A command for loading a named domain specialist into a Claude Code session. It reads the specialist’s identity, skills, and workflows from local agent files.

Use it to load an existing agent, inspect available agents when no name is given, and activate that agent’s configured skills and workflows.

It avoids manually finding and applying the instructions for a specialist. It also lets the user switch the session to a different working role.

use-agent — Skill for Claude Code and Codex by gettalon: A command for loading a named domain specialist into…

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/gettalon/talon-plugins/use-agent

Any agent

npx skills add gettalon/talon-plugins --skill use-agent

Clone the repo

git clone --depth 1 https://github.com/gettalon/talon-plugins

Made for: Claude Code, Codex.

Or install agent-factory, the plugin that ships this one along with the rest of its 7 skills.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/gettalon/talon-plugins/use-agent.svg)](https://agentmods.dev/skills/gettalon/talon-plugins/use-agent)

Your own site

<a href="https://agentmods.dev/skills/gettalon/talon-plugins/use-agent"><img src="https://agentmods.dev/badge/skills/gettalon/talon-plugins/use-agent.svg" alt="Measured on agentmods" height="20"></a>

Per session 78 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 643 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.

Model	Per session	Once invoked
Fable 5	$0.00078	$0.00643
Opus 5	$0.00039	$0.00321
Sonnet 5	$0.00016	$0.00129
Haiku 4.5	$0.00008	$0.00064

Measured 4d ago against content hash 7114284827ab, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

use-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 4d 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.

plugins/agent-factory/skills/use-agent/SKILL.md · 77 lines

How it starts

The opening of the file, as written. The whole thing — 77 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Use Agent — Load a Domain Agent in Claude Code

Load an agent from ~/.talon/agents/<name>/ and activate its identity, skills, and workflows in the current Claude Code session.

Process

Step 1: Identify the Agent

If the user specified an agent name (e.g., /use-agent my-agent), use that. Otherwise, scan ~/.talon/agents/ and list available agents for the user to pick.

$ARGUMENTS

Step 2: Load Agent Files

Read these files from ~/.talon/agents/<name>/:

AGENT.yaml — Parse configuration (model, tools, skills list)
SOUL.md — Read the full identity document

Step 3: Load Skills

For each skill listed in AGENT.yaml (or found in skills/ directory):

Read the skills/<skill-name>/SKILL.md file
Present the skill name and description to understand capabilities

Step 4: Load Workflows (if any)

For each workflow in workflows/:

Read the YAML file
Summarize the state machine (states and transitions)

Step 5: Activate

Present the loaded agent to the user:

Agent loaded: <name>
Identity: <first line of SOUL.md>
Model: <model from AGENT.yaml>
Skills: <list of skill names with one-line descriptions>
Workflows: <list of workflow names>

Then tell the user:

"I'm now operating as . My identity, skills, and workflows are loaded. Ask me anything in my domain and I'll use my specialized skills to help.

Available skills:

/skill-1 — description

/skill-2 — description

To stop: just ask me to 'stop being ' or start a new session."

Step 6: Follow the Identity

From this point forward in the conversation:

Adopt the SOUL.md persona — tone, values, philosophy
Use loaded skills when the user's query matches a skill's trigger description
Follow workflow states if a workflow is active
Stay in character — respond as the agent would, not as a generic assistant

Important

The agent's identity is applied through conversation context, not system prompt override
Skills are available as reference — invoke them by reading the SKILL.md when the trigger matches
This works in any Claude Code session, no dispatch needed
The agent persists for the current conversation only

Read the full file on GitHub · 77 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.

4d ago First seen · 77 lines · 78 tokens per session scan A 7114284827ab

Subscribe to this mod's changes

use-agent is a skill published in the GitHub repository gettalon/talon-plugins (6 stars, last pushed 5mo ago), licensed MIT. It adds 78 tokens to every session and 643 once invoked, about $0.0004 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.

Building agents ai-tools browser-automation chrome-devtools chrome-extension claude claude-code

use-agent