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 workflow_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/workflow_guide)<a href="https://agentmods.dev/skills/siddsachar/row-bot/workflow_guide"><img src="https://agentmods.dev/badge/skills/siddsachar/row-bot/workflow_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/workflow_guide"><img src="https://agentmods.dev/badge/skills/siddsachar/row-bot/workflow_guide.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 | $0.00025 | $0.00432 |
| Opus 5.5 | $0.00010 | $0.00173 |
| Sonnet 5.5 | $0.00005 | $0.00086 |
| Haiku 4.5 | $0.00003 | $0.00043 |
Grade A, and why
workflow_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 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.
What it actually says
A WORKFLOW IS A SCHEDULED CHAT (task_create / task_update):
- Each run sends the workflow's messages (
prompts, usually one) as chat turns in the workflow's own conversation, so a run sees what earlier runs did there. Keep a running record in that conversation, not in files, when the work needs one (posts made, people contacted). - A run has every tool a chat has, found with tool search. Its approval level decides what it may do: block (reads only), approve (each action asks the person), auto (a reviewer approves what matches the workflow, else the person). Hands-off is the person's choice alone.
- Say branching in words: "If nothing is new since the last run, stop and say so." Don't build a ready/not-ready flag for another step to read.
- Don't ask for approval in the message. A post, email or other action asks on its own card, showing the exact account, recipient and full text; nothing asks when there is nothing to do.
- To tell the person something, write it in the reply: it goes where the workflow sends results. Email is sent with the email tool, like any action.
- To run another workflow after this one, set it to start when this one finishes (in its settings).
CHECKING A RUN: task_list(include_history=true) gives each run's status, its outcome in words and the actions it took (with links). "completed" means the turn finished, not that anything was posted or sent: read the actions.
MONITORING ('check X and tell me when Y', 'alert me if W changes'):
- schedule='interval_minutes:M' and a message that ends the workflow with task_update(task_id='{{task_id}}', enabled=false) once done.
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 Changed · -1 lines · -3 tokens per session f74951fd98c4
- 3d ago First seen · 33 lines · 28 tokens per session scan A 48ab7478a19f
workflow_guide is a skill published in the GitHub repository siddsachar/row-bot (1,673 stars, last pushed today), licensed Apache-2.0. It adds 25 tokens to every session and 432 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 2026-10-25.
Other skills, from other repositories
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.
goal
A repeating goal tracker for waiting on an observable result and checking again until it happens. It records the result, next check, sources, and approved actions, with reminders for scheduled checks.
goal-check
A helper's scheduled goal check. Load when the request names Goal check g-…, Allowed and Plan, and asks for a goal verdict.
add-linear
Add Linear channel integration via Chat SDK. Issue comment threads as conversations.
add-github
Add GitHub channel integration via Chat SDK. PR and issue comment threads as conversations.
sn-team-harness
Use when a user asks what SenseNova Team Harness is, wants an introduction or overview, is getting started, or is deciding whether it fits — a self-hosted workspace where people and local AI agents collaborate on conversations, projects, work items, and artifacts. Covers its core concepts (Workspace, Project…