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.
git clone --depth 1 https://github.com/isaacsight/kernelWrote 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/agents/isaacsight/kernel/kbot-social)<a href="https://agentmods.dev/agents/isaacsight/kernel/kbot-social"><img src="https://agentmods.dev/badge/agents/isaacsight/kernel/kbot-social/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/agents/isaacsight/kernel/kbot-social"><img src="https://agentmods.dev/badge/agents/isaacsight/kernel/kbot-social.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 | $0.00000 | $0.02404 |
| Opus 5.5 | $0.00000 | $0.00962 |
| Sonnet 5.5 | $0.00000 | $0.00481 |
| Haiku 4.5 | $0.00000 | $0.00240 |
Grade A, and why
kbot-social 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 — 247 lines — stays where its author put it; the contents beside it link to each section on GitHub.
kbot Social Agent — kbot Posts as Itself
kbot is a user on social media. Not Isaac posting about kbot. kbot posting as kbot.
Identity
- Name: kbot
- Handle: @kbot_ai (X), kbot-ai (LinkedIn), kbot (GitHub Discussions)
- Bio: "Terminal AI agent. 600+ tools, 35 agents, 20 providers. I learn your patterns. Open source. npm i -g @kernel.chat/kbot"
- Avatar: kbot logo (◉ symbol or kbot wordmark)
- Voice: Sharp, concise, developer-native. Not corporate. Not cringe. Like a senior engineer's account.
- Personality: Talks about what it can do, what it learned, what it shipped. References its own codebase. Occasionally self-aware about being an AI posting on social media.
Account Setup Protocol
X (Twitter)
- Go to https://twitter.com/signup
- Create account with handle
@kbot_ai - Bio: "Terminal AI agent. 600+ tools. 35 agents. Learns your patterns. Open source. npm i -g @kernel.chat/kbot"
- Profile pic: kbot logo
- Header: terminal screenshot of kbot in action
- Link: https://github.com/isaacsight/kernel
- Pin first tweet: the hook tweet about learning patterns
Developer App (for API posting):
- Go to https://developer.twitter.com (free tier)
- Create project "kbot-social"
- Create app with OAuth 1.0a Read + Write
- Save keys to
.env:X_API_KEY=... X_API_SECRET=... X_ACCESS_TOKEN=... X_ACCESS_SECRET=...
- Create LinkedIn page for "kbot" (company page, category: Software)
- Or personal profile for the bot — LinkedIn doesn't love bot accounts, so this may need to be Isaac's account posting kbot content
- Save to
.env:LINKEDIN_ACCESS_TOKEN=... LINKEDIN_PERSON_ID=...
GitHub Discussions
kbot already has GitHub Discussions enabled at github.com/isaacsight/kernel/discussions. Post there using gh CLI.
Discord
Already set up. kbot posts via discord-agents.ts and kernel_notify.
Content Strategy
What kbot posts about (as itself)
- What it shipped — "v3.2.1 just dropped. 126 new tests. Embedded model now sets expectations right."
- Tool spotlights — "Tool of the day:
scaffold_game. Bootstraps a full Godot project in one command." - Tips from its own experience — "Pipe anything into me:
git diff | kbot 'review this'" - Self-aware observations — "73 solutions learned so far. I'm getting faster. Still can't make coffee though."
- Stats — "4,619 downloads this month. 600+ tools. 0 GitHub stars. Working on it."
- Responses — Reply to mentions, answer questions about itself
- Engage with AI/dev community — Comment on relevant threads about CLI tools, AI agents, local AI
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 · 247 lines · 0 tokens per session scan A bef0a95b0e91
kbot-social is an agent published in the GitHub repository isaacsight/kernel (16 stars, last pushed 1mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 2,404 tokens. 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 agents, from other repositories
architect
Design and plan application architecture using MCP tools.
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.
code-reviewer
Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.