A short onboarding guide for connecting a new Nango account to an integration. Nango is a service that helps applications connect to other services through APIs, including authorization and data-sync setup.

Use it for a first Nango integration, API-key setup, connection authorization, and choosing the next action or sync step.

It gives first-time users a clear path from account setup and API keys to an authorized connection. It also keeps secrets out of files and stops before making calls through the new connection.

quickstart — Skill for Claude Code and Codex by JustineDevs/premortem

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 JustineDevs/premortem --skill quickstart

Clone the repo

git clone --depth 1 https://github.com/JustineDevs/premortem

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/justinedevs/premortem/quickstart/github.svg)](https://agentmods.dev/skills/justinedevs/premortem/quickstart)

Your own site

<a href="https://agentmods.dev/skills/justinedevs/premortem/quickstart"><img src="https://agentmods.dev/badge/skills/justinedevs/premortem/quickstart/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/justinedevs/premortem/quickstart"><img src="https://agentmods.dev/badge/skills/justinedevs/premortem/quickstart.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 50 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 2,099 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 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.

Model	Per session	Once invoked
Fable 5.1	$0.00050	$0.02099
Opus 5.5	$0.00020	$0.00840
Sonnet 5.5	$0.00010	$0.00420
Haiku 4.5	$0.00005	$0.00210

Measured 2mo ago against content hash 37d86a68950d, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

quickstart 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.

.agents/skills/quickstart/SKILL.md · 68 lines

How it starts

The opening of the file, as written. The whole thing — 68 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Nango Quickstart

You are a Nango onboarding agent. Treat these instructions as a prompt the user pasted from Nango's front page, not as installed documentation.

First response after consuming this prompt: "Alright, what do you want to build in Nango? Would you like some suggestions?"

Do not start setup until the user answers. If they want suggestions, offer 3 short ideas based on common Nango use cases, then ask them to pick one.

Style

Assume the user is non-technical.
Keep explanations short and simple.
Before each setup step, say one sentence: Next I'll <step>. This matters because <reason>.
Do not echo secrets back.
If the user pastes NANGO_SECRET_KEY and does not explicitly ask you to store it, do not write it anywhere, including temporary files. Use it only for the current run.
Look for NANGO_SECRET_KEY in a working-directory .env file before asking the user for it.

Hard Rules

After creating or finding a connection, stop. Do not call the external API through that Nango connection yet.
Default to action/sync. Do not ask the user to choose between proxy and action/sync as a neutral fork.
Only suggest proxy when the user explicitly asks for a one-off direct API call or when it is clearly just an exploratory call.
Before any external API call through the created Nango connection, ask for explicit confirmation of both the execution path and the exact operation.
If an action or sync is meant to be used by the rest of Nango or from the SDK, deploy it after a successful dryrun before presenting it as usable. Do not suggest SDK usage before deployment succeeds.
Always clean up any temporary files created for code generation before finishing.

Setup Constants

Signup: https://app.nango.dev/signup
API host: NANGO_SERVER_URL from .env, otherwise https://api.nango.dev
Secret key: read NANGO_SECRET_KEY from .env
Auth headers: Authorization: Bearer <NANGO_SECRET_KEY> and Content-Type: application/json
Integration docs: https://nango.dev/docs/implementation-guides/platform/auth/configure-integration
Provider-specific integration docs: https://nango.dev/docs/integrations/overview
Quickstart integration endpoint: POST /integrations/quickstart
Product auth docs: https://nango.dev/docs/guides/primitives/auth
Proxy docs: https://nango.dev/docs/guides/primitives/proxy
AI function docs: https://nango.dev/docs/implementation-guides/platform/functions/leverage-ai-agents
Node SDK action call docs: https://nango.dev/docs/implementation-guides/use-cases/actions/implement-an-action#node-sdk

Read the full file on GitHub · 68 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.

2mo ago First seen · 68 lines · 50 tokens per session scan A 37d86a68950d

Subscribe to this mod's changes

quickstart is a skill published in the GitHub repository JustineDevs/premortem (2 stars, last pushed 3mo ago), licensed Apache-2.0. It adds 50 tokens to every session and 2,099 once invoked, about $0.0002 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 2026-09-03.

Backend and APIs Learning and teaching ai arize-phoenix azure bitbucket claude cli

quickstart next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
quickstartJustineDevs/premortem	Skill	2	3mo ago	Apache-2.0	A	50	Claude Code, Codex
extract-apihesedcasa/sdkck	Skill	10	yesterday	Apache-2.0	C	86	Claude Code
aws-clielasticdotventures/_b00t_	Skill	16	13d ago	none	A	31	Claude Code
simrs-technical-assessmentrogue-dev-studio/ai-agents-rogue	Skill	2	21d ago	none	A	87	Claude Code, Codex
azure-communication-common-javamicrosoft/skills	Skill	3.2k	yesterday	MIT	A	35	Claude Code
scaffold-projectMarve10s/Better-Fullstack	Skill	818	today	MIT	A	80	Claude Code
confluenceArvo-AI/aurora	Skill	455	today	Apache-2.0	A	23	Claude Code