knowledge-wiki-cluster

A tool for organizing concept notes that share a common name prefix, such as grouping apple-watch-ultra under apple-watch. It can create a missing parent note or connect notes to an existing parent.

In plain words
What is it for?
Use it to find related note groups, create or update parent concepts, and choose how each child note should be handled.
Why use it?
It reduces a scattered set of small or overlapping notes by giving them a shared structure. You decide whether each child note is folded into the parent, kept and linked, or merged with a sibling.

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/catchen/knowledge-wiki-template/knowledge-wiki-cluster
Any agent
npx skills add CatChen/knowledge-wiki-template --skill knowledge-wiki-cluster
Clone the repo
git clone --depth 1 https://github.com/CatChen/knowledge-wiki-template

Made for: Claude Code, Codex.

Per session 111 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 4,660 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 $0.00111 $0.04660
Opus 5 $0.00056 $0.02330
Sonnet 5 $0.00022 $0.00932
Haiku 4.5 $0.00011 $0.00466

Measured 3d ago against content hash e3050de091aa, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

knowledge-wiki-cluster 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 3d 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.

.claude/skills/knowledge-wiki-cluster/SKILL.md · 283 lines

How it starts

The opening of the file, as written. The whole thing — 283 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Knowledge Wiki Cluster

Detect clusters of concepts that share an implied parent slug, then decide for each child whether to fold (merge content into parent and delete the child) or link (keep the child as a standalone concept linked to the parent). The goal is to reduce total concept count by absorbing thin, redundant, or retired sub-concepts into a parent article.

Two cluster types are handled:

  • New-parent (parentExists: false): the implied parent concept does not exist yet — create it, then fold/link/merge children.
  • Existing-parent (parentExists: true): the implied parent already exists and these children have not yet been dismissed — fold/link/merge each one.

For new-parent clusters, each concept is grouped under its non-existing prefix ancestors up to (but not including) its nearest existing ancestor — so apple-watch-ultra forms an [apple-watch] cluster when apple-watch.md is absent, even if apple.md exists. For existing-parent clusters, the concept is grouped directly at its nearest existing ancestor. Presents one cluster at a time with a batch recommendation — you confirm, override, or dismiss.

Within a cluster, children may also be merged into each other (sibling merging) before any folding into the parent. A child judged not worth folding into the parent — an Anchor — can absorb another child's content if that child — a Fold-candidate — is a strict subset of the Anchor's content. The absorbed Fold-candidate is merged into the Anchor and deleted; the Anchor is recommended to stay standalone and is not expected to be folded into the parent.

Steps

1. Establish the working directory

The knowledge base root is the Git repository root. Run git rev-parse --show-toplevel and store the result as KNOWLEDGE_PATH.

2. Find clusters

Run:

node {KNOWLEDGE_PATH}/scripts/wiki/candidates.mjs find-implied-parent-concepts

This outputs { "clusters": [...] } sorted deepest first (most hyphens in impliedParent), with ties broken by cluster size descending. Both new-parent and existing-parent clusters are interleaved in this single ordering. Each entry has:

  • impliedParent — the parent slug
  • children — array of { path, dismissed } objects, where path is the concept file path (e.g. Wiki/Concepts/audi-etron.md) and dismissed is true if this child was previously dismissed from this cluster pair, false otherwise
  • parentExistsfalse if the parent concept needs to be created; true if it already exists

Read the full file on GitHub · 283 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. 3d ago First seen · 283 lines · 111 tokens per session scan A e3050de091aa

Subscribe to this mod's changes

knowledge-wiki-cluster is a skill published in the GitHub repository CatChen/knowledge-wiki-template (105 stars, last pushed 2mo ago), licensed MIT. It adds 111 tokens to every session and 4,660 once invoked, about $0.0006 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

systematic-debugging

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

obra/superpowers · 21 tokens

brainstorming

You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.

obra/superpowers · 37 tokens

auto-perf-optimize

Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.

microsoft/vscode · 62 tokens

chat-perf

Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.

microsoft/vscode · 51 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 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