agentleFS
metagit-aimetagit-ai/metagit-cli/skills/metagit-graph-maintain/SKILL.md

metagit-graph-maintain

Skill4 starsChanged 12 days agoMITView on GitHub

Discover, suggest, promote, validate, and ingest cross-repo graph.relationships in .metagit.yml for GitNexus overlay and dependency maps. Use for first-time graph bootstrap or ongoing workspace graph maintenance.

The file

We split this skill into the rules it gives an agent

8 rules. About 0 are common, 3 are distinctive, and 5 are 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.

  • 5

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Use this skill to discover and keep durable cross-repo edges in .metagit.yml graph.relationships, then sync them into GitNexus.

    line 11
  2. Distinctive:

    Do not apply until the operator approves the discovery report.

    line 22
  3. Very specific:

    After sign-off, continue with the maintenance workflow below (or metagit prompt workspace -k graph-maintain).

    line 38
  4. Distinctive:

    After repos are indexed, align the workspace with a GitNexus group:

    line 105
  5. Very specific:

    Default --min-confidence medium.

    line 131
  6. Distinctive:

    Never remove or rewrite existing manual relationships

    line 132
  7. Very specific:

    Use --dry-run / dry_run: true before first apply in a workspace

    line 133
  8. Very specific:

    Do not ingest Cypher until metagit config validate passes

    line 134

≈ “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

Workspace graph maintenance

Use this skill to discover and keep durable cross-repo edges in .metagit.yml graph.relationships, then sync them into GitNexus.

When to use

PhaseTrigger
DiscoverNew umbrella workspace, empty graph.relationships, or first graph authoring pass
MaintainAfter adding repos, promoting inferred deps, or refreshing GitNexus overlay

First-time discovery (report only)

Do not apply until the operator approves the discovery report.

export METAGIT_AGENT_MODE=true
metagit prompt workspace -c .metagit.yml -k graph-discover --text-only
metagit workspace list -c .metagit.yml --json
metagit config graph suggest -c .metagit.yml --json --include-declared --min-confidence all

Deliver a Graph Discovery Report:

  • inferred edges grouped by confidence (high / medium / low)
  • gap pairs with no machine path (need operator interview)
  • proposed_manual_edges[] from interview answers
  • operations_preview JSON — not applied

After sign-off, continue with the maintenance workflow below (or metagit prompt workspace -k graph-maintain).

Maintenance workflow

CLI flags: -c on config graph suggest|export is the manifest path (trailing leaf -c is valid). --workspace-root is the checkout root used to scan inferred deps. Global metagit -c configures appconfig, not .metagit.yml.

1. Bootstrap context

export METAGIT_AGENT_MODE=true
metagit prompt workspace -c .metagit.yml -k graph-maintain --text-only
metagit workspace list -c .metagit.yml --json

2. Suggest candidates

metagit config graph suggest -c .metagit.yml --json
metagit config graph suggest -c .metagit.yml --min-confidence high --json

MCP: metagit_suggest_graph_relationships

Review candidates[] for confidence, evidence, and source_edge_type. Skip low-confidence edges unless the operator approves.

Also review stale_manual[] — active manual relationships with no supporting inferred edge under the current scan, matched on endpoints so a differing relationship type still counts as support (report-only; do not edit/remove without operator confirmation). Use --verbose when candidates are empty to confirm scan roots and ignore prune counts.

3. Preview and apply

# Save operations from suggest JSON to ops.json, then:
metagit config preview -c .metagit.yml --file ops.json

# Apply all suggested candidates (medium+ confidence by default)
metagit config graph suggest -c .metagit.yml --apply

# Apply selected ids only
metagit config graph suggest -c .metagit.yml --apply \
  --candidate-id alpha-api-to-beta-worker-depends_on

metagit config validate -c .metagit.yml

MCP: metagit_apply_graph_relationships (dry_run: true to preview, save: true to persist)

4. Export and ingest GitNexus overlay

./skills/metagit-gitnexus/scripts/ingest-workspace-graph.sh -c .metagit.yml

Or manually:

metagit config graph export -c .metagit.yml --format tool-calls --output /tmp/graph-tool-calls.json

Then run each gitnexus_cypher call (or use the ingest script).

5. Refresh per-repo indexes

./skills/metagit-gitnexus/scripts/analyze-targets.sh <workspace_root> <project>

6. Sync GitNexus group (cross-index)

After repos are indexed, align the workspace with a GitNexus group:

./skills/metagit-gitnexus/scripts/sync-group.sh -c .metagit.yml
# MCP: metagit_gitnexus_group_sync

Enables gitnexus group query / group impact across member repos.

Output contract

Return:

  • candidate count and applied count
  • validation result after apply
  • GitNexus ingest status (schema + statement count)
  • repos still stale/missing in GitNexus registry

Lifecycle

  • Promoted edges are written with status: active, provenance: promoted.
  • Deprecate retired edges by setting status: deprecated rather than deleting them.
  • stale_manual[] from suggest is report-only: confirm with the operator before editing or removing the flagged edges.

Safety

  • Default --min-confidence medium; require operator approval for --min-confidence all
  • Never remove or rewrite existing manual relationships
  • Use --dry-run / dry_run: true before first apply in a workspace
  • Do not ingest Cypher until metagit config validate passes

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.