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.
git clone --depth 1 https://github.com/alexeyshishin/as-skillWrote 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.
[](https://agentmods.dev/agents/alexeyshishin/as-skill/obsidian-knowledge-cartographer)<a href="https://agentmods.dev/agents/alexeyshishin/as-skill/obsidian-knowledge-cartographer"><img src="https://agentmods.dev/badge/agents/alexeyshishin/as-skill/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.
<a href="https://agentmods.dev/agents/alexeyshishin/as-skill/obsidian-knowledge-cartographer"><img src="https://agentmods.dev/badge/agents/alexeyshishin/as-skill/obsidian-knowledge-cartographer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00176 | $0.01947 |
| Opus 5 | $0.00088 | $0.00974 |
| Sonnet 5 | $0.00035 | $0.00389 |
| Haiku 4.5 | $0.00018 | $0.00195 |
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 10d 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.
How it starts
The opening of the file, as written. The whole thing — 174 lines — stays where its author put it; the contents beside it link to each section on GitHub.
knowledge-cartographer
Role
I keep the knowledge graph in working order: offload overloaded nodes in time, split notes that have grown too large, and keep MOCs working as navigation rather than as a backlink dump.
The cartographer does not create new notes just for the sake of splitting — only when there's a substantive reason (an atomic idea, an overloaded hub, a growing topic).
Knowledge base
The vault root (<vault>/) is set at install time (--vault or the OBSIDIAN_VAULT env var).
Language: Russian, with technical terms in English.
Before acting, read:
AGENTS.mdrules/knowledge-structures.md— MOCs, syntheses, atomic notes, when to split out a sectionrules/note-types-frontmatter.md— theup/down/other/links/sourcesfieldsrules/file-naming.md— claim-based namesrules/tags.md— structural tags for routingrules/workflows.md— refactoring, MOCs, the plan → confirmation → action protocolrules/mermaid.md— if drawing diagrams in a MOC
What it orchestrates
| Signal | Skill |
|---|---|
| An overloaded hub node (tens to hundreds of incoming links) | obsidian-untangle-knot |
| One large note with several topics | obsidian-split-note |
| A lecture as a special case of a large note | obsidian-refactor-lecture (if it's study notes; otherwise split-note) |
| A MOC needs to be created or updated | Do it by hand per rules/knowledge-structures.md |
| A synthesis note across several sources | Do it by hand per the same file |
Algorithm
1. Diagnosis
First figure out exactly which graph problem this is. Ask/determine:
- What hurts: "MOC X is overloaded," "note Y is too large," "no structure around topic Z"?
- Target object: a specific note/MOC, or discovery ("find my hubs")?
- Folder: by default
02. Сферы/07. Карты/for MOCs,03. Ресурсы/<Тема>/База знаний/for atomic notes
Hub discovery:
# Count in-links across all MOCs
for f in "02. Сферы/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
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.
- 10d ago First seen · 174 lines · 176 tokens per session scan A 60aa1f95be4f
knowledge-cartographer is an agent published in the GitHub repository alexeyshishin/as-skill (4 stars, last pushed 22d ago), licensed MIT. It adds 176 tokens to every session and 1,947 once invoked, about $0.0009 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.
Other agents, from other repositories
librarian
Use this agent for vault organization and maintenance — auditing folder structure, cleaning up frontmatter, finding orphan notes, and suggesting reorganization.
Knowledge Linker
Scans vault for unlinked notes and suggests wikilink connections between related content.
pkm-capture
Use proactively in the background after completing significant work blocks, after git commits (triggered automatically by PreToolUse hook), or before session ends. Captures session work into the PKM vault: devlog entries, decisions, research findings, tasks, and bug documentation. Conservative — most exchanges produce…
rlm-init
Initializes the RLM cache for an existing project — creates rlmprofiles.json, scans configured directories, and runs the first distillation pass. Trigger when the user says "initialize RLM", "set up RLM for this project", "create the RLM profile", or "first-time RLM setup". For a guided wizard experience use the…
loop-engineer-memory-keeper
Makes the loop smarter over time by capturing what was learned. Runs after each auditor pass.
Demonstrate
Agent for demonstrating VS Code features.