create-agent

create-agent is a skill for Claude Code, Codex from luanmorenommaciel/agentspec. It costs 154 tokens per session (2,415 once invoked), scanned A, original, MIT.

Repo-specific SOP for adding a new agent to this repository — the frontmatter contract the auto-generated router feeds on (name, description one-liner, tier, model, tools, kbdomains, stop conditions, escalation targets), the thin-executor default, category placement, and the router/build/docs ship checklist. Use when…

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

Made for: Claude Code, Codex.

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 create-agent

README.md
[![agentmods](https://agentmods.dev/badge/skills/luanmorenommaciel/agentspec/create-agent.svg)](https://agentmods.dev/skills/luanmorenommaciel/agentspec/create-agent)
Your own site
<a href="https://agentmods.dev/skills/luanmorenommaciel/agentspec/create-agent"><img src="https://agentmods.dev/badge/skills/luanmorenommaciel/agentspec/create-agent.svg" alt="Measured on agentmods" height="20"></a>
Per session 154 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,415 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 $0.00154 $0.02415
Opus 5 $0.00077 $0.01208
Sonnet 5 $0.00031 $0.00483
Haiku 4.5 $0.00015 $0.00242

Measured 2d ago against content hash 6aaddc24f967, 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.

.claude/skills/create-agent/SKILL.md · 135 lines

How it starts

The opening of the file, as written. The whole thing — 135 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Create an Agent (repo conventions)

Agents are the EXECUTION layer of the component model: identity, tool scope, model tier, stop conditions, escalation — a thin shell around capabilities. The scaffold and tier rules are owned by .claude/agents/_template.md; the layer decision is owned by the component model. This skill carries the repo mechanics between those two: the frontmatter contract as the router reads it, the thin-executor default, and the checklist an agent passes before it ships.

Division of labor

Concern Owner
Is an agent even the right layer? the component-model skill (gate), grounded in .claude/kb/shared/component-model.md
Section structure, tier line budgets, section-by-tier requirements .claude/agents/_template.md (copy it) + .claude/agents/README.md
The methodology the agent executes a skill, authored via create-skill
Frontmatter contract, router coupling, ship checklist this skill

When to use / Skip if

First, run the layer gate. Before writing anything, apply the component-model skill (or read .claude/kb/shared/component-model.md). Most "new agent" asks are actually new skills plus a thin executor: if the request is "teach the system HOW to do X", that is a skill — the agent, if one is needed at all, is only the WHO (identity, tools, boundaries).

Use this skill when:

  • Adding a new specialist agent under .claude/agents/.
  • Splitting an overloaded agent into two roles with distinct tool scopes or KB domains.

Skip if:

  • The capability is methodology or how-to knowledge → create-skill.
  • The content is reference truth (facts, standards, deep dives) → /create-kb.
  • An existing agent already covers most of the capability → extend it instead; apply the four-condition gate in .claude/agents/README.md ("When NOT to Create an Agent" — no existing agent covers >60%, unique KB/tool combination, ≥3 distinct triggers, no >80% overlap).
  • Undecided which layer the logic belongs in → the component-model skill first.

Read the full file on GitHub · 135 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 · 135 lines · 154 tokens per session scan A 6aaddc24f967

Subscribe to this mod's changes

create-agent is a skill published in the GitHub repository luanmorenommaciel/agentspec (244 stars, last pushed 3d ago), licensed MIT. It adds 154 tokens to every session and 2,415 once invoked, about $0.0008 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 2026-09-01.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

brainstorming

You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.

obra/superpowers · 37 tokens

auto-perf-optimize

Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.

microsoft/vscode · 62 tokens

chat-perf

Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.

microsoft/vscode · 51 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens