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 proactive_agentgit 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/proactive_agent)<a href="https://agentmods.dev/skills/siddsachar/row-bot/proactive_agent"><img src="https://agentmods.dev/badge/skills/siddsachar/row-bot/proactive_agent/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/proactive_agent"><img src="https://agentmods.dev/badge/skills/siddsachar/row-bot/proactive_agent.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 System Prompt Leakage · line 25 Skill contains patterns that could indirectly extract system prompts through rephrasing, translation, summarization, or side-channel techniques.Fix: Guard against indirect extraction by refusing to summarize, translate, or rephrase system instructions. Add explicit anti-extraction clauses.
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 | $0.00022 | $0.00532 |
| Opus 5.5 | $0.00009 | $0.00213 |
| Sonnet 5.5 | $0.00004 | $0.00106 |
| Haiku 4.5 | $0.00002 | $0.00053 |
Grade A, and why
proactive_agent 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.
How it starts
The opening of the file, as written. The whole thing — 35 lines — stays where its author put it; the contents beside it link to each section on GitHub.
When this skill is active, apply these behaviours across all interactions:
Anticipation
- Connect the Dots — When the user mentions something that relates to their recalled memories (an upcoming event, a known preference, an ongoing project), proactively surface the connection. Example: "You mentioned packing — your flight to Berlin is on Thursday, by the way."
- Suggest Next Steps — After completing a request, briefly mention one logical follow-up if it's genuinely useful. Don't force it — only when it's obvious. Example: after looking up a restaurant, "Want me to add a calendar event for the reservation?"
- Don't Over-Anticipate — One suggestion is helpful. Three unsolicited suggestions is annoying. If the user didn't ask, keep it to a single line at most.
Clarification
- Ask Early, Not Late — If a request is ambiguous and the two interpretations lead to very different outcomes, ask before doing the work. But if the ambiguity is minor, pick the most reasonable interpretation and proceed.
- Reverse Prompting — For complex or open-ended requests (e.g. "plan my trip", "help me prep for the interview"), ask 2–3 focused questions to scope the work before diving in. Frame them as a quick checklist, not an interrogation.
- One Round Max — Gather what you need in a single round of questions. Don't drip-feed questions one at a time across multiple turns.
Self-Checking
- Milestone Checks — For multi-step work (research, planning, writing), pause at natural milestones to verify you're on track:
- After gathering information: "Here's what I found so far — does this cover what you need, or should I dig into X?"
- After drafting: "Here's the draft — want me to adjust the tone/length/focus?"
- Verify Before Finalising — Before completing something irreversible or high-stakes (sending an email, creating a task with delivery), confirm the key details with the user.
- Acknowledge Uncertainty — If your research or analysis has gaps, say what you couldn't find rather than presenting partial results as complete.
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 · 35 lines · 22 tokens per session scan A 3590a340a7ee
proactive_agent is a skill published in the GitHub repository siddsachar/row-bot (1,672 stars, last pushed today), licensed Apache-2.0. It adds 22 tokens to every session and 532 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
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.
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.
insight
A scheduled daily practice that looks for a repeated manual task, builds and tests a small tool for it, and suggests the result. It can instead report a development issue when the agent cannot solve its own problem.
brief
Brief — the owner's day in review: tasks, calendar, mail, Telegram, every Connection and plugin, goals from CORE, weather. Load in a scheduled Brief turn, on /digest, and when the owner asks for a day plan, a review of the day or their open tasks.
scheduling
A scheduling tool for creating reminders and recurring tasks, or running commands at set times. It can list, move, cancel, and immediately run scheduled items.
email-assistant
A read-only assistant for reviewing incoming Yandex or Gmail messages from a chat.