Audit RLM cache coverage - compare manifest against filesystem
Scanned 9/2/2026
Install to Claude Code
Skills Directorynpx -y skills add richfrem/agent-plugins-skills --skill rlm-audit --agent claude-codeInstalls into .claude/skills of the current project.
Are you the author of Rlm Audit?
Add the live security badge to your README — it updates automatically with every re-scan.
[](https://www.skillsdirectory.com/skills/richfrem-rlm-audit)More formats (shields.io, HTML) on the badges page.
---
name: rlm-audit
description: Audit RLM cache coverage - compare manifest against filesystem
trigger_phrases:
- "audit rlm cache"
- "check rlm coverage"
- "rlm inventory audit"
- "show missing rlm files"
- "check rlm gap"
---
# rlm-audit
## Purpose
Systematically audit the RLM (Recursive Language Model) semantic cache to identify gaps between the project manifest and the actual summary files stored on disk.
## Capabilities
- **Coverage Analysis**: Calculates the percentage of project documentation currently summarized.
- **Gap Identification**: Detects files that are included in the manifest but missing from the cache.
- **Exporting**: Generates CSV lists of missing files for batch processing.
- **Validation**: Ensures the cache directory structure mirrors the source repository.
## Usage
Run the audit for a specific profile to see what's missing:
```bash
python scripts/audit_cache.py --profile wiki --report audit_report.txt --csv missing_files.csv
```
## Related
- **rlm-distill-agent**: Use to fill the gaps identified by this audit.
- **rlm-cleanup-agent**: Use to remove stale entries from the cache.
Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.
No comments yet. Be the first to comment!
Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...
Ultra-compressed communication mode. Cuts token usage ~75% by speaking like caveman while keeping full technical accuracy. Supports intensity levels: lite, full (default), ultra, wenyan-lite, wenyan-full, wenyan-ultra. Use when user says "caveman mode", "talk like caveman", "use caveman", "less tokens", "be brief", or invokes /caveman. Also auto-triggers when token efficiency is requested.
**Complete production-ready guide for Google Gemini embeddings API** This skill provides comprehensive coverage of the `gemini-embedding-001` model for generating text embeddings, including SDK usage, REST API patterns, batch processing, RAG integration with Cloudflare Vectorize, and advanced use cases like semantic search and document clustering. ---
Use when a repo needs CodeGraph plus ast-grep for Codex MCP setup, exploration, impact analysis, structural search, or safe refactor planning.
Interview, source-challenge, verify, save, and ADR-gate fuzzy coding requests into Codex-ready implementation specs. Use when a feature, bugfix, refactor, migration, repo-wide change, or architecture task needs user-verified requirements, source-backed decisions, durable architecture decisions, acceptance criteria, validation commands, rollout notes, saved spec/ADR files, and a Codex execution prompt. Do not use when already fully specified or when the user wants direct implementation now.
