agentmods.dev

kb-init

kb-init is a skill for Claude Code from waelmas/codeplow. It costs 140 tokens per session (8,368 once invoked), scanned A, original, MIT.

A project-documentation skill that analyzes a codebase and fills an Obsidian vault with structured notes about it. It checks existing markdown documentation against the current code and marks outdated material.

In plain words
What is it for?
Use it to create architectural notes, references, and project overviews, or to audit existing README, architecture, and changelog files.
Why use it?
It reduces the time needed to understand an unfamiliar codebase and helps prevent old documentation from misleading developers. It can start with an empty or nearly empty vault.

Skill for Claude Code

Written for Claude Code: ${CLAUDE_PLUGIN_ROOT} variable. Also seen: mentions subagents.

Runs only inside its plugin — its command needs a path that Claude Code sets for a plugin’s own hooks and for nothing else. Install the plugin, not this.

Part of the obsidian-kb plugin — 8 skills, 8 commands shipped together

not rated 8repo 6mo ago A scan 140 tokens original MIT

Good fit Use it to create architectural notes, references, and project overviews, or to audit existing README, architecture, and changelog files.

Compare 6 skills from other repositories ↓
View source ↗ waelmas/codeplow
Install

Getting it into your agent

This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.

Claude Code
/plugin marketplace add waelmas/codeplow
Claude Code
/plugin install obsidian-kb

Made for: Claude Code.

Or install obsidian-kb, the plugin that ships this one along with the rest of its 8 skills, 8 commands.

Wrote 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.

agentmods badge for kb-init

README.md
[![agentmods](https://agentmods.dev/badge/skills/waelmas/codeplow/kb-init/github.svg)](https://agentmods.dev/skills/waelmas/codeplow/kb-init)
Your own site
<a href="https://agentmods.dev/skills/waelmas/codeplow/kb-init"><img src="https://agentmods.dev/badge/skills/waelmas/codeplow/kb-init/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for kb-init

Your own site · 80×15
<a href="https://agentmods.dev/skills/waelmas/codeplow/kb-init"><img src="https://agentmods.dev/badge/skills/waelmas/codeplow/kb-init.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 140 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 8,368 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00140 $0.08368
Opus 5.5 $0.00056 $0.03347
Sonnet 5.5 $0.00028 $0.01674
Haiku 4.5 $0.00014 $0.00837

Measured 2mo ago against content hash 485beaf14a3e, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

kb-init 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 2mo 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.

obsidian-kb/skills/kb-init/SKILL.md · 699 lines

How it starts

The opening of the file, as written. The whole thing — 699 lines — stays where its author put it; the contents beside it link to each section on GitHub.

kb-init - Initialize Project Knowledge Base

Dispatch parallel subagents to explore the codebase, then populate the Obsidian vault with a curated set of architectural notes, references, and overviews. Mines existing project markdown docs (README, ARCHITECTURE, CHANGELOG, etc.) for insights, but verifies every concrete claim against the current code so stale documentation doesn't pollute the vault.

Turns an empty vault (or a thin one) into a rich knowledge base the next agent can hit the ground running with - and flags which existing project docs are outdated.

Step 0: Preflight - Obsidian available and running?

Follow the Preflight Check in the obsidian-kb awareness skill (${CLAUDE_PLUGIN_ROOT}/skills/obsidian-kb/SKILL.md). In short:

  1. command -v obsidian - if missing, check if the app is installed; if neither, show cross-platform install instructions (brew install --cask obsidian / flatpak install flathub md.obsidian.Obsidian / winget install Obsidian.Obsidian, or https://obsidian.md/download) and stop.
  2. timeout 3 obsidian vaults - if it fails, launch Obsidian (open -a Obsidian on macOS, equivalent for Linux/Windows), wait 2-3 seconds, retry.
  3. Only proceed once obsidian vaults succeeds.

Step 1: Resolve the Project Vault (strict)

Follow the Vault Resolution Algorithm in ${CLAUDE_PLUGIN_ROOT}/skills/obsidian-kb/SKILL.md. Strict priority order:

  1. User argument (vault name) → fuzzy-match once, confirm.
  2. Path overlap - exactly one vault whose path is inside $PWD or vice versa.
  3. Frontmatter project_path - a root note's YAML matches $PWD exactly.
  4. Strong name match - word-boundary substring match, exactly one candidate.
  5. STOP and ask - if tiers 1–4 fail, list vaults and ask. Offer the "create a new vault for this project" option (the "If no vault exists" branch below).

This skill writes substantial content to the vault (5-8 notes). Writing to the wrong vault would pollute it. When uncertain, ASK.

Read the full file on GitHub · 699 lines

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. 2mo ago First seen · 699 lines · 140 tokens per session scan A 485beaf14a3e

Subscribe to this mod's changes

kb-init is a skill published in the GitHub repository waelmas/codeplow (8 stars, last pushed 6mo ago), licensed MIT. It adds 140 tokens to every session and 8,368 once invoked, about $0.0006 per session on Opus 5.5. 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.

Writing and docs
Related

kb-init compared with skills from other repositories

kb-init next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
kb-initwaelmas/codeplowSkill86mo agoMITA140Claude Code
imagegenopenai/codexSkill133kyesterdayApache-2.0A113Codex
playwright-climicrosoft/playwrightSkill99kyesterdayApache-2.0A19Claude Code
local-ai-agentsmicrosoft/ai-agents-for-beginnersSkill79k4d agoMITA200Claude Code, Codex
systematic-debuggingobra/superpowersSkill313k3d agoMITA21Claude Code
next-cache-components-adoptionvercel/next.jsSkill143kyesterdayMITA95Claude Code
next-partial-prefetching-adoptionvercel/next.jsSkill143kyesterdayMITA103Claude Code