How do I install the Tool Inventory Init skill?

Run npx skillmds@latest add richfrem/tool-inventory-init-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 Tool Inventory Init 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 Tool Inventory Init?

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 Tool Inventory Init free to use?

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

Who published Tool Inventory Init?

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

Tool Inventory Init by richfrem — Agent Skill

Name: Tool Inventory Init
Author: richfrem

Tool Inventory Init

Interactive Tool Inventory bootstrap. Use this when initializing a new project repo to configure the semantic tracking of Python/JS tools. It creates a dedicated RLM profile specifically for tools and performs the first intelligent distillation pass.

richfrem 980f051 3 files · 7.8 KB Updated Sep 17, 2026

File contents

Tool Inventory Init: The Librarian's Setup 🛠️

Initialize the semantic Tool Inventory for a new project. This is the first-run workflow for tracking executable scripts.

Architecture Note: This skill delegates the actual data storage and generation to the rlm-factory plugin, but it strongly enforces a pre-configured schema specifically for plugins/ and plugins/ scripts.

When to Use

Setting up Agent Skills inside a new root project repository.
Rebuilding the tool inventory ledger from scratch after severe corruption.
Moving from legacy JSON-only tracking to modern RLM tracking.

Interactive Setup Protocol

Step 1: Execute Initialization Script

Run the automated bootstrapping script. This script will ensure .agent/learning/rlm_profiles.json exists and will inject a tools profile if it doesn't.

python3 plugins/skills/tool-inventory-init/scripts/tool_inventory_init.py

Step 2: Serial Agent Distillation

The script above creates the target manifest, but YOU (the Agent) will execute the initial distillation pass if Ollama is unavailable, or you can delegate to batch mode if the project is massive.

Check what needs to be cached using the auditor:

python3 plugins/../rlm-factory/skills/rlm-curator/scripts/inventory.py --profile tools

If there are uncached tools:

Option A (Agent Distillation) - Recommended for < 20 tools: For each file identified as missing:

Read the tool script.
Summarize its purpose, layer, and CLI usage.
Write the summary using python plugins/rlm-factory/skills/rlm-curator/scripts/inject_summary.py --profile tools --file "..." --summary "..."

Option B (Batch Distillation) - Recommended for > 20 tools:

python3 plugins/../rlm-factory/skills/rlm-curator/scripts/distiller.py --type tool

Step 3: Verify

Run the audit again to confirm 100% coverage:

python3 plugins/../rlm-factory/skills/rlm-curator/scripts/inventory.py --profile tools

After Init

The semantic registry is now active. You no longer need to run this command.
Use manage_tool_inventory.py (inside the tool-inventory skill) to register single new scripts organically during development.

---name: tool-inventory-init-2description: Interactive Tool Inventory bootstrap. Use this when initializing a new project repo to configure the semantic tracking of Python/JS tools. It creates a dedicated RLM profile specifically for tools and performs the first intelligent distillation pass.---# Tool Inventory Init: The Librarian's Setup 🛠️Initialize the semantic Tool Inventory for a new project. This is the **first-run** workflow for tracking executable scripts. > **Architecture Note**: This skill delegates the actual data storage and generation to the `rlm-factory` plugin, but it strongly enforces a pre-configured schema specifically for `plugins/` and `plugins/` scripts.## When to Use- Setting up Agent Skills inside a new root project repository.- Rebuilding the tool inventory ledger from scratch after severe corruption.- Moving from legacy JSON-only tracking to modern RLM tracking.## Interactive Setup Protocol### Step 1: Execute Initialization Script Run the automated bootstrapping script. This script will ensure `.agent/learning/rlm_profiles.json` exists and will inject a `tools` profile if it doesn't. ```bashpython3 plugins/skills/tool-inventory-init/scripts/tool_inventory_init.py```### Step 2: Serial Agent DistillationThe script above creates the target manifest, but **YOU** (the Agent) will execute the initial distillation pass if Ollama is unavailable, or you can delegate to batch mode if the project is massive.Check what needs to be cached using the auditor:```bashpython3 plugins/../rlm-factory/skills/rlm-curator/scripts/inventory.py --profile tools```*If there are uncached tools:***Option A (Agent Distillation) - Recommended for < 20 tools:**For each file identified as missing:1. Read the tool script.2. Summarize its purpose, layer, and CLI usage.3. Write the summary using `python plugins/rlm-factory/skills/rlm-curator/scripts/inject_summary.py --profile tools --file "..." --summary "..."`**Option B (Batch Distillation) - Recommended for > 20 tools:**```bashpython3 plugins/../rlm-factory/skills/rlm-curator/scripts/distiller.py --type tool```### Step 3: VerifyRun the audit again to confirm 100% coverage:```bashpython3 plugins/../rlm-factory/skills/rlm-curator/scripts/inventory.py --profile tools```## After Init- The semantic registry is now active. You no longer need to run this command.- Use `manage_tool_inventory.py` (inside the `tool-inventory` skill) to register single new scripts organically during development.

Frequently asked questions