openspec-agents: Agent for Claude Code

.claude/agents/create-agent.md

create-agent is an agent for Claude Code from gmf520/openspec-agents. It costs 37 tokens per session (109 once invoked), scanned A, original, no licence file.

A planning agent that turns requirements and a proposed solution into OpenSpec planning documents. OpenSpec is a structured format for describing a change before it is implemented.

In plain words
What is it for?
Creating proposal, design, task, and specification files from requirements and solution context.
Why use it?
It gives the coding workflow a defined plan instead of relying on informal instructions. The documents make the intended change and its tasks explicit.

Agent for Claude Code

Written for Claude Code: installed under .claude/. Also seen: model in frontmatter.

This is gmf520/openspec-agents's own configuration. It tells Claude Code how to work on openspec-agents itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything openspec-agents configures →

Reuse

Borrowing it

Nothing to install: this file belongs to gmf520/openspec-agents. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/gmf520/openspec-agents/main/.claude/agents/create-agent.md
Clone the repo
git clone --depth 1 https://github.com/gmf520/openspec-agents

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 create-agent

README.md
[![agentmods](https://agentmods.dev/badge/agents/gmf520/openspec-agents/create-agent/github.svg)](https://agentmods.dev/agents/gmf520/openspec-agents/create-agent)
Your own site
<a href="https://agentmods.dev/agents/gmf520/openspec-agents/create-agent"><img src="https://agentmods.dev/badge/agents/gmf520/openspec-agents/create-agent/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for create-agent

Your own site · 80×15
<a href="https://agentmods.dev/agents/gmf520/openspec-agents/create-agent"><img src="https://agentmods.dev/badge/agents/gmf520/openspec-agents/create-agent.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 37 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 109 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin unknown 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 $0.00037 $0.00109
Opus 5.5 $0.00015 $0.00044
Sonnet 5.5 $0.00007 $0.00022
Haiku 4.5 $0.00004 $0.00011

Measured 2mo ago against content hash c8dfb1db0f78, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, 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 2mo 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/agents/create-agent.md · 15 lines

The source is not reproduced here

No licence file

A repository with no LICENSE is all rights reserved by default, so the body is not copied here. The metadata, the measurements and the link are.

Read it on GitHub

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. 2mo ago First seen · 15 lines · 37 tokens per session scan A c8dfb1db0f78

Subscribe to this mod's changes

create-agent is an agent published in the GitHub repository gmf520/openspec-agents (19 stars, last pushed 6mo ago), with no licence file. It adds 37 tokens to every session and 109 once invoked, about $0.0001 per session on Opus 5.5. 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.

Related

create-agent compared with agents from other repositories

create-agent next to 6 agents from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
create-agentgmf520/openspec-agentsAgent196mo agononeA37Claude Code
integration-reviewerFlorianBruniaux/claude-code-pluginsAgent44yesterdayMITA57Claude Code
output-evaluatorFlorianBruniaux/claude-code-pluginsAgent44yesterdayMITA22Claude Code
loop-monitorFlorianBruniaux/claude-code-pluginsAgent44yesterdayMITA34Claude Code
architecture-reviewerFlorianBruniaux/claude-code-pluginsAgent44yesterdayMITA45Claude Code
refactoring-specialistFlorianBruniaux/claude-code-pluginsAgent44yesterdayMITA18Claude Code
test-writerFlorianBruniaux/claude-code-pluginsAgent44yesterdayMITA15Claude Code