Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/richfrem/agent-plugins-skillsnpx agentmods add skills/richfrem/agent-plugins-skills/rlm-curatorWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/richfrem/agent-plugins-skills/rlm-curator)<a href="https://agentmods.dev/skills/richfrem/agent-plugins-skills/rlm-curator"><img src="https://agentmods.dev/badge/skills/richfrem/agent-plugins-skills/rlm-curator.svg" alt="Measured on agentmods" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00067 | $0.00835 |
| Opus 5 | $0.00034 | $0.00417 |
| Sonnet 5 | $0.00013 | $0.00167 |
| Haiku 4.5 | $0.00007 | $0.00084 |
Grade A, and why
rlm-curator scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 5d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 97 lines — stays where its author put it; the contents beside it link to each section on GitHub.
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)
| 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 the
rlm-searchskill and itsquery_cache.pyscript.
Architectural Constraints (The "Electric Fence")
The RLM Cache is an optimized architecture producing isolated Markdown files per component.
❌ WRONG: Manual Cache Manipulation (Negative Instruction Constraint)
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.
✅ CORRECT: Curatorial Scripts
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.
📂 Execution Protocol
1. Assessment (Always First)
python ./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:
python ./scripts/query_cache.py --profile plugins "search_term"
python ./scripts/query_cache.py --profile tools --list
What ships with it
28 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- acceptance-criteria.md 285 B
- assets/diagrams/rlm_late_binding_flow.mmd 53 B
- assets/diagrams/rlm_tool_enrichment_flow.mmd 56 B
- assets/resources/distiller_manifest.json 52 B
- assets/resources/manifest-index.json 48 B
- assets/resources/prompts/rlm/rlm_summarize_general.md 71 B
- assets/resources/prompts/rlm/rlm_summarize_tool.md 68 B
- assets/resources/rlm_manifest.json 46 B
- evals/evals.json 948 B
- evals/results.tsv 301 B
- fallback-tree.md 1.4 KB
- references/acceptance-criteria.md 42 B
- references/BLUEPRINT.md 32 B
- references/cheapest_models.json 40 B
- references/cheapest_models.md 38 B
- references/gap_analysis_rlm_v1.md 42 B
- references/prompt.md 29 B
- references/research-summary.md 39 B
- references/RLM_ARCHITECTURE.md 39 B
- requirements.txt 22 B
- scripts/cleanup_cache.py 33 B runs code
- scripts/debug_rlm.py 29 B runs code
- scripts/distiller.py 29 B runs code
- scripts/inject_summary.py 34 B runs code
- scripts/inventory.py 29 B runs code
- scripts/query_cache.py 31 B runs code
- scripts/rlm_config.py 30 B runs code
- scripts/swarm_run.py 29 B runs code
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 5d ago First seen · 97 lines · 67 tokens per session scan A 3625d1b2108a
rlm-curator is a skill published in the GitHub repository richfrem/agent-plugins-skills (6 stars, last pushed today), licensed MIT. It adds 67 tokens to every session and 835 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
Other skills, from other repositories
notebook
Project notes system to prevent AI context loss and reasoning loops. Init notes, save mid-flow, recover context, migrate messy notes, resolve lessons. Subcommands: /notebook, /notebook save, /notebook recover, /notebook migrate.
dotagents-standard
Set up, author, and navigate the dotagents standard — a slim AGENTS.md "router" at the repository root plus a hidden .agents/ directory (rules, context, memory, personas, skills, specs, logs, tasks) that splits agent context into small per-topic files loaded on demand (progressive disclosure). Use this WHENEVER the…
memento
Context handoff for fresh sessions. Saves unsaved session knowledge to notebook, then produces a short orientation block to paste into a new chat. Use when user says '/memento', 'hand off context', 'prepare for fresh chat', 'save and brief', or before clearing context. NOT for: recovering context (use /notebook…
sync-rules
Iteration closeout knowledge routing for AI-assisted development. Use when the user asks to summarize changed function points into a knowledge base, update project docs or generated superpower docs after code changes, sync rules, distill lessons from an iteration, record durable decisions, or remember user…
poly-wiki
A knowledge-base compiler for turning scattered notes and source material into an organised, reusable wiki. It also supports searching, importing, extracting general lessons, and checking the wiki for problems.
poly-wiki
Multi-platform knowledge base compiler. Compile raw materials into structured knowledge, maintain a reusable knowledge network. Triggers: wiki compile extract ingest lint query knowledge base notes Zettelkasten.