kg-setup

A command that configures where a Knowledge Graph—a connected collection of notes and relationships—is stored and creates its configuration file.

In plain words
What is it for?
It checks known configuration locations and common folders, verifies a graph contains the expected files, asks which path to use when needed, and saves the selected path.
Why use it?
It helps the tool find an existing knowledge graph or clearly reports when one is missing or misconfigured.

Command

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add commands/ethics03/kgskill/kg-setup
Clone the repo
git clone --depth 1 https://github.com/Ethics03/kgskill
Per session 8 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 320 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00008 $0.00320
Opus 5 $0.00004 $0.00160
Sonnet 5 $0.00002 $0.00064
Haiku 4.5 $0.00001 $0.00032

Measured 2d ago against content hash f9add432aa19, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

kg-setup 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 2d 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.

commands/kg-setup.md · 44 lines

What it actually says

Configure the Knowledge Graph path. If a path argument was provided, use it directly. Otherwise check for existing config and report it, or search for a KG and prompt the user.

Steps

1. Check for existing config

Check in order:

  1. $MYKG_PATH environment variable
  2. ~/.config/mykg/config file
  3. ~/.mykgrc file

If found, verify the path exists on disk:

  • If it exists and contains index.md: report ✓ KG found at <path> and stop.
  • If the path doesn't exist: tell the user the configured path is missing and suggest /kg-init to create it.

2. If no config found, search common locations

Check each of these for index.md + log.md:

  • ~/MyKG
  • ~/Dev/Obsidian/MyKG
  • ~/Documents/MyKG
  • ~/Notes/MyKG
  • ~/vault/MyKG

If any are found, show them to the user and ask which to use.

3. If nothing found, ask the user

Ask: "No KG found. Enter a path to configure, or I can create one with /kg-init."

4. Save config

Once a path is confirmed:

mkdir -p ~/.config/mykg
echo "<path>" > ~/.config/mykg/config

Report ✓ Config saved. KG path: <path>.

Changes

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.

  1. 2d ago First seen · 44 lines · 8 tokens per session scan A f9add432aa19

Subscribe to this mod's changes

kg-setup is a command published in the GitHub repository Ethics03/kgskill (3 stars, last pushed 4mo ago), licensed MIT. It adds 8 tokens to every session and 320 once invoked, about $0.0000 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 2026-08-31.