How do I install the Rlm Curator skill?

Run npx skillmds@latest add richfrem/rlm-curator-2 in your terminal (requires Node.js), paste this page's agent-chat prompt into Claude, Cursor, or any MCP-connected agent, or download the SKILL.md file and copy it into your agent's skills directory.

Is Rlm Curator safe to use?

This skill has not completed SkillMD's automated safety review yet. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.

Which AI agents work with Rlm Curator?

This skill is tagged as working with Claude Code, Claude.ai, OpenAI Codex. SKILL.md is an open format, so most agents that read a skills directory can load it too.

Is Rlm Curator free to use?

Yes. Installing skills from SkillMD is free, and the skill stays under its author's original license.

Who published Rlm Curator?

richfrem (@richfrem) published this skill. Their other Agent Skills are listed on their SkillMD profile.

Rlm Curator by richfrem — Agent Skill

Name: Rlm Curator
Author: richfrem

Rlm Curator

Knowledge Curator agent skill for the RLM Factory. Auto-invoked when tasks involve distilling code summaries, querying the semantic ledger, auditing cache coverage, or maintaining RLM hygiene. Supports both Ollama-based batch distillation and agent-powered direct summarization. V2 enforces Concurrency Safety constraints.

richfrem Updated Sep 17, 2026

File contents

Identity: The Knowledge Curator 🧠

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.

Tools (Plugin Scripts)

Script	Role	Ollama?
`distiller.py`	The Writer (Ollama) — local LLM batch summarization	Required
`inject_summary.py`	The Writer (Agent/Swarm) -- direct agent-generated injection, no Ollama	None
`inventory.py`	The Auditor -- coverage reporting	None
`cleanup_cache.py`	The Janitor -- stale entry removal	None
`rlm_config.py`	Shared Config -- manifest & profile mgmt	None

Searching the cache? Use the rlm-search skill and its query_cache.py script.

Architectural Constraints (The "Electric Fence")

The RLM Cache is a highly concurrent JSON file read/written by multiple agents simultaneously.

❌ WRONG: Manual Cache Manipulation (Negative Instruction Constraint)

NEVER manually edit the .agent/learning/rlm_summary_cache.json or .agent/learning/rlm_tool_cache.json using raw bash commands, sed, awk, or native LLM tool block writes. Doing so bypasses the Python fcntl.flock concurrency lock. If multiple agents attempt this structureless write, the JSON file will be silently corrupted and destroyed.

✅ CORRECT: Curatorial Scripts

ALWAYS use inject_summary.py or distiller.py to write to the cache. These scripts handle the fcntl.flock locks inherently, guaranteeing data integrity.

Delegated Constraint Verification (L5 Pattern)

When executing distiller.py:

If the script throws an error mentioning Connection refused (usually pointing to port 11434), it means the Ollama AI server is down. Do not attempt to retry indefinitely or modify python. You MUST IMMEDIATELY refer to references/fallback-tree.md.

📂 Execution Protocol

1. Assessment (Always First)

python3 ./scripts/inventory.py --type legacy

Check: Is coverage < 100%? Are there missing files?

2. Retrieval (Read -- Fast)

Use the rlm-search skill for all cache queries:

python3 ./scripts/query_cache.py --profile plugins "search_term"
python3 ./scripts/query_cache.py --profile tools --list

3. Distillation (Write)

Option A: 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:

Engine: copilot (free default) or gemini (higher throughput)
Job: ../../resources/jobs/rlm_chronicle.job.md
Files: gap list from inventory.py --missing
Workers: 2 for copilot (rate-limit safe), 5 for gemini

Option B: Ollama Batch (requires Ollama running locally)

python3 ./scripts/distiller.py

Option C: Manual Agent Injection (< 5 files)

python3 ./scripts/inject_summary.py \
  --profile project \
  --file path/to/file.md \
  --summary "Your dense summary here..."

4. Cleanup (Curate)

python3 ./scripts/cleanup_cache.py --type legacy --apply

Quality Guidelines

Every summary injected should answer "Why does this file exist?"

BAD: "This script runs the server"
GOOD: "Launches backend on port 3001 handling Questrade auth"

---name: rlm-curator-2description: Knowledge Curator agent skill for the RLM Factory. Auto-invoked when tasks involve distilling code summaries, querying the semantic ledger, auditing cache coverage, or maintaining RLM hygiene. Supports both Ollama-based batch distillation and agent-powered direct summarization. V2 enforces Concurrency Safety constraints.---# Identity: The Knowledge Curator 🧠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.## Tools (Plugin Scripts)| Script | Role | Ollama? ||:---|:---|:---|| `distiller.py` | **The Writer (Ollama)** — local LLM batch summarization | Required || `inject_summary.py` | **The Writer (Agent/Swarm)** -- direct agent-generated injection, no Ollama | None || `inventory.py` | **The Auditor** -- coverage reporting | None || `cleanup_cache.py` | **The Janitor** -- stale entry removal | None || `rlm_config.py` | **Shared Config** -- manifest & profile mgmt | None |> **Searching the cache?** Use the [`rlm-search` skill](../rlm-search/SKILL.md) and its `query_cache.py` script.## Architectural Constraints (The "Electric Fence")The RLM Cache is a highly concurrent JSON file read/written by multiple agents simultaneously.### ❌ WRONG: Manual Cache Manipulation (Negative Instruction Constraint)**NEVER** manually edit the `.agent/learning/rlm_summary_cache.json` or `.agent/learning/rlm_tool_cache.json` using raw bash commands, `sed`, `awk`, or native LLM tool block writes. Doing so bypasses the Python `fcntl.flock` concurrency lock. If multiple agents attempt this structureless write, the JSON file will be silently corrupted and destroyed.### ✅ CORRECT: Curatorial Scripts**ALWAYS** use `inject_summary.py` or `distiller.py` to write to the cache. These scripts handle the `fcntl.flock` locks inherently, guaranteeing data integrity.## Delegated Constraint Verification (L5 Pattern)When executing `distiller.py`:1. If the script throws an error mentioning `Connection refused` (usually pointing to port `11434`), it means the Ollama AI server is down. Do not attempt to retry indefinitely or modify python. You **MUST IMMEDIATELY** refer to `references/fallback-tree.md`.---## 📂 Execution Protocol### 1. Assessment (Always First)```bashpython3 ./scripts/inventory.py --type legacy```Check: Is coverage < 100%? Are there missing files?### 2. Retrieval (Read -- Fast)Use the **`rlm-search`** skill for all cache queries:```bashpython3 ./scripts/query_cache.py --profile plugins "search_term"python3 ./scripts/query_cache.py --profile tools --list```### 3. Distillation (Write)#### Option A: 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:- Engine: `copilot` (free default) or `gemini` (higher throughput)- Job: `../../resources/jobs/rlm_chronicle.job.md`- Files: gap list from `inventory.py --missing`- Workers: `2` for copilot (rate-limit safe), `5` for gemini#### Option B: Ollama Batch (requires Ollama running locally)```bashpython3 ./scripts/distiller.py```#### Option C: Manual Agent Injection (< 5 files)```bashpython3 ./scripts/inject_summary.py \ --profile project \ --file path/to/file.md \ --summary "Your dense summary here..."```### 4. Cleanup (Curate)```bashpython3 ./scripts/cleanup_cache.py --type legacy --apply```## Quality GuidelinesEvery summary injected should answer **"Why does this file exist?"**- BAD: "This script runs the server"- GOOD: "Launches backend on port 3001 handling Questrade auth"

Frequently asked questions