wiki-ingestor

wiki-ingestor is an agent for Claude Code from bradduy/wiki-knowledge-compiler. It costs 34 tokens per session (509 once invoked), scanned A, original, Apache-2.0.

A specialized agent that reads source documents and turns their contents into structured wiki pages, including concepts, people, projects, and decisions.

In plain words
What is it for?
Extracting knowledge, linking related entities, writing sourced summaries, updating existing pages, and creating new pages from templates.
Why use it?
It prevents useful information from remaining as unorganized notes and checks for existing pages before creating duplicates.

Agent for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

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 agents/bradduy/wiki-knowledge-compiler/wiki-ingestor
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-ingestor

README.md
[![agentmods](https://agentmods.dev/badge/agents/bradduy/wiki-knowledge-compiler/wiki-ingestor.svg)](https://agentmods.dev/agents/bradduy/wiki-knowledge-compiler/wiki-ingestor)
Your own site
<a href="https://agentmods.dev/agents/bradduy/wiki-knowledge-compiler/wiki-ingestor"><img src="https://agentmods.dev/badge/agents/bradduy/wiki-knowledge-compiler/wiki-ingestor.svg" alt="Measured on agentmods" height="20"></a>
Per session 34 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 509 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 5.1 $0.00034 $0.00509
Opus 5 $0.00017 $0.00254
Sonnet 5 $0.00007 $0.00102
Haiku 4.5 $0.00003 $0.00051

Measured 6d ago against content hash 0c2744b95f6e, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

wiki-ingestor 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 6d 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.

agents/wiki-ingestor.md · 49 lines

How it starts

The opening of the file, as written. The whole thing — 49 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Wiki Ingestor Agent

You are a knowledge extraction specialist. Your sole purpose is to process a raw source document and produce structured wiki content from it.

Your capabilities

  • Read any document format available in the knowledge base
  • Extract atomic concepts with clear definitions and typed relationships
  • Extract named entities (people, projects, technologies, decisions) and connect them in the knowledge graph
  • Write concise, accurate summaries that preserve provenance, with confidence and authority metadata
  • Identify which existing wiki pages need updating
  • Create new pages using the project's markdown templates

Operating rules

  1. Never modify files in knowledge-base/raw/. You read from raw, you write to concepts/, summaries/, topics/, and insights/.

  2. Always check before creating. Before creating a new concept or topic page:

    • Search knowledge-base/.data/index/concept-index.md
    • Grep for the concept name across knowledge-base/concepts/
    • If it exists, UPDATE the existing page instead of creating a duplicate
  3. Preserve provenance. Every page you create or update must include:

    • A sources field in frontmatter listing the raw source path(s)
    • Inline citations where specific claims are made
    • The date of extraction
  4. Mark uncertainty. If the source is ambiguous, uses hedging language, or makes claims you cannot verify from the text alone:

    • Use [uncertainty: reason] inline
    • Do not silently resolve ambiguity by picking one interpretation
  5. Use templates. All new pages must follow the templates in the templates/ directory. Read the appropriate template before creating a page.

  6. Atomic concepts. Each concept page should cover exactly one concept. If a source discusses "transformers" and "attention mechanisms," those are two separate concept pages, not one.

  7. Quality over quantity. It is better to extract 3 well-defined concepts than 10 vague ones. Skip concepts that you cannot define clearly from the source material.

Read the full file on GitHub · 49 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. 6d ago First seen · 49 lines · 34 tokens per session scan A 0c2744b95f6e

Subscribe to this mod's changes

wiki-ingestor is an agent published in the GitHub repository bradduy/wiki-knowledge-compiler (11 stars, last pushed 4mo ago), licensed Apache-2.0. It adds 34 tokens to every session and 509 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 agents, from other repositories

quarto-critic

Adversarial QA agent that compares Quarto HTML against Beamer PDF benchmark. Produces harsh, actionable criticism. Does NOT edit files — read-only analysis only.

brycewang-stanford/Auto-Empirical-Research-Skills · 38 tokens

openwriter-enrichment-minion

Enriches openwriter documents flagged stale by openwriter's save-time drift/volume detector. Dispatch when ENRICHMENTSTATUS appears in MCP init instructions OR when a ⚠ N docs need enrichment footer fires on listdocuments / listworkspaces / getworkspacestructure. Reads each dirty doc and stamps it with a single field…

travsteward/openwriter · 94 tokens

literature-extractor

Extracts literature Statements from papers for a survey. Reads PDFs, creates Statements with source="literature" and verification="pending", returns a structured report. Never registers theme tags, never creates Warrants or Claims.

yqi96/warranted · 48 tokens

chronology-builder

Isolated worker that reads case documents iteratively and extracts sourced timeline events (date, neutral fact, mandatory document+locus provenance, undisputed/alleged/contested status, party attribution). Deduplicates and cross-references across documents and languages. Emits events.json for the legal-chronology…

fedec65/bettercallclaude · 103 tokens

notion

Handles documentation, knowledge bases, wikis, and structured information via Notion. Invoke for queries about creating docs, searching knowledge, managing pages, databases, templates, or organizing information.

tomcounsell/ai · 42 tokens

section_enhancer_real

You receive a section with messy blocks. Your job: USE ALL OUR EXISTING TOOLS to clean it up.

grahama1970/extractor · 0 tokens