New: 98,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

Ramp Reference Architecture

by jeremylongshore in jeremylongshore/tons-of-skills-marketplace

Design a production Ramp integration with isolated OAuth clients, typed API adapters, durable webhook ingestion, reconciliation workers, and audited financial writes.

MITAuto-check passedBackend & APIs

Install Ramp Reference Architecture

skills CLI
$ npx skills add jeremylongshore/tons-of-skills-marketplace --skill ramp-reference-architecture -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install jeremylongshore/tons-of-skills-marketplace ramp-reference-architecture --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/jeremylongshore/tons-of-skills-marketplace.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/.curated/ramp-reference-architecture .claude/skills/ramp-reference-architecture && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
ramp-reference-architecture
GitHub stars
2.8k
Token cost
~1.3k tokens
SKILL.md length
540 words
Files
2 (incl. references)
Skills in repo
3,342
Repo updated
First seen
Licence
MIT

At a glance

Design a production Ramp integration with isolated OAuth clients, typed API adapters, durable webhook ingestion, reconciliation workers, and audited financial writes.

  • Works in 5 steps: Define business capabilities, actors,… → Partition separate OAuth applications… → Place an allowlisted typed adapter… → …
  • Reviewing architecture
  • SKILL.md covers Overview, Prerequisites, Current Contract and Instructions, plus 7 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Ramp Reference Architecture is an agent skill from jeremylongshore/tons-of-skills-marketplace. Design a production Ramp integration with isolated OAuth clients, typed API adapters, durable webhook ingestion, reconciliation workers, and audited financial writes. Use when reviewing architecture or building a new platform. Trigger with "Ramp architecture" or "design Ramp integration".

Its SKILL.md is about 1.3k tokens, which your agent loads only when the skill is triggered. The skill folder holds 2 other files, including reference files (for example `references/official-docs.md`). Compatibility notes: Requires current Ramp Developer API documentation and approved access for any live financial, card, identity, accounting, application, or configuration change

It sits in Backend & APIs, covering Accounting and bookkeeping, Webhooks and OAuth and OpenID Connect. The repository describes itself as: Model-agnostic agent-skills platform with a harness-free canonical layer, verified adapters, and the ccpi package manager. Explore at tonsofskills.com. The licence is MIT.

When your agent uses it

  • Reviewing architecture
  • Building a new platform
  • With Ramp architecture
  • Design Ramp integration

Example prompts

  • “Ramp architecture”
  • “design Ramp integration”
  • “/ramp-reference-architecture”

Requirements

  • Compatibility (from SKILL.md): Requires current Ramp Developer API documentation and approved access for any live financial, card, identity, accounting, application, or configuration change
  • Pre-approved tools (allowed-tools): Read, Glob, Grep, Write, Edit

Workflow steps

5 steps, taken from the first numbered list in SKILL.md.

  1. Define business capabilities, actors, tenants/entities, latency, volumes, data classes, financial effects, recovery objectives, and…
  2. Partition separate OAuth applications and services for read-only ingestion, event receipt, accounting writes, and card/spend authority…
  3. Place an allowlisted typed adapter behind secret-managed token acquisition; centralize rate budget, pagination, error parsing, trace IDs…
  4. Ingest verified webhooks into a durable deduplicating queue, process asynchronously, and reconcile current API state plus downstream…
  5. Design deployment, observability, incident isolation, data retention, negative-access tests, and rollback; threat-model every path that…

What it can do on your machine

Read from SKILL.md and the folder at commit cfae287. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves these tools, so the agent can use them without asking each time:

    • Read
    • Glob
    • Grep
    • Write
    • Edit

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md.

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

  • Compatibility

    Requires current Ramp Developer API documentation and approved access for any live financial, card, identity, accounting, application, or configuration change

    From compatibility in the SKILL.md frontmatter.

Context cost

Ramp Reference Architecture loads about 1.3k tokens when it runs, and up to ~1.5k if it reads all its reference files. Until then it costs about 79 tokens; SKILL.md has 540 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~79
When it runs · the whole SKILL.md, loaded when a task matches
~1.3k
With references · SKILL.md plus every file in references/, read only if the agent opens them
~1.5k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from jeremylongshore/tons-of-skills-marketplace at commit cfae287, republished under its MIT licence (© jeremylongshore). 540 words, ~1,287 tokens.

Download SKILL.mdSave it as .claude/skills/ramp-reference-architecture/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.
name
ramp-reference-architecture
description
Design a production Ramp integration with isolated OAuth clients, typed API adapters, durable webhook ingestion, reconciliation workers, and audited financial writes. Use when reviewing architecture or building a new platform. Trigger with "Ramp architecture" or "design Ramp integration".
allowed-tools
Read, Glob, Grep, Write, Edit
compatibility
Requires current Ramp Developer API documentation and approved access for any live financial, card, identity, accounting, application, or configuration change
version
2.0.0
argument-hint
[integration-or-environment]
model
inherit
effort
high
author
Jeremy Longshore <jeremy@intentsolutions.io>
license
MIT
tags
saas, ramp, architecture, integration, governance

Ramp Integration Reference Architecture

Overview

Separate trust and failure domains: credential broker, typed adapter, event ingress, durable work ledger, financial connectors, reconciliation, and evidence. Keep write authority narrower than read and observability paths.

Prerequisites

  • Identify the Ramp application, environment, business entities, affected data and workflows, accountable owner, and rollback boundary.
  • Read references/official-docs.md and re-check endpoint schemas, scopes, limits, and support status before a live operation.
  • Use synthetic fixtures or Ramp sandbox until production access and business effects are explicitly approved.
  • Prepare approved secret storage and a sanitized evidence location.

Current Contract

  • Ramp supports direct Developer API, webhooks, MCP, and CLI surfaces for different automation jobs; long-lived deterministic integrations belong on the Developer API.
  • Webhook events are notifications and may be duplicated or out of order; fetch current resource state before acting when needed.
  • OAuth grant, scope, principal, entity, and object policy jointly determine authority.
  • Accounting and card workflows have distinct approval, idempotency, sensitive-data, and reconciliation requirements.

Instructions

  1. Define business capabilities, actors, tenants/entities, latency, volumes, data classes, financial effects, recovery objectives, and prohibited actions.

  2. Partition separate OAuth applications and services for read-only ingestion, event receipt, accounting writes, and card/spend authority where trust differs.

  3. Place an allowlisted typed adapter behind secret-managed token acquisition; centralize rate budget, pagination, error parsing, trace IDs, and schema-version evidence.

  4. Ingest verified webhooks into a durable deduplicating queue, process asynchronously, and reconcile current API state plus downstream effects on a schedule.

  5. Design deployment, observability, incident isolation, data retention, negative-access tests, and rollback; threat-model every path that can spend, sync, or expose card data.

Tool Discipline

  • Use Glob to locate candidate code, manifests, fixtures, and evidence without widening scope.
  • Use Grep to find relevant endpoints, fields, permissions, identifiers, errors, and stale assumptions.
  • Use Read to inspect the smallest required local files and authoritative evidence.
  • Use Write only for a new approved local draft, test, configuration, or evidence artifact.
  • Use Edit only for a bounded approved change with a known rollback.
  • Local file tools do not authorize a Ramp operation or replace owner approval.
Show full SKILL.md (201 more words)Show less

Approval Boundaries

Architecture, security, privacy, business, and finance owners approve boundaries. Ramp approval is required for vendor-restricted surfaces such as production Vault access.

Output

A context and data-flow design, trust boundaries, application/scope matrix, component ownership, event/reconciliation model, threat analysis, SLOs, rollout, and rollback.

Error Handling

ConditionResponse
One service holds every scopeSplit authority by capability and lifecycle, then retest cross-boundary denial.
Webhooks directly perform financial writesInsert a durable deduplicating ledger and reconcile current state before side effects.
Observability needs raw payloadsDesign field-safe structured signals and restricted evidence access instead.

Examples

Example 1

Design a read-only warehouse exporter with webhook triggers and periodic reconciliation, isolated from accounting-write credentials.

Example 2

Design an ERP connector whose source ledger, downstream receipt, and Ramp sync receipt form one auditable state machine.

Validation

  • Every component has a single trust purpose, owner, and failure boundary.
  • Secrets, card data, identity data, and financial writes follow minimized paths.
  • Duplicates, out-of-order events, timeouts, partial failure, and replay are modeled.
  • Authority and reconciliation have positive and negative verification.

Resources

  • Official documentation and contract notes
  • Re-check the dated contract and current OpenAPI schema before any live request.
  • Treat unresolved vendor behavior, authority, or financial state as a stop condition.

© jeremylongshore, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 1 other file (references) in skills/.curated/ramp-reference-architecture of jeremylongshore/tons-of-skills-marketplace.

  • SKILL.md
  • references/official-docs.md

Open the folder on GitHubat commit cfae287

Compare with similar skills

Ramp Reference Architecture next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Ramp Reference Architecture compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Ramp Reference Architecture this skilljeremylongshore/tons-of-skills-marketplace2.8k—~1.3kAutomated safety check: PassMIT
XeroCraftOS-dev/CraftBot392—~2kAutomated safety check: PassMIT
QuickBooks Online Integrationhewi333/Mom-n-Pop-Skills122—~1.9kAutomated safety check: PassMIT
Pp Squaremvanhorn/printing-press-library2.1k—~15kAutomated safety check: NotesApache-2.0
Stripe Best Practiceskanchengw/cnllm1732 repos~925Automated safety check: PassApache-2.0
Discord Php Bot Securitydiscord-php/DiscordPHP1.1k—~1.2kAutomated safety check: NotesMIT

Similar skills

  • Xero

    CraftOS-dev/CraftBot

    Xero API integration with managed OAuth. An agent skill from CraftOS-dev/CraftBot.

    392 GitHub stars~2k tokensUpdated 2 days ago
    Backend & APIsAuto-check passed

  • QuickBooks Online Integration

    hewi333/Mom-n-Pop-Skills

    Connects a small business to QuickBooks Online for customers, estimates, invoices and payments, using Intuit OAuth 2.0 with token refresh and sandbox or production setups.

    122 GitHub stars~1.9k tokensUpdated 1 mo ago
    Backend & APIsAuto-check passed

  • Pp Square

    mvanhorn/printing-press-library

    The current Square v2 API surface, plus local reconciliation and retained history.

    2.1k GitHub stars~15k tokensUpdated yesterday
    Business, Finance & HRAuto-check: notes

  • Stripe Best Practices

    kanchengw/cnllm

    Guides Stripe integration decisions — API selection (Checkout Sessions vs PaymentIntents), Connect platform setup (Accounts v2, controller properties), billing/subscriptions, Treasury financial…

    173 GitHub starsUsed in 2 repos~925 tokens
    Backend & APIsAuto-check passed

  • Discord Php Bot Security

    discord-php/DiscordPHP

    Audit checklist for DiscordPHP bots and API libraries — stop the bot token leaking to third-party APIs or logs, keep secrets out of customids and exception messages, use constant-time comparison and…

    1.1k GitHub stars~1.2k tokensUpdated today
    Backend & APIsAuto-check: notes

  • GitHub OAuth Nango Integration

    AgentWorkforce/relay

    A skill your agent uses when implementing GitHub OAuth + GitHub App authentication with Nango - provides two-connection pattern for user login and repo access with webhook handling

    872 GitHub starsUsed in 1 repo~3.4k tokens
    Backend & APIsAuto-check passed

More from jeremylongshore/tons-of-skills-marketplace

All 3,342 skills in this repo

  • Performing Security Code Review

    jeremylongshore/tons-of-skills-marketplace

    Execute this skill enables AI assistant to conduct a security-focused code review using the security-agent plugin.

    2.8k GitHub starsUsed in 2 repos~1.3k tokens
    Auto-check: notes

  • Adapting Transfer Learning Models

    jeremylongshore/tons-of-skills-marketplace

    Build this skill automates the adaptation of pre-trained machine learning models using transfer learning techniques.

    2.8k GitHub stars~1.1k tokensUpdated today
    Auto-check passed

  • Agent Context Loader

    jeremylongshore/tons-of-skills-marketplace

    Execute proactive auto-loading: automatically detects and loads agents.md files.

    2.8k GitHub stars~1.1k tokensUpdated today
    Auto-check passed

  • Aggregating Performance Metrics

    jeremylongshore/tons-of-skills-marketplace

    Aggregate and centralize performance metrics from applications, systems, databases, caches, and services.

    2.8k GitHub stars~1.2k tokensUpdated today
    Auto-check passed

  • Analyzing Capacity Planning

    jeremylongshore/tons-of-skills-marketplace

    Execute this skill enables AI assistant to analyze capacity requirements and plan for future growth.

    2.8k GitHub stars~947 tokensUpdated today
    Auto-check passed

  • Analyzing Database Indexes

    jeremylongshore/tons-of-skills-marketplace

    Process use when you need to work with database indexing. An agent skill from jeremylongshore/tons-of-skills-marketplace.

    2.8k GitHub stars~2k tokensUpdated today
    Auto-check passed

Categories

Questions about Ramp Reference Architecture

What does Ramp Reference Architecture do?

Design a production Ramp integration with isolated OAuth clients, typed API adapters, durable webhook ingestion, reconciliation workers, and audited financial writes. Ramp Reference Architecture is an agent skill from jeremylongshore/tons-of-skills-marketplace. Design a production Ramp integration with isolated OAuth clients, typed API adapters, durable webhook ingestion, reconciliation workers, and audited financial writes.

When should I use Ramp Reference Architecture?

Ramp Reference Architecture fits situations like: reviewing architecture; building a new platform; with Ramp architecture; design Ramp integration.

How do I install Ramp Reference Architecture in Claude Code?

Run `npx skills add jeremylongshore/tons-of-skills-marketplace --skill ramp-reference-architecture -a claude-code`. Or copy the skill folder (skills/.curated/ramp-reference-architecture in jeremylongshore/tons-of-skills-marketplace) into .claude/skills/ramp-reference-architecture in your project. Claude Code loads it when a task matches its description.

How do I install Ramp Reference Architecture in Codex?

Run `npx skills add jeremylongshore/tons-of-skills-marketplace --skill ramp-reference-architecture -a codex`. Or copy the skill folder (skills/.curated/ramp-reference-architecture in jeremylongshore/tons-of-skills-marketplace) into .agents/skills/ramp-reference-architecture in your project. Codex loads it when a task matches its description.

Can I use Ramp Reference Architecture in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add jeremylongshore/tons-of-skills-marketplace --skill ramp-reference-architecture -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/ramp-reference-architecture, .gemini/skills/ramp-reference-architecture, .github/skills/ramp-reference-architecture and .opencode/skills/ramp-reference-architecture in your project.

What does Ramp Reference Architecture need to run?

SKILL.md names no scripts, command-line tools or credentials: Ramp Reference Architecture is instructions for the agent only. Its frontmatter pre-approves these tools: Read, Glob, Grep, Write, Edit. Compatibility (from SKILL.md): Requires current Ramp Developer API documentation and approved access for any live financial, card, identity, accounting, application, or configuration change.

Does Ramp Reference Architecture access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Ramp Reference Architecture safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Ramp Reference Architecture use?

Ramp Reference Architecture is published under the MIT licence (declared in SKILL.md). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Ramp Reference Architecture use?

About 1.3k tokens (SKILL.md is roughly 5.1k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 216 tokens, read only when the agent opens those files.

What are the alternatives to Ramp Reference Architecture?

Skills that share tags, products or a category with Ramp Reference Architecture: Xero (CraftOS-dev/CraftBot, 392 stars), QuickBooks Online Integration (hewi333/Mom-n-Pop-Skills, 122 stars), Pp Square (mvanhorn/printing-press-library, 2.1k stars) and Stripe Best Practices (kanchengw/cnllm, 173 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Ramp Reference Architecture?

jeremylongshore (a GitHub user) maintains it in jeremylongshore/tons-of-skills-marketplace, which has 2,827 GitHub stars. The repository holds 3,342 skills in this directory. The repository was last updated on October 10, 2026.

Source: jeremylongshore/tons-of-skills-marketplace on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.