Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/jtprogru/bear-skillsnpx agentmods add skills/jtprogru/bear-skills/vault-statsWrote 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/vault-stats)<a href="https://agentmods.dev/skills/jtprogru/bear-skills/vault-stats"><img src="https://agentmods.dev/badge/skills/jtprogru/bear-skills/vault-stats/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/vault-stats"><img src="https://agentmods.dev/badge/skills/jtprogru/bear-skills/vault-stats.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 | $0.00095 | $0.00858 |
| Opus 5 | $0.00048 | $0.00429 |
| Sonnet 5 | $0.00019 | $0.00172 |
| Haiku 4.5 | $0.00010 | $0.00086 |
Grade A, and why
vault-stats 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.
How it starts
The opening of the file, as written. The whole thing — 27 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Статистика хранилища и поиск мёртвых заметок
Набор .agents/scripts/vault_stats_*.py считает сигналы «мёртвости» заметки. Запускается по явному запросу («какие заметки бесполезны», «статистика базы»), в рабочем цикле не участвует. Промежуточные файлы кладутся в каталог из VAULT_STATS_OUT (по умолчанию временный). Заметок скрипты не трогают; единственное исключение — calibrate, который перезаписывает .agents/scripts/vault_stats_weights.json, то есть меняет поведение скоринга при следующих прогонах. Флага «только посчитать» у него нет, откат — через git.
python3 .agents/scripts/vault_stats_graph.py # связность, плотность, частота правок, композитный скор
python3 .agents/scripts/vault_stats_lexdup.py # вычитание шаблонного каркаса + текстовые дубли
python3 .agents/scripts/vault_stats_embed.py # эмбеддинги заметок через LM Studio
uv run --with numpy .agents/scripts/vault_stats_semdup.py # семантические дубли и изоляты
uv run --with numpy .agents/scripts/vault_stats_calibrate.py # веса по git-удалениям → weights.json
Порядок обязателен: каждый шаг читает выхлоп предыдущих. embed требует поднятого LM Studio с той же моделью, что в OPENAI_EMBEDDING_MODEL из .mcp.json. calibrate пишет weights.json, который graph подхватывает автоматически при следующем прогоне.
Исключения задаются слоями: встроенные умолчания → OBSIDIAN_IGNORE_PATTERNS из .mcp.json → VAULT_STATS_IGNORE/VAULT_STATS_UNIGNORE → флаги --ignore/--unignore/--no-score. Из патернов MCP по умолчанию вычитаются 04. Архив/** и 05. Дневник/** — поиску они не нужны, статистике нужны. --show-config печатает итог.
Метод, ограничения каждого сигнала и способ калибровки описаны в заметке [[Мёртвая заметка опознаётся пересечением сигналов, а не одним]] и в шапках скриптов. Скор ранжирует список на разбор, а не выносит приговор.
Автоматизация
_Система/scripts/weekly-distillate.sh — headless claude -p, собирает черновик weekly из ежедневных заметок завершившейся недели. Запускается launchd-агентом ru.jtprog.weekly-distillate (пн 08:04), лог — ~/Library/Logs/weekly-distillate.log. _Система/scripts/monthly-distillate.sh — аналогично собирает черновик monthly из weekly-заметок завершившегося месяца; launchd-агент ru.jtprog.monthly-distillate (1-е число, 08:12), лог — ~/Library/Logs/monthly-distillate.log. Руками дёргать не нужно. .agents/scripts/excalidraw_migration.py — разовый миграционный скрипт, в рабочем цикле не участвует.
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.
- 9d ago First seen · 27 lines · 95 tokens per session scan A a40e251bb761
vault-stats is a skill published in the GitHub repository jtprogru/bear-skills (1 stars, last pushed 22d ago), licensed MIT. It adds 95 tokens to every session and 858 once invoked, about $0.0005 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
obsidian-safe-write
A process for clarifying and prioritising software requirements before detailed planning. It identifies the request type, asks six core questions, and can rank work by reach, impact, confidence, effort, and other priority methods.
memory-log
A read-only timeline of changes to an agent's stored memories, including additions, corrections, downgrades, migrations, and rollbacks. It rebuilds the timeline from event records and current memory metadata.
obsidian-doc-structure
A read-only tool for inspecting the structure and properties of Obsidian notes. Obsidian is a note-taking app that stores linked Markdown files, and properties are fields such as status or date.
session-digest
A session-summary tool that records what changed during a coding session in a Markdown file for the next session to read.
librarian
A memory-maintenance role that reviews temporary notes and promotes well-supported facts into longer-term memory files. It also keeps shared knowledge concise and records what changed.
agent-memory
Set up repo-level agent memory: create an agent-memory.md learnings log at the repository root and wire up CLAUDE.md so agents read it when stuck and append durable learnings as they work. Use this whenever the user wants to add, set up, bootstrap, install, enable, or repair "agent memory," a "learnings file," a…