kb-init

A setup tool for a project's knowledge base, which is a collection of reusable team notes and documentation. It creates the documentation folder and adds or updates its reference section in CLAUDE.md.

In plain words
What is it for?
Starting a knowledge base, creating its directory, registering it in CLAUDE.md, and checking whether an existing setup is already present.
Why use it?
It gives a project a consistent place and configuration for shared technical knowledge, while allowing the setup to be run again safely.

Skill for Claude CodeCodex

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 skills/charlesjones-dev/claude-code-plugins-dev/kb-init
Any agent
npx skills add charlesjones-dev/claude-code-plugins-dev --skill kb-init
Clone the repo
git clone --depth 1 https://github.com/charlesjones-dev/claude-code-plugins-dev

Made for: Claude Code, Codex.

Per session 32 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,903 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 $0.00032 $0.02903
Opus 5 $0.00016 $0.01452
Sonnet 5 $0.00006 $0.00581
Haiku 4.5 $0.00003 $0.00290

Measured 2d ago against content hash 8c296707cec8, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, 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 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.

plugins/ai-knowledge/skills/kb-init/SKILL.md · 272 lines

How it starts

The opening of the file, as written. The whole thing — 272 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Knowledge Base Initialization

You are a knowledge base setup assistant. Your job is to initialize the Knowledge Base infrastructure in the current project.

Instructions

CRITICAL: This command MUST NOT accept any arguments. Ignore any text provided after the command.

SCOPE RULE: All KB operations target only the current working directory (the parent directory where Claude Code is running). Never create docs/kb/ in subdirectories, never modify CLAUDE.md files in subdirectories, and never add KB references to sub-directory CLAUDE.md files. The docs/kb/ directory and its contents should be committed to source control for team sharing.

Step 1: Detect Current State

  1. Check for docs/kb/ directory: Use Glob to check if docs/kb/ exists and contains any .md files.
  2. Check for CLAUDE.md: Read the project's CLAUDE.md file (in the current working directory). If it doesn't exist, note that it will be created.
  3. Check for existing KB section: If CLAUDE.md exists, look for a ## Knowledge Base section (or # Knowledge Base depending on heading conventions used in the file).

Step 2: Create Directory Structure

Resolve today's date (cross-platform, CRITICAL): Before writing any file below, run the first command that works in the current shell and use the returned YYYY-MM-DD string for every {today's date} placeholder in the templates. Never guess, never infer, never increment.

  • macOS / Linux / WSL / Git Bash (bash, zsh, sh): date +%Y-%m-%d
  • Windows PowerShell / pwsh: Get-Date -Format 'yyyy-MM-dd'
  • Windows cmd.exe: powershell -NoProfile -Command "Get-Date -Format 'yyyy-MM-dd'"
  • Portable fallback (Node or Python available): node -e "console.log(new Date().toISOString().slice(0,10))" or python -c "import datetime; print(datetime.date.today().isoformat())"

If docs/kb/ does not exist, create it with a placeholder README:

File: docs/kb/README.md

# Knowledge Base

This directory contains topic-specific knowledge base files that are dynamically referenced in CLAUDE.md.

## Structure

KB articles are organized in category folders. Special files (prefixed with `_`) live at the root:

docs/kb/ _global-learnings.md # Cross-cutting rules (pinned, always loaded) _index.md # Auto-generated page catalog with summaries _log.md # Chronological operation log README.md # This file architecture/ # Architecture patterns and system design conventions/ # Naming, coding, and API conventions tools/ # Tooling, workflow, and infrastructure ... # Other categories as needed


Category folders are created as needed based on article content. Articles can also be flat at the root for small KBs:

## Frontmatter Schema

Every KB file MUST include YAML frontmatter. This metadata is used by all `/kb-*` commands for search, pruning, cross-referencing, and contextual loading.

```yaml
---
tags: [api, auth, security]          # Cross-cutting topic tags for discovery
related: [[api-conventions]]         # Cross-references to other KB files (by filename without extension)
created: 2026-04-02                  # Date the file was created
last-updated: 2026-04-02            # Date the file was last modified
pinned: false                        # If true, always loaded regardless of context
scope: "packages/api/**"             # Optional glob pattern(s) for auto-matching. String or array of strings.
---

Field Reference

Field Required Description
tags Yes Array of lowercase tags for cross-cutting discovery. Used by /kb-search.
related No Array of [[filename]] references to other KB files. When one file is loaded, related files may also be consulted.
created Yes ISO date (YYYY-MM-DD) when the file was first created.
last-updated Yes ISO date (YYYY-MM-DD) when the file was last modified. Updated automatically by KB commands.
pinned No Boolean. When true, this file is always loaded at the start of every conversation. Default: false. Use sparingly.
scope No Glob pattern(s) matching file paths where this knowledge applies. Can be a single string ("src/api/**") or an array of strings (["src/api/**", "*.controller.ts"]). These patterns are surfaced in the CLAUDE.md table's "When to Load" column for efficient context matching.

File Format

Each KB file should follow this structure:

---
tags: [topic-tag]
related: [[other-kb-file]]
created: YYYY-MM-DD
last-updated: YYYY-MM-DD
pinned: false
scope: []                            # String or array of glob patterns for auto-matching
---

Read the full file on GitHub · 272 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. 2d ago First seen · 272 lines · 32 tokens per session scan A 8c296707cec8

Subscribe to this mod's changes

kb-init is a skill published in the GitHub repository charlesjones-dev/claude-code-plugins-dev (34 stars, last pushed 1mo ago), licensed MIT. It adds 32 tokens to every session and 2,903 once invoked, about $0.0002 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 2026-08-30.

Related

Other skills, from other repositories

gwm

Manage git worktrees across any repository with the gwm Rust binary (CLI + ratatui TUI). Use when the user asks to create / list / remove / bootstrap / switch / link worktrees, run a command across worktrees (gwm exec) or reclaim build artifacts (gwm clean), materialise a PR into a worktree (gwm review), drive a…

kbrdn1/gwm-cli · 379 tokens

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

babysit-pr

Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…

openai/codex · 114 tokens

imagegen

Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…

openai/codex · 113 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens