Adr Index

Rebuilds your entire ADR index and relationship graph in one shot by calling a Node script instead of making hundreds of individual MCP calls. It scans for ADRs in docs folders, handles both YAML frontmatter and markdown heading formats, extracts supersedes/amends/depends-on relationships, and stores everything in the adr-patterns and adr-edges namespaces. You'd reach for this after importing ADRs from another repo or when your graph has drifted from the filesystem. The false-positive filtering is smart enough to ignore issue numbers and commit hashes that look like ADR IDs. Pair it with adr-verify to catch cycles before they become a problem.

skills.sh installs: 737
GitHub stars: 81.4K
last updated: Aug 21, 2026

View on GitHub

Install

$ npx -y skills add ruvnet/ruflo --skill adr-index --agent claude-code

Installs into .claude/skills of the current project.

Files

ADR Index

Persists every ADR under */docs/adr/ or */docs/adrs/ to the adr-patterns namespace and every relationship (supersedes / amends / related / depends-on) to adr-edges. Handles both ADR formats found in the Ruflo monorepo:

v3-style: # ADR-097: Title heading + **Status**: Proposed line
plugin-style: YAML frontmatter (id: ADR-NNNN, status: Proposed)

Implementation is in scripts/import.mjs (one Bash call) rather than dozens of per-ADR MCP tool calls — same effective behavior, materially faster, dual-format-aware, and false-positive-resistant for issue numbers.

When to use

After importing ADRs from another project
When the AgentDB graph is out of sync with the on-disk ADR files
Bootstrapping ADR tracking on an existing codebase

Steps

Run the importer:
```
node plugins/ruflo-adr/scripts/import.mjs
```
Optional env:
- IMPORT_FORMAT=json — emit JSON instead of markdown
- IMPORT_DRY_RUN=1 — parse + summarize, skip persistence
- ADR_ROOT=/path — scan a different root (default: cwd)