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-searchWrote 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-search)<a href="https://agentmods.dev/skills/richfrem/agent-plugins-skills/rlm-search"><img src="https://agentmods.dev/badge/skills/richfrem/agent-plugins-skills/rlm-search.svg" alt="Measured on agentmods" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00068 | $0.01498 |
| Opus 5 | $0.00034 | $0.00749 |
| Sonnet 5 | $0.00014 | $0.00300 |
| Haiku 4.5 | $0.00007 | $0.00150 |
Grade A, and why
rlm-search 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 4d 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 — 160 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 Navigator 🔍
You are the Knowledge Navigator. Your job is to find things efficiently. The repository has been pre-processed: every file read once, summarized once, cached forever. Use that prework. Never start cold.
The 3-Phase Search Protocol
Always start at Phase 1. Only escalate if the current phase is insufficient. Never skip to grep unless Phases 1 and 2 have failed.
Phase 1: RLM Summary Scan -- 1ms, O(1) -- "Table of Contents"
Phase 2: Vector DB Semantic -- 1-5s, O(log N) -- "Index at the back of the book"
Phase 3: Grep / Exact Search -- Seconds, O(N) -- "Ctrl+F"
Phase 1 -- RLM Summary Scan (Table of Contents)
When to use: Orientation, understanding what a file does, planning, high-level questions.
The concept: The RLM pre-reads every file ONCE, generates a dense 1-sentence summary, and caches it forever as a native Markdown file. Searching those summaries costs nothing. This is amortized prework -- pay the reading cost once, benefit many times.
Searching the Ledger
Because the summaries are now pure Markdown files, you can search them instantly using your native grep_search tool across the cache directories defined in rlm_profiles.json (typically .agent/learning/rlm_summary_cache/ or rlm_tool_cache/).
Common defaults:
| Profile | Cache Directory | Use When |
|---|---|---|
project |
.agent/learning/rlm_summary_cache/ |
Topic is a concept, decision, or process |
tools |
.agent/learning/rlm_tool_cache/ |
Topic is a tool, command, or implementation |
When topic is ambiguous: search all profile directories. Each is O(1) -- near-zero cost.
What ships with it
48 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 291 B
- assets/diagrams/rlm_late_binding_flow.mmd 53 B
- assets/diagrams/rlm_tool_enrichment_flow.mmd 56 B
- assets/diagrams/rlm-factory-architecture.mmd 56 B
- assets/diagrams/rlm-factory-dual-path.mmd 53 B
- assets/diagrams/search_process.mmd 46 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 1.2 KB
- evals/results.tsv 172 B
- references/acceptance-criteria.md 42 B
- references/BLUEPRINT.md 32 B
- references/cheapest_models.json 40 B
- references/cheapest_models.md 38 B
- references/diagrams/distillation_process.mmd 56 B
- references/diagrams/logic.mmd 41 B
- references/diagrams/rlm_late_binding_flow.mmd 57 B
- references/diagrams/rlm_mechanism_workflow.mmd 58 B
- references/diagrams/rlm_mechanism_workflow.png 58 B
- references/diagrams/rlm_tool_enrichment_flow.mmd 60 B
- references/diagrams/rlm-factory-architecture.mmd 60 B
- references/diagrams/rlm-factory-architecture.png 60 B
- references/diagrams/rlm-factory-dual-path.mmd 57 B
- references/diagrams/rlm-factory-dual-path.png 57 B
- references/diagrams/rlm-factory-workflow.mmd 56 B
- references/diagrams/search_process.mmd 50 B
- references/diagrams/unpacking.mmd 45 B
- references/diagrams/workflow.mmd 44 B
- references/examples/rlm_profiles.json 49 B
- references/examples/rlm_summary_cache_manifest.json 63 B
- references/examples/rlm_tools_manifest.json 55 B
- references/gap_analysis_rlm_v1.md 42 B
- references/prompt.md 29 B
- references/research-summary.md 39 B
- references/research/2512.24601v1.pdf 48 B
- references/research/summary.md 42 B
- references/RLM_ARCHITECTURE.md 39 B
- requirements.txt 22 B
- scripts/cleanup_cache.py 33 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.
- 4d ago First seen · 160 lines · 68 tokens per session scan A f49f7901e076
rlm-search is a skill published in the GitHub repository richfrem/agent-plugins-skills (6 stars, last pushed today), licensed MIT. It adds 68 tokens to every session and 1,498 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.