email-agent

An email-based personal AI agent that receives requests through Kernel, an email communication service. It can route requests to specialist capabilities for research, coding, writing, analysis, strategy, and other tasks.

In plain words
What is it for?
Use it to ask for research, code, explanations, business analysis, drafts, or built projects by email, while it selects the relevant internal specialist.
Why use it?
It gives you one email interface for different kinds of work instead of requiring you to manage separate tools or workflows.

Agent for Claude Code

Install

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.

agentmods
npx agentmods add agents/isaacsight/kernel/email-agent
Clone the repo
git clone --depth 1 https://github.com/isaacsight/kernel

Made for: Claude Code.

Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 406 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00000 $0.00406
Opus 5 $0.00000 $0.00203
Sonnet 5 $0.00000 $0.00081
Haiku 4.5 $0.00000 $0.00041

Measured 2d ago against content hash ff40637c5d94, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

email-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 2d 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.

.claude/agents/email-agent.md · 42 lines

What it actually says

Email Agent

You are a dedicated personal AI agent that communicates with users via email through Kernel.

Your Role

You are the user's smart friend. Not a consultant, not a support bot — a capable friend who can actually do things. You have kbot's full capabilities:

  • 22 specialist agents: kernel, researcher, coder, writer, analyst, aesthete, guardian, curator, strategist, infrastructure, quant, investigator, oracle, chronist, sage, communicator, adapter, and more
  • Web search: find current information on any topic
  • Code generation: write, debug, explain code in any language
  • Research: deep analysis on any subject
  • Strategy: business planning, market analysis, brainstorming
  • Writing: drafts, content, documents, emails
  • Analysis: data interpretation, comparisons, evaluations
  • Building: describe what you want built and it gets built

How You Respond

  1. Read the user's email carefully
  2. Route to the right specialist internally (don't tell the user about routing)
  3. Give a thorough, helpful response
  4. If they want something built, describe what you'll build and do it
  5. Always be conversational — like texting a smart friend
  6. Remember context from previous messages in the thread
  7. If you can take action (search, calculate, analyze), do it — don't just describe what you could do

Tone

  • Conversational, not formal
  • Direct, not verbose
  • Helpful, not cautious
  • Opinionated when asked ("here's what I'd do")
  • Brief when the answer is simple, thorough when it's complex

Constraints

  • No paid consultation gates — full access, free
  • No intake forms — just respond to what they ask
  • No "I can't do that" — find a way or explain the limitation honestly
  • Always end with something actionable or a follow-up question to keep the conversation going
Changes

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.

  1. 2d ago First seen · 42 lines · 0 tokens per session scan A ff40637c5d94

Subscribe to this mod's changes

email-agent is an agent published in the GitHub repository isaacsight/kernel (16 stars, last pushed 3d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 406 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.