kb-load

A command for manually loading selected knowledge-base articles into the current conversation. A knowledge base is a collection of project notes or reference documents.

In plain words
What is it for?
Use it to load an article by filename or topic, load articles with a tag, load several articles, or load the whole registered knowledge base.
Why use it?
It supplies information that the coding agent did not load automatically, without changing any files.

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

Made for: Claude Code, Codex.

Per session 40 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,114 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 $0.00040 $0.01114
Opus 5 $0.00020 $0.00557
Sonnet 5 $0.00008 $0.00223
Haiku 4.5 $0.00004 $0.00111

Measured 2d ago against content hash 44fedaeda21f, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

kb-load 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-load/SKILL.md · 103 lines

How it starts

The opening of the file, as written. The whole thing — 103 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Knowledge Base Manual Load

You are a knowledge base loading assistant. Your job is to load specific KB articles into the current conversation context when the user feels relevant knowledge wasn't automatically loaded. This is a quick, read-only operation — no files are modified.

Instructions

Step 1: Determine What to Load

Check if the user provided an argument after the command. Arguments can be:

  • Filename (with or without path/extension): e.g., /kb-load api-conventions or /kb-load docs/kb/conventions/api-conventions.md
  • Topic name: e.g., /kb-load API Conventions (matches against the Topic column in the CLAUDE.md table)
  • Tag filter: e.g., /kb-load tag:api or /kb-load tag:testing (loads all KB files with the matching tag)
  • Multiple items: e.g., /kb-load api-conventions auth-patterns (space-separated filenames)
  • all: /kb-load all — loads every registered KB file (warn that this may use significant context)

If no argument provided: Proceed to Step 2 for interactive selection.

If argument provided: Skip to Step 3.

Step 2: Interactive Selection (no argument)

  1. Read CLAUDE.md: Parse the Knowledge Base table to get all registered entries.

  2. Read docs/kb/_index.md if it exists for summaries.

  3. Present available KB files using AskUserQuestion:

    • Header: "KB Load"
    • Question: Show the table of available KB files with their topics, tags (from frontmatter or index), and "When to Load" criteria. Ask: "Which KB file(s) would you like to load? Enter a topic name, filename, tag (e.g., tag:api), or number."
    • Number each entry for easy selection.
    • Allow free-text response.

Step 3: Resolve Files

Based on the user's input, resolve to one or more file paths:

Filename match
  1. If the input looks like a filename (contains no spaces, may have path segments):
    • Try exact path match first: docs/kb/{input}, docs/kb/{input}.md
    • Try recursive glob: docs/kb/**/{input}.md, docs/kb/**/{input}
    • If multiple matches, present them and ask the user to pick.
    • If no match, inform the user and suggest checking /kb-list.

Read the full file on GitHub · 103 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 · 103 lines · 40 tokens per session scan A 44fedaeda21f

Subscribe to this mod's changes

kb-load is a skill published in the GitHub repository charlesjones-dev/claude-code-plugins-dev (34 stars, last pushed 1mo ago), licensed MIT. It adds 40 tokens to every session and 1,114 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