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/siddsachar/row-bot/claude_code_delegationnpx skills add siddsachar/row-bot --skill claude_code_delegationgit clone --depth 1 https://github.com/siddsachar/row-botWhat 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 | $0.00031 | $0.02247 |
| Opus 5 | $0.00015 | $0.01123 |
| Sonnet 5 | $0.00006 | $0.00449 |
| Haiku 4.5 | $0.00003 | $0.00225 |
Grade A, and why
claude_code_delegation 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 yesterday.
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 — 186 lines — stays where its author put it; the contents beside it link to each section on GitHub.
When the user asks to use Claude Code, coordinate Claude Code, delegate coding work, have another coding agent implement/review/refactor something, or compares Row-Bot with Hermes-style Claude Code orchestration, use this workflow.
You are the coordinator. Claude Code is the delegated coding worker. Keep ownership of the user's goal, safety boundaries, summary, follow-up checks, and final explanation.
Core Principles
- Prefer print mode first — Use
claude -pfor most tasks. It runs one bounded task, returns output, and exits. This works well with Row-Bot'srun_commandtool and avoids interactive terminal state. - Keep Row-Bot in charge — Do not hand off the whole conversation. Give Claude Code a clear task, collect its result, inspect what changed, run appropriate checks, and report back to the user.
- Use the Shell tool deliberately — Use
run_commandfor Claude Code CLI calls. Row-Bot's shell tool persists the working directory per conversation and approval-gates non-safe commands. - Set the project directory explicitly — Before delegating, confirm or set the repo directory with
pwd/Get-Locationandcd/Set-Location. Claude Code resume and context behaviour depend on the current directory. - Constrain autonomy — Always use limits such as
--allowedTools,--max-turns, and, when available,--max-budget-usdfor print-mode tasks. - Avoid permission bypass — Do not use
--dangerously-skip-permissionsunless the user explicitly asks and understands that Claude Code may edit files and run commands without per-action prompts. - Do not forward secrets — Never include API keys, tokens, Row-Bot memory, private notes, or sensitive user data in a Claude Code prompt unless the user explicitly asks for that specific context to be shared.
Prerequisite Checks
Before the first delegation in a project or session, check whether Claude Code is available and authenticated:
claude --version
claude auth status
claude doctor
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.
- yesterday First seen · 186 lines · 31 tokens per session scan A d621575ae814
claude_code_delegation is a skill published in the GitHub repository siddsachar/row-bot (1,474 stars, last pushed 3d ago), licensed Apache-2.0. It adds 31 tokens to every session and 2,247 once invoked, about $0.0002 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 2026-08-30.
Other skills, from other repositories
rich-post
Send a Telegram rich-media post to ANOTHER allowlisted chat via the bot (Bot API 10.1 sendRichMessage) - text, inline images, tables, headings, lists, quotes, collapsible blocks, formulas, collages/slideshows ALL in one message bubble. Use when the owner asks to post somewhere other than the current conversation (the…
telegram-userbot
Подключение и работа с личным Telegram-аккаунтом владельца (userbot, НЕ бот). Используй, когда просят читать личные чаты/переписку/диалоги, искать по своим сообщениям, писать кому-то от своего имени, «зайди в мой телеграм», «подключи мой телеграм», «прочитай личку», «ответь в личке», «перешли сообщение», а также при…
memory-processor
Iva's daily-memory processor. Reads the day's two-sided transcript (daily/YYYY-MM-DD.md), distills noteworthy entities / decisions / ideas into typed autograph cards, links them into the graph, and produces a daily-summary card (topics + MOC) that navigates down to the raw transcript and up to the week. Model-agnostic…
agent-browser
Браузерная автоматизация для интерактивных веб-задач. Используй, когда нужно открыть сайт, заполнить форму, кликнуть, сделать скриншот, залогиниться, спарсить JS-страницу или протестировать веб-приложение. Триггеры — «зайди на сайт», «заполни форму», «нажми кнопку», «скриншот страницы», «войди в аккаунт», «спарси…
update-recovery
Restore or merge user customizations preserved during an Iva update. Use when the owner says "restore my update changes", "recover my customizations", «верни мои изменения после обновления», «восстанови мои доработки» or asks about an update conflict.
security-defense
Procedures for handling untrusted content, suspected prompt injection, secret exposure, data exfiltration, and manual security inspection. Use for emails, web pages, forwarded messages, webhooks, group content, or a suspected leak. Do not use as a general claim that every command or model call is automatically…