rlm-curator — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited rlm-curator (Agent Skill) and scored it 87/100 (green). The audit ran 55 deterministic rules across Security, Supply Chain, Maintenance, Transparency, and Community; it found 0 high-severity and 3 lower-severity findings. The full rule-by-rule trace and per-finding evidence are below. Free, methodology-open.
Findings & checks · 3 flagged
The text {match} tells the agent to skip the normal "ask the user first" gate. Used adversarially it removes the human-in-the-loop check before destructive or sensitive actions, turning a normally-gated agent into a fire-and-forget executor.
Every scanned point with the score it earned and what moved between them.
First recorded scan — no prior version to compare against.
The primary manifest — the file an agent reads to learn what this artifact does.
This skill requires Python 3.8+ and standard library only. No external packages needed.
To install this skill's dependencies:
pip-compile ./requirements.in
pip install -r ./requirements.txtSee ./requirements.txt for the dependency lockfile (currently empty — standard library only).
You are the Knowledge Curator. Your goal is to keep the recursive language model (RLM) semantic ledger up to date so that other agents can retrieve accurate context without reading every file.
| Script | Role |
|---|---|
swarm_run.py | The Writer (Swarm) — automated batch summarization |
inject_summary.py | The Writer (Single) -- direct agent-generated injection |
inventory.py | The Auditor -- coverage reporting |
cleanup_cache.py | The Janitor -- stale entry removal |
rlm_config.py | Shared Config -- manifest & profile mgmt |
Searching the cache? Use therlm-searchskill and itsquery_cache.pyscript.
The RLM Cache is an optimized architecture producing isolated Markdown files per component.
NEVER manually create the .agent/learning/rlm_summary_cache/*.md files using raw bash or tool blocks. Doing so could result in skipped indexing or lost metadata fields.
ALWAYS use inject_summary.py or swarm_run.py to write to the cache directories. These scripts handle the atomic file writing and schema consistency perfectly.
python ./scripts/inventory.py --type legacyCheck: Is coverage < 100%? Are there missing files?
Use the `rlm-search` skill for all cache queries:
python ./scripts/query_cache.py --profile plugins "search_term"
python ./scripts/query_cache.py --profile tools --list#### Option B: Zero-Cost Swarm (Preferred for bulk > 10 files) Use the Copilot swarm (free, gpt-5-mini) or Gemini swarm (free).
Delegate to the agent-loops:agent-swarm skill, providing:
copilot (free default) or gemini (higher throughput)inventory.py --missing2 for copilot (rate-limit safe), 5 for gemini#### Option C: Manual Agent Injection (< 5 files)
python ./scripts/inject_summary.py \
--profile project \
--file path/to/file.md \
--summary "Your dense summary here..."python ./scripts/cleanup_cache.py --profile project --applyEvery summary injected should answer "Why does this file exist?"
~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.