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 knowledge-structuresgit 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/knowledge-structures)<a href="https://agentmods.dev/skills/jtprogru/bear-skills/knowledge-structures"><img src="https://agentmods.dev/badge/skills/jtprogru/bear-skills/knowledge-structures/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/knowledge-structures"><img src="https://agentmods.dev/badge/skills/jtprogru/bear-skills/knowledge-structures.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 | $0.00084 | $0.01615 |
| Opus 5.5 | $0.00034 | $0.00646 |
| Sonnet 5.5 | $0.00017 | $0.00323 |
| Haiku 4.5 | $0.00008 | $0.00161 |
Grade A, and why
knowledge-structures 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.
How it starts
The opening of the file, as written. The whole thing — 103 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Структуры знаний: MOC, синтез, атомарные заметки
MOC (Map of Content)
MOC — навигационная заметка, которая собирает ссылки по определённой теме.
Главная MOC — README.md в корне. Тематические MOC лежат в 03. Ресурсы/07. Карты/; новую карту агент создаёт в 00. Входящие/ с #MapOfContent + #review и она переезжает в Карты после ревью (см. workflows.md).
Когда создавать MOC
- Тема упоминается в 5+ заметках и нет единой точки входа
- Пользователь явно просит создать карту по теме
- Появляется новая крупная область знаний
Структура и правила MOC
Каркас — Шаблон карты.md в _Система/1. Шаблоны/. Обязательные секции: ## Описание (2–3 предложения своими словами), ## Ключевые заметки (ссылки с краткими аннотациями — не просто список, а список с контекстом), ## Связанные темы, ## Автосбор заметок (Dataview/Bases-запрос по ссылкам или тегу).
- В
upуказывай родительскую MOC или область (если есть), вdown— дочерние крупные подтемы - Добавляй Dataview-запрос для автоматического сбора связанных заметок
Синтез-заметки
Синтез — заметка, сравнивающая несколько концептов/инструментов/подходов и выдающая кросс-срезовый вывод.
Хранится в 03. Ресурсы/07. Карты/, тег #synthesis. Как и карта, создаётся агентом в 00. Входящие/ с #review и переезжает после ревью.
Когда создавать синтез
- Есть 2+ концепта/инструмента для сравнения
- Появился инсайт, охватывающий несколько заметок сразу
- Пользователь явно просит «сравни», «что лучше», «какой подход выбрать»
Структура и правила синтеза
Каркас: frontmatter с tags: [synthesis], sources, confidence + секции ## Сравнение (таблица по критериям), ## Анализ (кросс-срезовые выводы), ## Рекомендация (когда какой подход и почему), ## Связанные заметки (ссылки с пояснениями).
- В
sourcesперечисляй все исходные заметки; каждый вывод должен ссылаться на конкретные заметки - Если вывод основан на одной заметке — это не синтез, а атомарная мысль
- При обновлении исходных заметок — проверяй актуальность синтеза
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.
- 1mo ago First seen · 103 lines · 84 tokens per session scan A 76e8105a377d
knowledge-structures is a skill published in the GitHub repository jtprogru/bear-skills (1 stars, last pushed 4d ago), licensed MIT. It adds 84 tokens to every session and 1,615 once invoked, about $0.0003 per session on Opus 5.5. 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.
potpie-source-ingestion
Use when the user explicitly asks to ingest, refresh, or deeply understand a repository, PR, issue, ticket, runbook, incident report, document, or web link into Potpie. The harness performs todo-driven discovery, uses local/GitHub/integration tools and read-only subagents when available, builds evidence-backed…
voice-extractor
Capture a user's real writing voice from 5-20 prior samples, store a local voice.yaml fingerprint, and enforce it on newsjack drafts so AI tells disappear. Measures voice with named stylometry lenses (Burrows's Delta function-word vector, MATTR lexical diversity, sentence-length burstiness, Biber Dimension-1 register…
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.
coding-principles
Language-agnostic coding principles for maintainability, readability, and quality. Use when implementing features, refactoring code, or reviewing code quality.