wiki-update

wiki-update is a command for Claude Code from bradduy/wiki-knowledge-compiler. It costs 16 tokens per session (1,324 once invoked), scanned A, original, Apache-2.0.

A command for synchronising a wiki: it processes new files in a raw folder and rebuilds the wiki's summaries, concepts, topics, indexes, and related records.

In plain words
What is it for?
Use it after adding source documents to ingest them, create summaries and extracted concepts, and refresh the wiki's organised data.
Why use it?
It prevents newly added documents from being left out of the knowledge base and keeps the wiki's generated indexes up to date.

Command for Claude Code

Part of the wiki-knowledge-compiler plugin — 7 commands, 4 agents, 1 hook shipped together

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 commands/bradduy/wiki-knowledge-compiler/wiki-update
Clone the repo
git clone --depth 1 https://github.com/bradduy/wiki-knowledge-compiler

Made for: Claude Code.

Or install wiki-knowledge-compiler, the plugin that ships this one along with the rest of its 7 commands, 4 agents, 1 hook.

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 wiki-update

README.md
[![agentmods](https://agentmods.dev/badge/commands/bradduy/wiki-knowledge-compiler/wiki-update.svg)](https://agentmods.dev/commands/bradduy/wiki-knowledge-compiler/wiki-update)
Your own site
<a href="https://agentmods.dev/commands/bradduy/wiki-knowledge-compiler/wiki-update"><img src="https://agentmods.dev/badge/commands/bradduy/wiki-knowledge-compiler/wiki-update.svg" alt="Measured on agentmods" height="20"></a>
Per session 16 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,324 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 $0.00016 $0.01324
Opus 5 $0.00008 $0.00662
Sonnet 5 $0.00003 $0.00265
Haiku 4.5 $0.00002 $0.00132

Measured 4d ago against content hash 685fe8c9cc76, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

wiki-update 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 4d 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/commands/wiki-update.md · 172 lines

How it starts

The opening of the file, as written. The whole thing — 172 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Wiki Update

You are the wiki-librarian. Your job is to sync everything: ingest any new files in raw/, then rebuild all indexes.

Procedure

Step 1: Check for unprocessed files in raw/

  1. Scan raw/ for all files.
  2. Check which ones already have a matching summary in .data/summaries/.
  3. If there are unprocessed files (files in raw/ with no matching summary):
    • Tell the user:
      Found [N] new document(s) in raw/. Ingesting...
      
    • Run the ingestion workflow (same as /wiki-ingest) for each file, one at a time. Show progress:
      [1/N] Ingesting: filename1.md ...
        ✓ Summary created, 3 concepts extracted
      
      [2/N] Ingesting: filename2.pdf ...
        ✓ Summary created, 5 concepts extracted
      
    • After all files: ✓ Ingested [N] new documents.
  4. If no new files, tell the user: No new files in raw/.

Step 2: Scan all directories

  1. Use Glob to list all .md files in each knowledge-base subdirectory:
    • raw/**/*.md (and PDFs, etc.)
    • wiki/*.md
    • .data/concepts/*.md
    • .data/topics/*.md
    • .data/summaries/*.md
    • .data/insights/*.md
    • .data/entities/*.md
    • .data/references/*.md
    • .data/drafts/*.md
  2. For each file, read its frontmatter to extract title, type, created, sources, confidence, verified.

Step 3: Rebuild source-index.md

Write .data/index/source-index.md:

---
title: Source Index
type: index
updated: [today]
---

# Source Index

All raw sources ingested into the knowledge base.

| Source | Date Ingested | Summary | Key Concepts |
|--------|--------------|---------|--------------|
| [filename](../raw/filename) | date | [summary](../summaries/name.md) | concept1, concept2 |

Step 4: Rebuild concept-index.md

Write .data/index/concept-index.md:

---
title: Concept Index
type: index
updated: [today]
---

# Concept Index

All concepts in the knowledge base, alphabetically.

| Concept | Sources | Related Topics |
|---------|---------|----------------|
| [Name](../concepts/name.md) | source1, source2 | topic1, topic2 |

Read the full file on GitHub · 172 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. 4d ago First seen · 172 lines · 16 tokens per session scan A 685fe8c9cc76

Subscribe to this mod's changes

wiki-update is a command published in the GitHub repository bradduy/wiki-knowledge-compiler (11 stars, last pushed 4mo ago), licensed Apache-2.0. It adds 16 tokens to every session and 1,324 once invoked, about $0.0001 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.