create-agent

A command for creating a new AgenticMail software agent with a name and role. The new agent can then be reached and used in work coordinated through email.

In plain words
What is it for?
Use it to create a developer, designer, reviewer, or other specialised agent, confirm that it can be reached, and prepare it for solo or team tasks.
Why use it?
It removes the manual setup involved in adding a teammate to an agent-based workflow. Giving the agent a clear role makes its intended responsibility explicit.

Skill for Claude CodeCodex

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 skills/agenticmail/agenticmail/create-agent
Any agent
npx skills add agenticmail/agenticmail --skill create-agent
Clone the repo
git clone --depth 1 https://github.com/agenticmail/agenticmail

Made for: Claude Code, Codex.

Per session 21 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 272 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 $0.00021 $0.00272
Opus 5 $0.00010 $0.00136
Sonnet 5 $0.00004 $0.00054
Haiku 4.5 $0.00002 $0.00027

Measured 2d ago against content hash f0441f584c49, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

create-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.

plugin/skills/create-agent/SKILL.md · 23 lines

What it actually says

/agenticmail-create-agent

Create a fresh AgenticMail agent and confirm it is reachable. Use this when the user wants to spin up a teammate for a multi-agent task.

The user's arguments are: $ARGUMENTS

Steps

  1. Parse the first argument as the agent name. Parse the second (optional) argument as the role. If the role is not given, default to assistant.
  2. Call mcp__agenticmail__create_account with the name and role.
  3. Confirm the result by printing the new agent's email address and a one-line summary of what they can do.
  4. Suggest the next step. If the user is setting up a coordination task, tell them to send one kickoff email with all teammates on CC. If they wanted a solo agent, tell them how to address mail to <name>@localhost.

Notes

The dispatcher will pick up the new agent within milliseconds via the system-events push, so the agent is wake-able immediately. No restart needed for fresh agents.

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 · 23 lines · 21 tokens per session scan A f0441f584c49

Subscribe to this mod's changes

create-agent is a skill published in the GitHub repository agenticmail/agenticmail (212 stars, last pushed 20d ago), licensed MIT. It adds 21 tokens to every session and 272 once invoked, about $0.0001 per session on Opus 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.