifest name.

GitNexus group sync (cross-index analysis)

Align workspace.projects[] repos with a GitNexus group for group impact, group query, and contract linking:

./skills/metagit-gitnexus/scripts/sync-group.sh -c .metagit.yml
metagit gitnexus group sync -c .metagit.yml --json
metagit gitnexus group sync -c .metagit.yml --group-name my-workspace --prune

MCP: metagit_gitnexus_group_sync

Prerequisites:

  1. Each managed repo checkout exists locally and has been analyzed (gitnexus analyze).
  2. Registry entries exist in ~/.gitnexus/registry.json for those paths.
  3. Multi-repo workspace with workspace.projects[] in .metagit.yml.

Group paths use <project>/<repo>; default group name is a slug of manifest name (stored under ~/.gitnexus/groups/<name>/).

After sync, use GitNexus directly:

npx gitnexus group status <group>
npx gitnexus group query <group> "authentication flow"
npx gitnexus group impact <group> --repo <registryName> --target <symbol>

Output Contract

Return:

  • analyzed repositories
  • failures and reasons
  • whether graph queries are safe to run now

Safety

  • Skip repositories that do not exist locally.
  • Do not mutate repo content; analysis should be read-only indexing.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free