Row-Bot is a local-first desktop AI assistant that combines language models with memory and tools for working across files, repositories, workflows, and communication channels. It is intended for people who want an assistant that can run locally while keeping application data on their machine.
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 siddsachar/row-bot --skill custom_tool_builder_guidegit clone --depth 1 https://github.com/siddsachar/row-botWrote 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/siddsachar/row-bot/custom_tool_builder_guide)<a href="https://agentmods.dev/skills/siddsachar/row-bot/custom_tool_builder_guide"><img src="https://agentmods.dev/badge/skills/siddsachar/row-bot/custom_tool_builder_guide/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/siddsachar/row-bot/custom_tool_builder_guide"><img src="https://agentmods.dev/badge/skills/siddsachar/row-bot/custom_tool_builder_guide.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Excessive Agency · line 28 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 | $0.00018 | $0.00483 |
| Opus 5.5 | $0.00007 | $0.00193 |
| Sonnet 5.5 | $0.00004 | $0.00097 |
| Haiku 4.5 | $0.00002 | $0.00048 |
Grade A, and why
custom_tool_builder_guide 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
Custom Tool Builder Guide
Use custom_tool_builder when the user asks to turn a GitHub repo, local folder, or current project into a reusable Row-Bot Custom Tool.
Default flow:
- Start with
action="start". - For a repo URL, pass
source_url. If the user gave a clone parent, passfields={"clone_parent": "..."}. If no clone parent is known, ask for one. - Show the proposed tool name, warnings, and commands before creating anything.
- Use
action="refine"when the user asks to adjust commands or behavior. - Use
action="test"for a smoke test when requested. - For Python repos with missing dependencies, use
action="setup"to create/reuse the tool folder's.venvand install dependencies there. - Use
action="create"only after the user accepts the draft. - Use
action="enable"for Developer availability andaction="promote"only when the user explicitly wants it available in normal chat/workflows.
Rules:
- Do not ask the user to hand-write
row-bot-custom-tool.jsonor internal config files. - Use
custom_tool_builderfor lifecycle state: clone/import source, draft, refine, create, enable, promote, delete. - Use
custom_tool_builder action="setup"for Python dependency setup. Do not runpip installmanually in Row-Bot's own Python environment. - Shell can help with extra read-only inspection or explicit user-approved command testing when the builder needs more evidence.
- Do not use shell to manually register, enable, promote, delete, or edit Custom Tool metadata.
- Public repo Custom Tools do not have a separate hidden enablement gate. Safety comes from explicit clone destination, command review, test approval/sandboxing, and the separate enable/promote steps.
- Explain that generated commands usually operate on the cloned/local repo files unless a command is clearly network-enabled.
- Removing a Custom Tool should preserve source files unless the user explicitly asks to delete managed files.
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 · 36 lines · 18 tokens per session scan A 203e01781ee4
custom_tool_builder_guide is a skill published in the GitHub repository siddsachar/row-bot (1,674 stars, last pushed today), licensed Apache-2.0. It adds 18 tokens to every session and 483 once invoked, about $0.0001 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 2026-08-30.
Other skills, from other repositories
rich-replies
Shape a reply for Telegram: headings, tables, folds, footnotes, formulas, pictures, slideshows, maps, and buttons (choice, link, copy, mini app) inside the text. Load before a structured answer, a comparison, a report in chat, or whenever you offer the user a choice or a link.
telegram-userbot
A skill for connecting to and working through the owner's personal Telegram account, rather than a Telegram bot. It can read personal chats, search messages, and send messages as the account owner after setup and consent.
rich-post
Send a rich Telegram post to ANOTHER allowlisted chat; not for the current chat reply or plain reports.
update-recovery
Use when an update leaves out owner customizations or they need restoring or merging.
agent-browser
A command-line browser for interactive websites and web apps. It can open pages, inspect clickable elements, fill forms, click buttons, take screenshots, sign in, and read pages whose content is loaded by JavaScript.
watch
A monitoring and briefing workflow that checks unread Telegram messages, email, failed checks, and failed scheduled units, then decides what needs the owner's attention. It can also explain actions such as creating a task, delaying a reminder, ignoring an item, or fixing a failure.