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 AlekseiUL/openclaw-superagent --skill agent-doctorgit clone --depth 1 https://github.com/AlekseiUL/openclaw-superagentWrote 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/alekseiul/openclaw-superagent/agent-doctor)<a href="https://agentmods.dev/skills/alekseiul/openclaw-superagent/agent-doctor"><img src="https://agentmods.dev/badge/skills/alekseiul/openclaw-superagent/agent-doctor/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/alekseiul/openclaw-superagent/agent-doctor"><img src="https://agentmods.dev/badge/skills/alekseiul/openclaw-superagent/agent-doctor.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 | $0.00041 | $0.03632 |
| Opus 5 | $0.00020 | $0.01816 |
| Sonnet 5 | $0.00008 | $0.00726 |
| Haiku 4.5 | $0.00004 | $0.00363 |
Grade C, and why
agent-doctor scanned grade C 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 10d 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.
Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
rm -rf ~/.openclaw/logs/*.log.old How it starts
The opening of the file, as written. The whole thing — 534 lines — stays where its author put it; the contents beside it link to each section on GitHub.
🏥 Agent Doctor - Самодиагностика OpenClaw
Версия: 1.0.0 (Public Release) Создано: 2026-03-06 Лицензия: MIT
Описание
Комплексная диагностика всех систем OpenClaw агента. Проверяет память, кроны, конфиг, файлы, gateway, систему и безопасность. Выявляет проблемы и предлагает конкретные решения.
ВАЖНО: Скилл ТОЛЬКО диагностирует. Изменения применяются ТОЛЬКО после вашего явного подтверждения.
Установка
- Скопируйте этот файл в
skills/agent-doctor/SKILL.md - Агент автоматически подхватит скилл при следующем запуске
Триггеры
Когда говорить агенту для запуска:
- "продиагностируй себя"
- "самодиагностика"
- "проверь систему"
- "что с тобой не так"
- "диагностика агента"
- "self-check"
- "health check"
Как работает
Алгоритм
- Агент запускает проверку всех систем
- Собирает результаты по 7 категориям
- Формирует отчет с найденными проблемами
- Предлагает конкретные решения
- Применяет фиксы ТОЛЬКО после вашего "ок"
Что проверяется
🧠 Память
-
SQLite база данных
- Существует ли ~/.openclaw/memory/*.sqlite?
- Размер базы адекватный?
-
WAL mode (критично!)
- Проверка:
sqlite3 ~/.openclaw/memory/main.sqlite "PRAGMA journal_mode;" - Должно быть:
wal(НЕdelete!) - Почему важно: без WAL агент видит устаревшие данные
- Проверка:
-
Количество записей
- Сколько чанков в базе?
- Есть ли записи из файлов (memory) и сессий (sessions)?
-
Конфиг memorySearch
- enabled = true?
- embeddingProvider настроен?
- similarityThreshold указан?
-
Embedding провайдер
- OpenAI / Gemini / Anthropic
- API ключ настроен?
-
Тестовый поиск
- memory_search возвращает результаты?
- Нет ошибок при запросе?
-
Файлы памяти
- MEMORY.md существует и не пустой?
- Структура папок: core/, decisions/, projects/
- Последний daily note (memory/YYYY-MM-DD.md) свежий?
⏰ Кроны
-
Список всех кронов
- Команда:
openclaw cron list
- Команда:
-
Статус кронов
- Есть ли отключенные (enabled: false)?
- Когда последний запуск?
What ships with it
6 files 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.
- 10d ago First seen · 534 lines · 41 tokens per session scan C cfd5ea8026a1
agent-doctor is a skill published in the GitHub repository AlekseiUL/openclaw-superagent (41 stars, last pushed 3mo ago), licensed MIT. It adds 41 tokens to every session and 3,632 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it C with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
incident-brief-generator
Builds a concise incident handoff from symptoms, health evidence, and logs.
autofix-readiness-review
Use this bundled starter skill to inspect self-healing actions before any repair is executed.
repo-health-check
Reviews the current repository or workspace and answers two questions quickly.
system-health-snapshot
Use this bundled starter skill to read Friday's current runtime snapshot and summarize.
review-open-issues
Use this bundled starter skill to inspect what Friday already knows about open incidents.
local-service-diagnose
Checks a process, port, health URL, and recent logs, then explains.