agent-create

A command for creating a project-specific AI agent, either by copying a template or drafting one from scratch. It can also start that agent with a question.

In plain words
What is it for?
Use it to add consultant agents to a project's `.claude/agents/` directory, define their role and responsibilities, and ask them to investigate a specific question.
Why use it?
It avoids manually writing agent files and registering them. It also handles conflicts when an agent with the same name already exists.

Command

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 commands/trustmybot/plugin/agent-create
Clone the repo
git clone --depth 1 https://github.com/trustmybot/plugin
Per session 30 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 610 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 $0.00030 $0.00610
Opus 5 $0.00015 $0.00305
Sonnet 5 $0.00006 $0.00122
Haiku 4.5 $0.00003 $0.00061

Measured yesterday against content hash 2d3cf5336d53, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

agent-create 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.

commands/agent-create.md · 42 lines

How it starts

The opening of the file, as written. The whole thing — 42 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/tmb:agent-create <name> [question]

User-created agents default to kind='consultant'.

Resolution

agent_resolve(agent='bro', name=<name>) returns the mode — collision, template-copy, or from-scratch — which decides the path below. Whichever path writes the file at <project>/.claude/agents/<name>.md, follow it with agent_register to record the new project-local consultant.

Collision dialog

When .claude/agents/<name>.md already exists, read the tmb_owner field:

  • tmb_owner: bro or tmb_owner: user-adopted → show unified diff, ask yes/no.
  • No tmb_owner (user-authored) → AskUserQuestion with options: Skip (Recommended), Adopt + manage (insert tmb_owner: user-adopted), or Overwrite (tmb_owner: bro).

Template-copy

Show the template, ask for confirmation (interactive), then write verbatim. If a follow-on question was provided, scope an issue and spawn via Agent.

From-scratch

Gather the shape in one AskUserQuestion batch (up to 3 questions): role/title, core responsibilities, and the closest existing agent plus its gap. Read the top-level project files for stack context, then draft from ${CLAUDE_PLUGIN_ROOT}/templates/agents/template.md — body cap 15 lines after frontmatter. Run the pre-write lint (${CLAUDE_PLUGIN_ROOT}/scripts/prompt-author-lint.sh <draft-path>) and surface its findings via AUQ. Show the full draft, and on approval write it with tmb_owner: bro in frontmatter.

Edge case — code-writing consultant

If the user wants a consultant that writes source code, warn:

This agent will write source code. The plugin's swe role already exists for that. Are you sure you want a parallel code-writing consultant? It will need isolation: worktree and Write/Edit tools, which means it bypasses bro's task-spec gating.

If they confirm, add isolation: worktree to frontmatter and Write, Edit to tools.

Read the full file on GitHub · 42 lines

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. yesterday First seen · 42 lines · 30 tokens per session scan A 2d3cf5336d53

Subscribe to this mod's changes

agent-create is a command published in the GitHub repository trustmybot/plugin (6 stars, last pushed 2d ago), licensed MIT. It adds 30 tokens to every session and 610 once invoked, about $0.0002 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 2026-08-31.