new-agent

new-agent is a skill for Claude Code from AcKeskin/contexture. It costs 75 tokens per session (4,928 once invoked), scanned A, original, MIT.

An interview-led scaffold for creating a Claude Code subagent, which is a specialist helper agent for a specific job.

In plain words
What is it for?
It helps define a subagent’s job, pre-flight questions, anti-patterns, and troubleshooting workflow before creating its file.
Why use it?
It prevents new agents from becoming vague personas with no guidance for questions, common mistakes, or debugging.

Skill for Claude Code

Written for Claude Code: SessionStart hook event. Also seen: reads .claude/ paths; mentions subagents; names the AskUserQuestion tool.

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/ackeskin/contexture/new-agent
Any agent
npx skills add AcKeskin/contexture --skill new-agent
Clone the repo
git clone --depth 1 https://github.com/AcKeskin/contexture

Made for: Claude Code.

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.

agentmods badge for new-agent

README.md
[![agentmods](https://agentmods.dev/badge/skills/ackeskin/contexture/new-agent.svg)](https://agentmods.dev/skills/ackeskin/contexture/new-agent)
Your own site
<a href="https://agentmods.dev/skills/ackeskin/contexture/new-agent"><img src="https://agentmods.dev/badge/skills/ackeskin/contexture/new-agent.svg" alt="Measured on agentmods" height="20"></a>
Per session 75 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 4,928 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 5.1 $0.00075 $0.04928
Opus 5 $0.00037 $0.02464
Sonnet 5 $0.00015 $0.00986
Haiku 4.5 $0.00007 $0.00493

Measured 2d ago against content hash 71abab53ab10, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

new-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.

skills/new-agent/SKILL.md · 387 lines

How it starts

The opening of the file, as written. The whole thing — 387 lines — stays where its author put it; the contents beside it link to each section on GitHub.

new-agent

The subagent scaffold organ. Closes the gap that the existing *-pro.md files in agents/ are persona stubs — concise but topic-list shaped, easy to copy thinly. This skill turns the act of "write a new agent" into an interview that surfaces the operational knowledge a new agent file should carry: the questions the agent must ask before writing code, the landmines it must avoid, and the triage order it follows when output is wrong.

When to run

  • User types /new-agent (explicit trigger).
  • User says "scaffold a new subagent," "I want a new agent for X," "add a *-pro agent."
  • Do not auto-fire. No session-start or event-hook triggers. Mode A only — every run goes through the full interview.

Inputs

  1. Triggering message. Anything after /new-agent is hint text — used to pre-fill a suggested answer for the relevant interview question, never to skip the question.
  2. Existing agents tree. agents/ (in this project root) and ~/.claude/agents/ — used for the collision check on the chosen name and to surface the existing *-pro.md files as anchors so the new file matches house style.
  3. No settings.json edit. Subagents are auto-discovered by Claude Code from ~/.claude/agents/. The bootstrap symlinks agents/~/.claude/agents/. This skill only writes one file.

Why this skill exists

The existing pattern (cpp-pro.md, c-sharp-pro.md, etc.) gives you four sections — Focus Areas, Approach, Output, plus a one-line opening — and that is enough for broad-stroke language experts. It is not enough for a domain agent (e.g. "video frame source for Metal," "Postgres logical-replication debugging," "Unity URP shader graph"). A domain agent needs:

  • The specific questions it must ask before writing code, because the wrong default cascades.
  • The landmines the user already discovered, written down so the agent will not re-discover them.
  • The debugging order for when its output looks plausible but wrong.

A free-form "describe an agent" prompt produces topic lists. A structured interview produces operational knowledge. This skill is the structured interview.

Read the full file on GitHub · 387 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. 2d ago First seen · 387 lines · 75 tokens per session scan A 71abab53ab10

Subscribe to this mod's changes

new-agent is a skill published in the GitHub repository AcKeskin/contexture (2 stars, last pushed 1mo ago), licensed MIT. It adds 75 tokens to every session and 4,928 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 2026-09-03.