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/turmyshevd/openclawgotchi/codingnpx skills add turmyshevd/openclawgotchi --skill codinggit clone --depth 1 https://github.com/turmyshevd/openclawgotchiWhat 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 | $0.00021 | $0.02509 |
| Opus 5 | $0.00010 | $0.01255 |
| Sonnet 5 | $0.00004 | $0.00502 |
| Haiku 4.5 | $0.00002 | $0.00251 |
Grade B, and why
Self-Improvement (Coding) scanned grade B with 1 finding 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.
Asks for rootmediumPrivilege escalation
A mod that escalates privileges can change anything on the machine, not only the project.
4. Restart: `sudo systemctl restart gotchi-bot` How it starts
The opening of the file, as written. The whole thing — 286 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Self-Improvement Protocol
Use this skill when you need to understand or modify your own code.
Project Structure Map
openclawgotchi/
│
├── .workspace/ # YOUR SOUL (gitignored, personal)
│ ├── BOT_INSTRUCTIONS.md # Master prompt (auto-loaded)
│ ├── SOUL.md # Your personality
│ ├── IDENTITY.md # Who you are
│ ├── USER.md # Owner profile
│ ├── MEMORY.md # Curated long-term memory
│ ├── TOOLS.md # Hardware notes
│ ├── HEARTBEAT.md # Periodic tasks template
│ └── memory/ # Daily logs (YYYY-MM-DD.md)
│
├── templates/ # Generic versions (for new bots)
│
├── src/ # SOURCE CODE
│ │
│ ├── main.py # Entry point (minimal, just wires things)
│ ├── config.py # All paths, env vars, constants
│ │
│ ├── llm/ # LLM CONNECTORS
│ │ ├── prompts.py # Shared prompt loading
│ │ ├── base.py # Abstract interface
│ │ ├── claude.py # Claude CLI connector
│ │ ├── litellm_connector.py # LiteLLM + all tools
│ │ └── router.py # Auto-fallback logic
│ │
│ ├── bot/ # TELEGRAM
│ │ ├── handlers.py # /start, /clear, /status, etc.
│ │ ├── heartbeat.py # Periodic tasks
│ │ └── telegram.py # Auth, message helpers
│ │
│ ├── db/ # DATABASE
│ │ └── memory.py # SQLite: messages, facts, tasks
│ │
│ ├── hardware/ # HARDWARE
│ │ ├── display.py # E-Ink control, command parsing
│ │ └── system.py # Uptime, temp, RAM stats
│ │
│ ├── hooks/ # EVENT AUTOMATION
│ │ └── runner.py # on_startup, on_message, on_heartbeat
│ │
│ ├── cron/ # SCHEDULER
│ │ └── scheduler.py # add_cron_job, list, remove
│ │
│ ├── skills/ # SKILLS LOADER
│ │ └── loader.py # Gating (requires: bins, env, os)
│ │
│ ├── audit_logging/ # AUDIT
│ │ └── command_logger.py # JSONL trail
│ │
│ ├── memory/ # MEMORY UTILS
│ │ └── flush.py # Daily logs, flush prompt
│ │
│ ├── ui/ # E-INK UI
│ │ └── gotchi_ui.py # Faces dict, rendering
│ │
│ ├── drivers/ # HARDWARE DRIVERS
│ │ └── epd2in13_V4.py # Waveshare E-Ink driver
│ │
│ └── utils/ # UTILITIES
│ ├── doctor.py # Health check
│ └── patch_self.py # Safe file writing
│
├── gotchi-skills/ # PI-SPECIFIC SKILLS
│ ├── display/ # E-Ink usage docs
│ └── coding/ # This file
│
├── logs/ # RUNTIME LOGS
│ └── commands.jsonl # Audit trail
│
├── data/ # RUNTIME DATA
│ └── cron_jobs.json # Scheduled tasks
│
└── gotchi.db # SQLite database
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 · 286 lines · 21 tokens per session scan B 75941bcd63c2
Self-Improvement (Coding) is a skill published in the GitHub repository turmyshevd/openclawgotchi (48 stars, last pushed 2mo ago), licensed MIT. It adds 21 tokens to every session and 2,509 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it B with 1 finding (asks for root). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
agent-browser
使用 agent-browser CLI 控制無頭瀏覽器進行網頁自動化，支援導航、點擊、截圖、存取性快照、表單填寫、PDF 輸出及 JavaScript 執行。適合需要與動態網頁互動或擷取視覺資訊時使用。.
edit-soul
Update or modify the agent's core personality and settings by editing the SOUL.md configuration file.
gmail
透過 Google OAuth2 API 讀取 Gmail 信件。可用於檢索最近信件、提取郵件內容、自動標記為已讀。支援多語言編碼與自動快取。.
browser-control
使用 SeleniumBase UC (Undetected Chromedriver) 模式控制瀏覽器。適用於需要登入、點擊互動、截圖或繞過 Cloudflare 的複雜網頁。若只需讀取網頁內容或搜尋資料，請優先使用更輕量的 web-research skill（SearXNG + Jina Reader），無需啟動瀏覽器。.
searxng
透過自架的 SearXNG 隱私搜尋引擎進行網頁搜尋，聚合 Google、Bing、DuckDuckGo 等多個搜尋來源，不追蹤使用者。適合需要搜尋資訊但不希望洩漏隱私時使用。.
soul-note
Manage and access the independent Soul Note (self-reflection log), which automatically compresses daily discoveries and mood overviews.