richfrem/vector-db-cleanup
plugins/agent-memory/skills/vector-db-cleanup/SKILL.md
Removes stale and orphaned chunks from the ChromaDB vector store for files that have been deleted or renamed. Use after files are removed or moved to keep the vector index in sync with the filesystem. <example> user: "Clean up the vector store after I deleted some files" assistant: "I'll use vector-db-cleanup to remove orphaned chunks." </example> <example> user: "The vector database has chunks for files that no longer exist" assistant: "I'll run vector-db-cleanup to prune them." </example>
$ install --global
skillsauthnpx skillsauth add richfrem/agent-plugins-skills vector-db-cleanupInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
Security Scan Results
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
3
Scanners Passed
9
Scanners in report
Clean
TrivyContainer and dependency vulnerability scanner
95%
Clean
SemgrepStatic code analysis for vulnerabilities
95%
Clean
mcp-scan (Snyk)Model Context Protocol security validation
95%
Skipped
Snyk (dep)Open source security scanning
50%
Skipped
Socket.devSupply chain security analysis
50%
Skipped
VirusTotalMulti-engine malware detection
50%
Skipped
CrowdStrikeAdvanced threat intelligence
50%
Skipped
OSV-ScannerOpen Source Vulnerability database check
50%
Skipped
OWASP Dep-Check
50%
Last scanned: Jun 2, 2026, 4:53 AM247.9s11 files scanned
SKILL.md
- name:
- vector-db-cleanup
- plugin:
- vector-db
- description:
- |
- user:
- The vector database has chunks for files that no longer exist
- assistant:
- I'll run vector-db-cleanup to prune them.
- allowed-tools:
- Bash, Read, Write
Dependencies
This skill requires the chromadb and langchain packages defined in the plugin root.
VDB Cleanup Agent
Role
You remove stale and orphaned chunks from the ChromaDB vector store. A chunk is stale when its source file no longer exists on disk. Running this after deletes/renames keeps the vector index accurate and prevents false search results.
This is a write (delete) operation.
When to Run
- After deleting or renaming files that were previously ingested.
- After a major refactor that moved directories.
- When
query.pyreturns results pointing to non-existent files. - Periodically as housekeeping to maintain index health.
Execution Mode
This skill defaults to In-Process mode for zero-latency direct disk access. No background server is required.
Execution Protocol
1. Identify Search Profile
Verify available profiles in .agent/learning/vector_profiles.json. The default profile is usually wiki.
2. Run Cleanup
Note: The --profile flag is mandatory to ensure the correct collection and disk paths are loaded.
python ./scripts/cleanup.py --profile wiki
3. Verify Store Integrity (Optional)
Run the consistency check to verify that remaining facts are still supported.
python ./scripts/vector_consistency_check.py --profile wiki --topic .agent/learning/
Rules
- Profile Sovereignty: Always pass
--profileto ensure the correct semantic space is pruned. - API Integrity: NEVER attempt to delete chunks from the database SQLite files directly. Always use
cleanup.py. - Transparency: State which profile was cleaned and how many chunks were removed.
Related Skills
richfrem/vector-db-ingest
tools
VerifiedTrustedCommunity
Ingests repository files into the ChromaDB vector store. Builds or updates the vector index from a manifest or directory scan using ingest.py. Use when new files need to be indexed or the vector store is out of date. <example> user: "Index these new plugin files into the vector database" assistant: "I'll use vector-db-ingest to add them to the vector store." </example> <example> user: "The vector store is missing recent files -- update it" assistant: "I'll use vector-db-ingest to re-index the changes." </example>
3SKILL.mdUpdated Jun 2, 2026
richfrem/vector-db-audit
testing
VerifiedTrustedCommunity
Audit Vector DB coverage -- compares the live filesystem manifest against the ChromaDB index to identify coverage gaps.
3SKILL.mdUpdated Jun 2, 2026
richfrem/rlm-search
development
VerifiedTrustedCommunity
3-Phase Knowledge Search strategy for the RLM Factory ecosystem. Auto-invoked when tasks involve finding code, documentation, or architecture context in the repository. Enforces the optimal search order: RLM Summary Scan (O(1)) -> Vector DB Semantic Search -> Grep/Exact Match. Never skip phases.
3SKILL.mdUpdated Jun 2, 2026
richfrem/rlm-init
tools
VerifiedTrustedCommunity
Interactive RLM cache initialization. Use when: setting up a new project's semantic cache for the first time, or adding a new cache profile. Walks the user through folder selection, extension config, manifest creation, and first distillation pass.
3SKILL.mdUpdated Jun 2, 2026