agentmods.dev

knowledge-cartographer

knowledge-cartographer is an agent for Claude Code from jtprogru/bear-skills. It costs 203 tokens per session (2,272 once invoked), scanned A, original, MIT.

An Obsidian knowledge-base maintenance agent focused on keeping linked notes and maps of content organised. Obsidian is a note-taking app where links between notes form a knowledge graph.

In plain words
What is it for?
Use it to split oversized notes, clean up maps of content, improve navigation, and reorganise connected notes in an Obsidian vault.
Why use it?
It helps reduce overloaded hub notes, tangled links, and large notes covering unrelated subjects. It follows the vault’s existing naming, tagging, and structure rules before making changes.

Agent for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: positional $N argument; mentions AGENTS.md.

Part of the bear-skills plugin — 42 skills, 3 commands, 11 agents, 1 hook shipped together

not rated 1repo 22d ago A scan 203 tokens original MIT

Good fit Use it to split oversized notes, clean up maps of content, improve navigation, and reorganise connected notes in an Obsidian vault.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/jtprogru/bear-skills/obsidian-knowledge-cartographer
View source ↗ jtprogru/bear-skills
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/jtprogru/bear-skills

Made for: Claude Code.

Or install bear-skills, the plugin that ships this one along with the rest of its 42 skills, 3 commands, 11 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 knowledge-cartographer

README.md
[![agentmods](https://agentmods.dev/badge/agents/jtprogru/bear-skills/obsidian-knowledge-cartographer/github.svg)](https://agentmods.dev/agents/jtprogru/bear-skills/obsidian-knowledge-cartographer)
Your own site
<a href="https://agentmods.dev/agents/jtprogru/bear-skills/obsidian-knowledge-cartographer"><img src="https://agentmods.dev/badge/agents/jtprogru/bear-skills/obsidian-knowledge-cartographer/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.

agentmods 80×15 button for knowledge-cartographer

Your own site · 80×15
<a href="https://agentmods.dev/agents/jtprogru/bear-skills/obsidian-knowledge-cartographer"><img src="https://agentmods.dev/badge/agents/jtprogru/bear-skills/obsidian-knowledge-cartographer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 203 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,272 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00203 $0.02272
Opus 5 $0.00102 $0.01136
Sonnet 5 $0.00041 $0.00454
Haiku 4.5 $0.00020 $0.00227

Measured 9d ago against content hash 4b8a1e24ce1c, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

knowledge-cartographer 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 9d 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/obsidian-knowledge-cartographer.md · 177 lines

How it starts

The opening of the file, as written. The whole thing — 177 lines — stays where its author put it; the contents beside it link to each section on GitHub.

knowledge-cartographer

Роль

Поддерживаю граф знаний в работоспособном состоянии: вовремя разгружаю перегруженные узлы, разбиваю выросшие заметки, поддерживаю MOC как навигацию, а не как свалку backlinks.

Картограф не создаёт новых заметок ради дробления — только когда есть содержательный повод (атомарная идея, перегрузка hub-а, разрастание темы).

База знаний

Корень хранилища (<vault>/) задан при установке (--vault или env BEAR_VAULT). Язык: русский, технические термины — английские.

Перед действием прочитай:

  • AGENTS.md
  • навык /knowledge-structures — MOC, синтезы, атомарные заметки, когда выделять раздел
  • rules/note-types-frontmatter.md — поля up/down/other/links/sources
  • rules/file-naming.md — claim-based имена
  • rules/tags.md — структурные теги для маршрутизации
  • rules/workflows.md — рефакторинг, MOC, протокол план → подтверждение → действие
  • навык /vault-mermaid — если рисуешь схемы в MOC

Чем оркестрирует

Сигнал Скилл
Перегруженный hub-узел (десятки–сотни входящих) obsidian-untangle-knot
Одна большая заметка с несколькими темами obsidian-split-note
Лекция как частный случай большой заметки obsidian-refactor-lecture (если это конспект учёбы; иначе split-note)
MOC нужно создать или обновить Делаю руками по навыку /knowledge-structures
Синтез-заметка по нескольким источникам Делаю руками по тому же файлу

Алгоритм

1. Диагностика

Сначала пойми, какая именно проблема графа. Спроси/выясни:

  • Что болит: «MOC X перегружен», «заметка Y слишком большая», «нет структуры по теме Z»?
  • Целевой объект: конкретная заметка/MOC или discovery («найди мои hub-ы»)?
  • Папка: по умолчанию 03. Ресурсы/07. Карты/ для MOC, 03. Ресурсы/04. Заметки/ для атомарок

Discovery hub-ов:

# Подсчёт in-links по всем MOC
for f in "03. Ресурсы/07. Карты/"*.md; do
  name=$(basename "$f" .md)
  in_count=$(rg -c -F "[[$name]]" . 2>/dev/null | wc -l)
  echo "$in_count  $f"
done | sort -rn | head -10

Read the full file on GitHub · 177 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. 9d ago First seen · 177 lines · 203 tokens per session scan A 4b8a1e24ce1c

Subscribe to this mod's changes

knowledge-cartographer is an agent published in the GitHub repository jtprogru/bear-skills (1 stars, last pushed 22d ago), licensed MIT. It adds 203 tokens to every session and 2,272 once invoked, about $0.0010 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 2026-08-31.

Claude CodeMemory and contextagentopsagentsai-agentsclaude-code-plugin
Related

Other agents, from other repositories

memory-extractor

OPS specialist: Background agent that extracts user profiles, contact cards, and behavioral patterns…

Lifecycle-Innovations-Limited/claude-ops · 21 tokens

evolve-memo

Lightweight PASS-cycle memo agent (v8.57.0+, Layer P). Fires on PASS verdicts after ship to capture observations Scout/Triage saw but did NOT commit to topn. Single-pass, $0.10–0.20 per cycle. Emits carryover-todos.json and memo.md — does NOT do retrospective/digest work (that's the FAIL/WARN retrospective agent's…

mickeyyaya/evolve-loop · 86 tokens

brain-keeper

Maintains Agentic SEO project authorial brain pages, append-only log, source provenance, and Obsidian-compatible links.

agencia-conversion/agentic-seo-skills · 29 tokens

code-explorer

Fast, read-only code search and exploration subagent. Locates files by pattern, greps for symbols or keywords, answers "where is X defined / which files reference Y" with file:line citations and short excerpts. Spawn it to protect the orchestrator's context window from large search results — it reads excerpts, not…

ggemba/squad-mcp · 116 tokens

tyrion-lannister

The Hand — orchestrator and chief of staff. Use for messy, high-level, cross-cutting work that needs a plan and the right specialists on it: take an ambiguous ask, work out the strategy, delegate the pieces to the right agents (security, debugging, legal, and the rest), reconcile their reports, and deliver one clear…

takoyaro/the-agency · 0 tokens

Demonstrate

Agent for demonstrating VS Code features.

microsoft/vscode · 10 tokens