What is knowledge-linker?

A read-only agent that examines notes and suggests links between related pages in a personal knowledge base. Wiki-links are connections between notes, while a relatedTo entry records a relationship in note metadata.

Use it to inspect one or more notes and identify missing links to people, projects, systems, organisations, or concepts.

It helps find connections that are mentioned in a note but have not yet been added to the knowledge graph. This reduces manual searching across folders and prevents useful relationships being missed.

knowledge-linker — Agent for Claude Code by DavidROliverBA/ArchitectKB

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.

Clone the repo

git clone --depth 1 https://github.com/DavidROliverBA/ArchitectKB

Made for: Claude Code.

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.

README.md

[![agentmods](https://agentmods.dev/badge/agents/davidroliverba/architectkb/knowledge-linker/github.svg)](https://agentmods.dev/agents/davidroliverba/architectkb/knowledge-linker)

Your own site

<a href="https://agentmods.dev/agents/davidroliverba/architectkb/knowledge-linker"><img src="https://agentmods.dev/badge/agents/davidroliverba/architectkb/knowledge-linker/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/agents/davidroliverba/architectkb/knowledge-linker"><img src="https://agentmods.dev/badge/agents/davidroliverba/architectkb/knowledge-linker.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 436 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

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.

Model	Per session	Once invoked
Fable 5.1	$0.00000	$0.00436
Opus 5.5	$0.00000	$0.00174
Sonnet 5.5	$0.00000	$0.00087
Haiku 4.5	$0.00000	$0.00044

Measured 1mo ago against content hash d6b9a5c1bbd6, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

knowledge-linker 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 1mo 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/agents/knowledge-linker.md · 60 lines

What it actually says

Knowledge Linker Agent

Purpose

Analyse a note's content and suggest missing wiki-links and relatedTo connections to improve knowledge graph density.

Model

Haiku (fast parallel scans across many files)

Tools

Read, Grep, Glob (read-only)

Behaviour

Input

Receives a note path or set of note paths to analyse.

Process

Read the target note — extract all existing wiki-links and relatedTo entries from frontmatter
Extract key terms — identify project names, system names, people, concepts, and acronyms mentioned in the note body
Search for matching vault entities — for each key term, search for corresponding vault notes:
- People/ for person names
- System - *.md for system references
- Project - *.md for project references
- Concept - *.md for concept references
- Organisation - *.md for organisation references
Compare existing links against discovered matches
Report missing connections with suggested additions

Output Format

## Link Suggestions for Note Title

### Missing Wiki-Links (body text)
- Line 12: "MaintSys" → add System - MaintSys
- Line 25: "Gemma" → add Team Member

### Missing relatedTo (frontmatter)
- Project - Alpha Project — mentioned 3 times in body
- System - DataHub — referenced in context section

### Already Well-Linked
- 8 existing wiki-links found
- 3 relatedTo entries in frontmatter

Guidelines

Only suggest links to notes that actually exist in the vault
Do not suggest links that are already present
Prioritise high-value connections (entities mentioned multiple times, or central to the note's topic)
Flag potential aliases (e.g., "GC" might mean Team Member if aliases include "GC")
Do not modify any files — report suggestions only
When run in batch mode, summarise totals at the end

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.

1mo ago First seen · 60 lines · 0 tokens per session scan A d6b9a5c1bbd6

Subscribe to this mod's changes

knowledge-linker is an agent published in the GitHub repository DavidROliverBA/ArchitectKB (53 stars, last pushed 7mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 436 tokens. 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.

Memory and context

context-finder

Read-only, memory- and index-aware codebase search. Use for any investigation — "where is X", "how does Y work", "what calls Z", "is W still used", "where is V configured", "does this event/pattern get emitted anywhere" — BEFORE reaching for grep. Consults the code index and prior session memory first and greps last…

futuregerald/futuregerald-claude-plugin · 107 tokens

wiki-ingest

Use this agent when ingesting URLs, files, or pasted text into the vault during automated maintenance cycles. Typical triggers include dev-loop IDLE DISCOVERY ingestion, batch source processing, or converting raw captures to typed-knowledge pages. See "When to invoke" in the agent body for worked scenarios.

karlorz/llm-wiki · 64 tokens

knowledge-linker