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.
npx skills add jtprogru/bear-skills --skill obsidian-untangle-knotgit clone --depth 1 https://github.com/jtprogru/bear-skillsWrote 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/skills/jtprogru/bear-skills/obsidian-untangle-knot)<a href="https://agentmods.dev/skills/jtprogru/bear-skills/obsidian-untangle-knot"><img src="https://agentmods.dev/badge/skills/jtprogru/bear-skills/obsidian-untangle-knot/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/skills/jtprogru/bear-skills/obsidian-untangle-knot"><img src="https://agentmods.dev/badge/skills/jtprogru/bear-skills/obsidian-untangle-knot.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 | $0.00089 | $0.03509 |
| Opus 5 | $0.00044 | $0.01754 |
| Sonnet 5 | $0.00018 | $0.00702 |
| Haiku 4.5 | $0.00009 | $0.00351 |
Grade A, and why
obsidian-untangle-knot 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 12d 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 — 156 lines — stays where its author put it; the contents beside it link to each section on GitHub.
obsidian-untangle-knot
Базовая идея
На общие MOC ссылаются десятки заметок: проще сослаться на [[DevOps]], чем искать подкарту. In-links растут стихийно, out-links — медленно, поэтому сигнал клубка — высокий in-degree, не out.
Скилл считает in/out хаба, использует существующую структуру hub (подзаголовки, категории) как готовые точки приземления, создаёт под-MOC и — главное действие — переключает входящие ссылки ресурсных заметок на подходящий под-MOC. Оригинал остаётся точкой входа «не знаю точнее куда»: не удаляем, один hub за прогон, файлы между папками PARA не двигаем — перевязываем связи, а не структуру.
Правила хранилища — .agents/rules/, загружаются автоматически. obsidian-split-note разбивает содержимое заметки на атомарки; здесь разбиваем связи — атомарки не создаются.
Алгоритм
1. Выбор hub-заметки
Точечный — пользователь назвал заметку: fd -t f "DevOps.md" .; несколько совпадений — спроси. Discovery — «найди мои hub-заметки»: прогон по 03. Ресурсы/07. Карты/ (или другой папке), top-10 по in + out, спроси какую разгружать:
for f in "03. Ресурсы/07. Карты/"*.md; do
out=$(rg -o '\[\[[^\]]+\]\]' "$f" | wc -l); echo "$out $f"
done | sort -rn | head -10
rg -c -F "[[Имя заметки]]" . # in-links
2. Подсчёт ссылок и диагностика
In-links — три потока с разной стратегией:
| Поток | Что это | Перепривязка |
|---|---|---|
| A. Out-соседи hub | Заметки, на которые ссылается hub (тело или down) |
Итерация 1 |
| B. Up-children | Заметки с up: [[Hub]], не упомянутые в теле hub |
Итерация 1 — не пропускай, самая «забытая» нагрузка |
| C. In-links в телах | Упоминания [[Hub]] в телах (rg -l -F, плюс pipe-вариант `[[Hub |
`) |
Поток B ищи только по полю up: — грубый grep ловит [[Hub]] в other/links/category/sources, а это другая семантика. Точный парсинг:
python3 - <<'PY'
import os, re
n = 0
for dp, _, fns in os.walk('.'):
for fn in fns:
if not fn.endswith('.md'): continue
try: c = open(os.path.join(dp, fn), encoding='utf-8').read(4000)
except: continue
m = re.match(r'^---\n(.*?)\n---', c, re.DOTALL)
if not m: continue
fm = m.group(1)
b = re.search(r'^up:\s*\n(.*?)(?=^[a-zA-Z_]+:|\Z)', fm, re.M|re.S)
s = re.search(r'^up:\s*(.+)$', fm, re.M)
if (b and re.search(r'-\s*"?\[\[Hub\]\]"?', b.group(1))) or (s and '[[Hub]]' in s.group(1)): n += 1
print(n)
PY
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 12d ago First seen · 156 lines · 89 tokens per session scan A 1018f606c130
obsidian-untangle-knot is a skill published in the GitHub repository jtprogru/bear-skills (1 stars, last pushed today), licensed MIT. It adds 89 tokens to every session and 3,509 once invoked, about $0.0004 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 skills, from other repositories
hunk-launch-video
Produces Hunk videos by driving the real TUI headlessly in a PTY, compositing captioned 1080p frames in Chromium, and encoding with ffmpeg. Use for feature demos, workflow explainers, announcements, launch videos, and full-release roundups.
docs-decisions
Work on Composio documentation content, Fumadocs configuration, changelogs, docs automation prompts, docs decisions, ADR-style records, and docs review guidance. Use for files under docs/, documentation workflows, or requests to record or update a docs decision. Do not use for SDK runtime changes unless docs are the…
ai-development-guide
Applies language-agnostic and backend technical decision criteria, anti-pattern detection, debugging, and quality gates. Use when reviewing general/backend implementation choices, code smells, failures, or implementation completeness.
recipe-front-review
Reviews completed frontend implementation for governing-source compliance, scope economy, repository quality, and security, then applies user-approved React corrections.
recipe-review
Reviews completed implementation for governing-source compliance, scope economy, repository quality, and security, then applies user-approved corrections.
buyer-job-intent-analysis
Recover source-bound buyer jobs, struggling moments, desired progress, forces, workarounds, information acts, journey states, criteria, constraints, roles, locales, and authentic language. Use on approved ICP hypotheses plus customer, search, review, forum, procurement, support, or public-market evidence before…