PromptArch
Builds and lints agent instruction files such as CLAUDE.md and Cursor rules, checking size budgets and scoring prompts for quality.
not read yet
Use
- Price
- Free plan · From $9/mopricing page, read 2026-10-13 ↗
- Activity
- Actively maintainedsite updated 3 days ago
- Company
- Domain since 2026domain registered
- Runs as
- CLI
- generate agent context files from a project description
- lint CLAUDE.md and cursor rules against size budgets
- build and score prompts from guided questions
- Domain since2026domain registered
- Their AI providers train on itNoprivacy policy ↗
- Privacy policy updated2026-10-04privacy policy ↗
“Anthropic: AI model provider (receives your prompt inputs to generate outputs; inputs are not used for model training per Anthropic s API terms).”
privacy policy ↗
These are PromptArch's own statements, read from its pages. We did not audit them. A line that is missing was not found on the pages we read; it does not mean the practice is absent.
- MCP serverai.promptarch/mcpverified in the MCP registry
- Stateanswers, 3 toolschecked 2026-10-13
- Address to connectmcp.promptarch.ai/mcp
- MCP docspromptarch.ai/blog/promptarch-cli-and-mcp-server-guidethe vendor's page ↗
Each line is something a program found when it went looking: the registry entry, the server's own answer, a spec that parses. A missing line means we did not find it, not that it does not exist.
Figure and bar: visits/mo, estimate · year: online since
- #1
Open Agent Skill
Registry that helps AI agents discover, compare, and install reusable skills with trust signals and install commands.
305Active—2026 - #2
Loop Engineering
Builds AI agent workflows with explicit goals, validation rules, budget limits, and human approval gates.
48Active— - #3
MCP360
Unified gateway connecting AI agents to 100 production-ready tools via Model Context Protocol.
16ActiveFrom $16/user/mo - #4
VerifiMCP · open
Routes an AI agent's question, claim or draft to a human reviewer who accepts, rejects or rewrites it, returning a verdict via callback.
14not readFrom ≈ $0.11 per use - #5
AqtaMCP · open
Checks each AI agent action against your rules and a person's prior approval, then signs the allowed or refused decision as a verifiable record.
12ActiveContact sales2026 - #6
Orkas
Orchestrates specialized AI agents via chat to research, write, design, and build deliverables for business tasks.
9ActiveFrom $11.99/mo
What is PromptArch?
Builds and lints agent instruction files such as CLAUDE.md and Cursor rules, checking size budgets and scoring prompts for quality. It is listed in the Atlas under Agents.
How much does PromptArch cost?
PromptArch has a free plan; paid plans start at $9/mo, per its pricing page on 2026-10-13.
Is PromptArch free?
Yes, PromptArch has a free plan, per its pricing page on 2026-10-13.
Do people use PromptArch?
Little sign of use.
Is PromptArch still maintained?
Actively maintained: site updated 3 days ago.
Does PromptArch train AI on your data?
Its privacy policy speaks for its AI providers rather than for PromptArch itself (2026-10-13): “Anthropic: AI model provider (receives your prompt inputs to generate outputs; inputs are not used for model training per Anthropic s API terms).”
How do I cancel PromptArch?
In its own words (terms of service, 2026-10-13): “You can cancel at any time from the billing portal linked in your account.”
Does PromptArch give refunds?
In its own words (terms of service, 2026-10-13): “Credit packs have a 30-day money-back guarantee; the first payment of a new subscription can be refunded within 30 days, minus the credits you used.”
What are alternatives to PromptArch?
In Agents, by use: Open Agent Skill, Loop Engineering, MCP360, Verifi, Aqta, Orkas.
Not quite it? Describe the job
betaFive tools from the Atlas that fit it, each judged against what you wrote.
How we read a tool
No votes, no reviews, no vendor claims. Every week a crawler reads each tool's own site and a few public registries, and the words on the card are bands over what it read.
- Use: visits to the site (estimated), installs from npm and PyPI, presence in Chrome's usage report.
- Activity: the newest release on GitHub, npm or PyPI; the newest dated page on the site; open roles on a public jobs board.
- Price: the vendor's own pricing page, read with the date. A figure is printed only when it is on that page.
- The line and the use cases are written by us from the homepage, one tool at a time, and refused when they repeat the vendor's marketing.
How AI assistants read each site — the reading vendors ask us about — is on each tool's own visibility page.