eve-registry-porting

eve-registry-porting is a skill for Claude Code from lukedj78/dev-flow. It costs 213 tokens per session (2,752 once invoked), scanned A, original, MIT.

A guide for adapting tools, connections, or skills from public eve agent registries for use in a multi-tenant eve application. These registries are catalogs of reusable agent code, while a multi-tenant app serves multiple separate customers from one application.

In plain words
What is it for?
Use it to find and port reusable eve components from community registries, after checking whether an official eve integration already exists.
Why use it?
It helps avoid copying the registry's standalone-agent runtime into an application that needs customer isolation. It also provides checks for making third-party code safe for separate tenants.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: mentions subagents.

Part of the dev-flow plugin — 47 skills shipped together

Good fit Use it to find and port reusable eve components from community registries, after checking whether an official eve integration already exists.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/lukedj78/dev-flow/eve-registry-porting
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.

Any agent
npx skills add lukedj78/dev-flow --skill eve-registry-porting
Clone the repo
git clone --depth 1 https://github.com/lukedj78/dev-flow

Made for: Claude Code.

Or install dev-flow, the plugin that ships this one along with the rest of its 47 skills.

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 eve-registry-porting

README.md
[![agentmods](https://agentmods.dev/badge/skills/lukedj78/dev-flow/eve-registry-porting.svg)](https://agentmods.dev/skills/lukedj78/dev-flow/eve-registry-porting)
Your own site
<a href="https://agentmods.dev/skills/lukedj78/dev-flow/eve-registry-porting"><img src="https://agentmods.dev/badge/skills/lukedj78/dev-flow/eve-registry-porting.svg" alt="Measured on agentmods" height="20"></a>
Per session 213 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,752 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector warn 7 Sept 2026
SkillSpector: 4 findings, up to medium

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

  • medium MCP Rug Pull · line 63
    npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.
    Fix: Pin the version: npx @scope/[email protected]
  • medium MCP Rug Pull · line 64
    npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.
    Fix: Pin the version: npx @scope/[email protected]
  • medium MCP Rug Pull · line 65
    npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.
    Fix: Pin the version: npx @scope/[email protected]
  • medium MCP Rug Pull · line 66
    npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.
    Fix: Pin the version: npx @scope/[email protected]
How audits are shown
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 $0.00213 $0.02752
Opus 5 $0.00106 $0.01376
Sonnet 5 $0.00043 $0.00550
Haiku 4.5 $0.00021 $0.00275

Measured 3d ago against content hash daa1e3316b9a, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

eve-registry-porting scanned grade A with 1 finding 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 3d 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

**`[VERIFY]` each registry actually serves the shadcn JSON shape** — one `curl` and look at `$schema`;
eve-registry-porting/SKILL.md · 159 lines

How it starts

The opening of the file, as written. The whole thing — 159 lines — stays where its author put it; the contents beside it link to each section on GitHub.

eve-registry-porting — borrow the bricks, not the agent

The eve ecosystem has spawned "shadcn for agents" registries — you copy source, not a dependency. They are a great catalog + code mine. But their unit of distribution is a standalone agent (one eve project that runs itself on a cron or from Slack), which is the opposite of a multi-tenant app where one interpreter wears profiles from a DB and delegates in a hierarchy.

So the rule is: port the components (tool / connection / skill), never the agent-as-a-runtime, and rewrite each one to be tenant-safe.

Where porting sits — the sourcing priority

Porting is third choice, not first. Before vendoring third-party source, prefer a maintained option higher up the list:

  1. eve's official integrations — discover + install from the CLI: eve registry search <cap>eve add <kind>/<name> (catalog at https://eve.dev/integrations — 50+ MCP/OpenAPI connections, 11+ channels, official extensions). If the service is there, install and stop — don't port. (eve-agent → §Install from the registry FIRST / Connection / Channel.)
  2. Install a third-party registry as a source — the community registries below are shadcn-registry format, so you can register one as an eve source (eve registry add @name=https://…/r/{name}.json, stored in package.json#registries) and pull with eve add @name/<slug>. That's an install (files written, dep tracked) — prefer it over porting whenever you don't need to own/modify the source. The mechanism is verified against [email protected]'s own docs: "eve stores the mapping in package.json#registries. The {name} placeholder becomes the integration name, so @acme/analytics resolves to https://registry.acme.com/r/analytics.json." Narrow a query to one source with eve registry list --registry @acme / eve registry search <q> --registry @acme.

[VERIFY] each registry actually serves the shadcn JSON shape — one curl and look at $schema; it must be https://ui.shadcn.com/schema/registry-item.json. The four this skill set names were all checked on 2026-08-26 and all four pass:

Read the full file on GitHub · 159 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. 3d ago Changed · +1 lines daa1e3316b9a
  2. 7d ago First seen · 158 lines · 213 tokens per session scan A 792e91cf70e0

Subscribe to this mod's changes

eve-registry-porting is a skill published in the GitHub repository lukedj78/dev-flow (6 stars, last pushed yesterday), licensed MIT. It adds 213 tokens to every session and 2,752 once invoked, about $0.0011 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.