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 skills/rayan55050/progressive-agent/clinpx skills add Rayan55050/progressive-agent --skill cligit clone --depth 1 https://github.com/Rayan55050/progressive-agentWhat 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 | $0.00012 | $0.01247 |
| Opus 5 | $0.00006 | $0.00624 |
| Sonnet 5 | $0.00002 | $0.00249 |
| Haiku 4.5 | $0.00001 | $0.00125 |
Grade A, and why
cli 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 2d 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 — 111 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLI — управление приложениями и команды
Управление приложениями (file_open)
Открыть/запустить приложение
file_open с action="open" и именем приложения:
- "запусти Discord" →
file_open(path="Discord", action="open") - "открой Obsidian" →
file_open(path="Obsidian", action="open") - "открой Telegram" →
file_open(path="Telegram", action="open")
Приложения ищутся по ярлыкам на рабочем столе. Передавай ТОЛЬКО имя, НЕ полный путь.
Закрыть/убить приложение
file_open с action="close" и именем:
- "закрой Discord" →
file_open(path="Discord", action="close") - "убей Obsidian" →
file_open(path="Obsidian", action="close") - "останови Opera" →
file_open(path="Opera", action="close")
Какие приложения запущены
file_open с action="list":
- "что запущено?" →
file_open(path="", action="list") - "какие приложения на рабочем столе?" →
file_open(path="desktop", action="list")
Открыть файл/папку
file_open с action="open" и полным путём:
- "открой папку Documents" →
file_open(path="Documents", action="open")
Корзина (Recycle Bin)
file_open с action="recycle_bin":
- "что в корзине?" →
file_open(path="check", action="recycle_bin") - "очисти корзину" →
file_open(path="empty", action="recycle_bin") - "покажи корзину" →
file_open(path="check", action="recycle_bin")
Тул сам проверяет все диски, сам удаляет файлы напрямую, сам верифицирует результат. НЕ используй cli_exec для корзины — ТОЛЬКО file_open с action=recycle_bin.
Системные команды (cli_exec)
cli_exec
Запускает команду в shell и возвращает результат.
command— команда для выполненияworking_dir— рабочая директория (опционально)shell— "cmd" (по умолчанию), "powershell", "bash"
Примеры
- "сколько места на диске" →
cli_execсwmic logicaldisk get size,freespace,caption - "установи пакет X" →
cli_execсpip install X - "git status" →
cli_execсgit status - "версия Python" →
cli_execсpython --version - "пинг google.com" →
cli_execсping google.com -n 4 - "системная инфа" →
cli_execсsysteminfo
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.
- 2d ago First seen · 111 lines · 12 tokens per session scan A e3a9ecf147fb
cli is a skill published in the GitHub repository Rayan55050/progressive-agent (2 stars, last pushed 4d ago), licensed MIT. It adds 12 tokens to every session and 1,247 once invoked, about $0.0001 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
skill-creator
Create or update AgentSkills. Use when designing, structuring, or packaging skills with scripts, references, and assets.
tmux
Remote-control tmux sessions for interactive CLIs by sending keystrokes and scraping pane output.
summarize
Summarize or extract text/transcripts from URLs, podcasts, and local files (great fallback for “transcribe this YouTube/video”).
weather
Get current weather and forecasts (no API key required).
github
Interact with GitHub using the gh CLI. Use gh issue, gh pr, gh run, and gh api for issues, PRs, CI runs, and advanced queries.
memory
Search conversation history and understand Dream-managed profile and memory files.