Borrowing it
Nothing to install: this file belongs to radif-ru/ai-multi-agent-system. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/radif-ru/ai-multi-agent-system/main/.agents/skills/error-handling-discipline/SKILL.mdgit clone --depth 1 https://github.com/radif-ru/ai-multi-agent-systemWrote 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/radif-ru/ai-multi-agent-system/error-handling-discipline)<a href="https://agentmods.dev/skills/radif-ru/ai-multi-agent-system/error-handling-discipline"><img src="https://agentmods.dev/badge/skills/radif-ru/ai-multi-agent-system/error-handling-discipline/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/radif-ru/ai-multi-agent-system/error-handling-discipline"><img src="https://agentmods.dev/badge/skills/radif-ru/ai-multi-agent-system/error-handling-discipline.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 | $0.00047 | $0.00559 |
| Opus 5.5 | $0.00019 | $0.00224 |
| Sonnet 5.5 | $0.00009 | $0.00112 |
| Haiku 4.5 | $0.00005 | $0.00056 |
Grade A, and why
error-handling-discipline 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 1mo 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.
What it actually says
Skill: error-handling-discipline
Правила обработки ошибок. Источник истины — _docs/instructions.md §5 и §6, _docs/architecture.md §2.
Когда использовать
- Пишешь или меняешь handler, tool, агентный цикл или сервис с внешним I/O.
- Добавляешь новый класс ошибок или новую внешнюю интеграцию.
- Формируешь сообщение пользователю при сбое.
Алгоритм
- Нет необработанных исключений (NFR-3). Каждый handler / tool / агентный цикл либо сам ловит ожидаемые (
LLMError,ToolError,asyncio.TimeoutError), либо полагается на глобальный error handler в Dispatcher. - Переиспользуй существующие иерархии, не плоди новые в обход:
app/services/llm.py:LLMError → LLMTimeout / LLMUnavailable / LLMBadResponse.app/tools/errors.py:ToolError → ToolNotFound / ArgsValidationError.
- Пользователю — человеческое сообщение, без stacktrace и внутренних деталей. Текст — по §1 (русский).
- Stacktrace — только в лог:
logger.exception(...)илиlogger.error(..., exc_info=True). Чувствительные данные в лог не пишем (§6). - Отказоустойчивость по слоям. Таймаут LLM, сетевой сбой, недоступность Ollama, битый JSON, упавший tool, превышение лимита шагов — каждый ловится и превращается в понятное сообщение + запись в лог (
_docs/architecture.md§2). - Деградация, а не падение. Где это предусмотрено (авто-подгрузка архива,
Planner/Critic) —WARNINGи продолжение с последним доступным результатом, а не исключение наружу.
Чего избегать
- Голого
except Exception: passи проглоченных ошибок без лога. - Stacktrace и внутренних путей в сообщении пользователю (см.
prompt-injection-defense). - Новых ad-hoc классов ошибок вместо существующих иерархий.
- Необработанного I/O, способного уронить агентный цикл.
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.
- 1mo ago First seen · 33 lines · 47 tokens per session scan A 0498a058ee7f
error-handling-discipline is a skill published in the GitHub repository radif-ru/ai-multi-agent-system (6 stars, last pushed 21d ago), licensed MIT. It adds 47 tokens to every session and 559 once invoked, about $0.0002 per session on Opus 5.5. 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
self-map
Your evidence and how you work: one Trace turn to its cause and whose it is (owner side, the Version, outside); spend, schedules, failures, the journal, docs; what Stop, Interrupt or a break leave; where to look before asking. Load in an Insight turn with failures, when the owner asks what you did, why it failed, what…
ripple
Analyzing pre-change impact across vertical (dependency chains, files) and horizontal (pattern consistency, naming) dimensions. Use to estimate blast radius before a refactor. No code.
sweep
Detecting unnecessary files, unused code, and orphaned files, and proposing safe deletion. Not for removal execution (Builder), repo structure (Grove), or scope cutting (Void).
code-review
Performs structured code review on a file or directory.
report-problem
A troubleshooting procedure for a broken Iva assistant, schedule, tool, or delivery. It collects a diagnostic report, checks recent logs and facts, and prepares either an issue report or a support-chat message.