rlm-curator（RLM 策展人）

Dependencies

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.txt

See ./requirements.txt for the dependency lockfile (currently empty — standard library only).

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)

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:

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 ./fallback-tree.md.

📂 Execution Protocol

1. Assessment (Always First)

python3 .agents/skills/rlm-curator/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 .agents/skills/rlm-curator/scripts/query_cache.py --profile plugins "search_term"
python3 .agents/skills/rlm-curator/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: provide a job file describing the summarization task
• 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 .agents/skills/rlm-curator/scripts/distiller.py

Option C: Manual Agent Injection (< 5 files)

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

4. Cleanup (Curate)

python3 .agents/skills/rlm-curator/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"