knowledge-base

A set of rules for creating and maintaining a Markdown knowledge base that AI agents can read. Markdown is plain text with simple formatting, and the knowledge base uses an index to point agents to individual notes.

In plain words
What is it for?
Use it to start a knowledge base, add or update notes, organize agent documentation, or clean up an existing Markdown note collection.
Why use it?
It keeps notes organized and discoverable without needing a vector database, while stable IDs and links help notes remain usable after moves or renames.

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/developkiko/dsktpcmndr/knowledge-base
Any agent
npx skills add developkiko/DsktpCmndr --skill knowledge-base
Clone the repo
git clone --depth 1 https://github.com/developkiko/DsktpCmndr

Made for: Claude Code, Codex.

Per session 112 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,165 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin 100% copy Near-identical to another mod 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 $0.00112 $0.02165
Opus 5 $0.00056 $0.01082
Sonnet 5 $0.00022 $0.00433
Haiku 4.5 $0.00011 $0.00216

Measured yesterday against content hash 34ca1c1fd9e6, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

knowledge-base 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 yesterday.

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.

Origin

This is a copy

100% identical to knowledge-base — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

plugins/claude/skills/knowledge-base/SKILL.md · 199 lines

How it starts

The opening of the file, as written. The whole thing — 199 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Knowledge Base (Markdown, agent-readable)

A knowledge base (KB) here is a folder of Markdown files designed so any AI agent can navigate it without a vector database: the agent reads one index file, picks the relevant notes by their descriptions, and opens only those. Keep the whole KB readable and the index lean — the index is what gets loaded into context, so it must be high-signal.

Apply the rules below when creating a new KB, adding/editing notes, or doing a maintenance pass. When the user's request is ambiguous (new KB vs. add note vs. cleanup), ask which one before acting.

Core principles (the "why")

  1. Index-first navigation. The index is a map, not a container. An agent reads INDEX.md, selects notes by their one-line descriptions, then opens only those files. No note is "in" the KB unless it's registered in the index.
  2. Atomicity. One topic per note. If a title needs an "and", it's probably two notes. Atomic notes are easier to find, link, and reuse.
  3. Stable IDs. Every note has a permanent ID that never changes and is never reused, so links survive renames and moves.
  4. Linked with reason. When two notes connect, state why (prerequisite, supports, contrasts, see-also). Connections carry as much value as the notes.
  5. Lean instructions. Keep INDEX.md instructions short and high-signal — it competes for the agent's context budget. Bodies load on demand.
  6. Structured for retrieval. Clear H1 title and H2/H3 sections so an agent can grab the relevant slice of a note, not the whole thing.

Folder structure (nested by topic)

knowledge-base/
  INDEX.md                 # entry point: instructions + full note registry
  topics/
    <topic>/
      _topic.md            # topic map: what this topic covers + its notes
      <slug>.md            # one atomic note
  assets/                  # images / attachments referenced by notes
  • Topic folders are short, lowercase nouns (auth, billing, deploys).
  • _topic.md is the topic-level map of content (MOC): a short intro plus links to every note in that topic. It is a convenience view; INDEX.md remains the source of truth.

Read the full file on GitHub · 199 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. yesterday First seen · 199 lines · 112 tokens per session scan A 34ca1c1fd9e6

Subscribe to this mod's changes

knowledge-base is a skill published in the GitHub repository developkiko/DsktpCmndr (0 stars, last pushed 1mo ago), licensed MIT. It adds 112 tokens to every session and 2,165 once invoked, about $0.0006 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to knowledge-base, differing in 0 lines, and is treated as a copy.

Related

Other skills, from other repositories

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

next-cache-components-optimizer

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…

vercel/next.js · 170 tokens