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 agentmods add instructions/jtprogru/bear-skills/agents-mdgit 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/instructions/jtprogru/bear-skills/agents-md)<a href="https://agentmods.dev/instructions/jtprogru/bear-skills/agents-md"><img src="https://agentmods.dev/badge/instructions/jtprogru/bear-skills/agents-md.svg" alt="Measured on agentmods" 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 | $0.02918 | $0.02918 |
| Opus 5 | $0.01459 | $0.01459 |
| Sonnet 5 | $0.00584 | $0.00584 |
| Haiku 4.5 | $0.00292 | $0.00292 |
Grade A, and why
bear-skills AGENTS.md 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 5d 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 — 210 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Этот файл — точка входа для любого AI-агента, который работает со скиллами bear-skills. Прочитай его целиком до первого действия.
Что такое bear-skills
Это мульти-доменная коллекция правил, скиллов и агентов для Claude Code. Каждый домен — самодостаточная вертикаль (Obsidian PKB, Git workflow, SRE/Kubernetes, контент). Структура единая, контракт работы общий.
Архитектура
bear-skills/
└── domains/
├── <domain-name>/
│ ├── manifest.yaml ← name, description, requires_env, targets
│ ├── rules/ ← долговечные правила домена
│ ├── skills/ ← атомарные операции
│ └── agents/ ← оркестраторы
└── ...
Каждый домен в domains/<name>/ имеет свой manifest.yaml, который объявляет:
name,description— что это за доменrequires_env— переменные окружения, без которых домен не разворачивается (например,BEAR_VAULTдля obsidian)targets— куда уезжают rules/skills/agents послеinstall
Зависимости — только сверху вниз: агент знает про скилл, скилл знает про правило. Обратное не допускается.
Текущие домены
| Домен | requires_env | Что делает |
|---|---|---|
obsidian |
BEAR_VAULT |
PKB на Obsidian по PARA — ингест, разбор inbox, untangle hub, ежедневник |
git |
— | Git workflow — Conventional Commits, PR-описания, semver-релизы |
sre |
— | SRE — incident postmortem, runbook authoring, Kubernetes triage |
content |
— | Контент — Telegram-посты, статьи, технические туториалы |
Детали — в domains/<name>/manifest.yaml и в файлах внутри.
Куда что разворачивается
После bear-skills install:
obsidianrules →$BEAR_VAULT/.agents/rules/(vault-local, скиллы ссылаются как.agents/rules/<file>.md)git,sre,contentrules →~/.claude/rules/(глобально, скиллы ссылаются как~/.claude/rules/<file>.md)- все skills →
~/.claude/skills/ - все agents →
~/.claude/agents/
Если у домена не выполнен requires_env — он скипается с warning, остальные ставятся. То же с requires_bin: объявленный на уровне домена бинарь пропускает домен целиком, объявленный под конкретные компоненты — только их. Скиллы srekit* без CLI srekit в PATH не устанавливаются, остальной SRE-домен ставится.
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.
- 5d ago First seen · 210 lines · 2,918 tokens per session scan A 163955aa9fee
bear-skills AGENTS.md is an instructions file published in the GitHub repository jtprogru/bear-skills (1 stars, last pushed 18d ago), licensed MIT. It adds 2,918 tokens to every session, about $0.0146 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 instructions, from other repositories
notfair-plugin AGENTS.md
AGENTS.md instructions for nowork-studio/notfair-plugin, covering notfair — skill resolver for ai agents, how to use this file, seo, paid ads and analytics.
sage CLAUDE.md
Instructions for gendigitalinc/sage, covering claude.md, project, commands, repository structure and test tiers.
codebay CLAUDE.md
Claude Code instructions for khromov/codebay, covering claude.md, what this is, runtime & commands, comments and architecture.
ai-tc AGENTS.md
AGENTS.md instructions for akasecurity/ai-tc: The conventions live in CLAUDE.md. Read that first, every session.
claudex-setup CLAUDE.md
Claude Code instructions for runnithan/claudex-setup, covering claudex-setup, architecture, project structure, workflow and key conventions.
octowiz AGENTS.md
Instructions for raelli/octowiz, covering agent skills, issue tracker, triage labels, domain docs and path validation (dual-validator pattern).