Index of every page on this site: llms.txt
All skills
jeremylongshore avatar

/ideogram-install-auth

@820dfc8
Run it yourself

Configure Ideogram API access with prepaid billing, server-side credentials, and explicit team ownership. Use when installing or auditing a new Ideogram environment. Trigger with "set up Ideogram API", "configure an Ideogram key", or "audit Ideogram authentication".

Use this Skill: https://skilld.dev/gh/jeremylongshore/tons-of-skills-marketplace/ideogram-install-auth

Nothing lands on disk. Nothing to clean up.

Fork this Skill

Edit a local copy. It keeps the author and licence.

SKILL.md

≈72 tokens for metadata: the name and description. ≈988 when used: this file. ≈618 more on demand in 1 file.

Description uses 3.6% of example budget

Before choosing a Skill, your Agent reads its name and description. All available Skills share that space.

  • A shorter description leaves more room for other Skills. This entry exceeds our 1% size suggestion.

In our Claude Code example, all Skill names and descriptions share 8,000 characters. This Skill uses ≈290 characters, or 3.6%.

The 1% threshold is a size suggestion. Longer descriptions can still fit.

Your model, settings, and other Skills decide how much text your Agent can read.

Example settings and source

The example uses a 200k-token context and default Claude Code settings. The count includes the name, description, separators, and when_to_use when present. Codex also counts local file paths.

Skit's source and limits: Codex 0.160.1, Claude Code 2.1.292.

Ideogram Authentication and Installation

Overview

Establish a reviewable Ideogram API boundary before any paid generation runs. Separate developer-account enrollment, team ownership, billing, secret storage, and application authorization so a valid key never becomes accidental authority for a browser or untrusted tenant.

Prerequisites

  • A named Ideogram team Owner and accountable application owner.
  • Accepted developer terms, a payment method, and positive prepaid API credit.
  • A server-side secret manager and an environment-specific rollback plan.

Current Contract

Ideogram API subscriptions and web-app subscriptions are billed separately. Keys are created in the API dashboard, displayed once, revocable, and shared against the team's credit balance. Team roles are Owner, Admin, and Member; multiple keys do not create separate balances.

Authentication

Store the key as IDEOGRAM_API_KEY and send it only in the Api-Key header to https://api.ideogram.ai. Never place it in source control, URLs, browser bundles, prompts, logs, screenshots, or client telemetry. Treat application user authorization as a separate control.

Instructions

  1. Inventory the runtime, Ideogram team, environment, data class, expected concurrency, and spend owner.
  2. Confirm developer terms, payment method, positive credit, and the team role allowed to create or revoke keys.
  3. Create one environment-scoped key and capture it directly into the approved secret manager because it is shown once.
  4. Configure the API host and secret reference without copying the value into repository files.
  5. Validate configuration offline, then run one synthetic generation only when live spend and content are approved.
  6. Record the key owner, creation date, rotation route, billing owner, validation result, and rollback state.

Tool Discipline

Use Read, Glob, and Grep to inspect dependency, configuration, and deployment surfaces. Use Write and Edit only for approved configuration or documentation changes. Invocation alone does not authorize key creation, billing changes, team membership changes, paid generation, or deployment.

Approval Boundaries

Require explicit ownership before adding credit, enabling auto-recharge, creating or revoking a key, changing a team role, sending sensitive prompts or images, or deploying a live integration. Repository inspection and synthetic offline validation remain read-only.

Error Handling

  • A 401 points first to a missing, malformed, revoked, or wrong-environment key.
  • A syntactically valid key can still fail when the shared team balance lacks positive credit.
  • A key exposed to a client or log is an incident: revoke it, rotate consumers, and verify removal from history.

Output

Return the environment, team and role boundary, secret-manager reference name, API host, billing readiness, offline and live-check status, evidence identifiers, risks, and rollback state. Exclude the credential, prompts, images, expiring URLs, and customer data.

Examples

  • Configure a production worker with an injected secret reference and a distinct staging key.
  • Report environment=staging; auth=Api-Key; credit=positive; live_smoke=approved; rollback=key-revocation-ready.

Validation

Verify the header name and host, scan tracked files for accidental values, confirm no browser exposure, and check that the accountable owner can revoke the key. A successful generation is not sufficient if evidence retention or billing ownership is unresolved.

Resources

  • Current first-party evidence map — use the dated endpoint, webhook, billing, team, and training links as the contract index for this workflow.
  • Recheck the endpoint-specific page and current OpenAPI description before relying on an enum, limit, beta feature, or lifecycle claim.
  • Record live observations as environment-specific evidence, not as universal vendor guarantees.

Source: SKILL.md on GitHub

No rule matched.

skilld matched fixed text patterns in SKILL.md and file names. Patterns miss obfuscated code.

skilld run checks every file with the same patterns. It asks for approval before it loads a Skill with a behavior marked Needs approval.

No alerts2mo3 checks · Risk SAFE
  • Gen Agent Trust Hub2mo

    The skill provides secure and standard instructions for setting up Ideogram API authentication, following industry best practices such as environment variable management and version control exclusion for secrets.

  • Socket2mo

    No alerts

  • Snyk2mo

    Risk: LOW · No issues

Signed by skilld at 820dfc8. This ties the file your Agent reads to that commit on GitHub. It does not review the instructions.

Last checked against GitHub 20 hours ago.

Activeupdated 2 months ago
What it can do
Reads files Edits files
Modelinherit
argument-hint
<runtime> <team> <environment>
version
1.11.0
author
Jeremy Longshore <jeremy@intentsolutions.io>
All 5 allowed tools
ReadGlobGrepWriteEdit
Other metadata
tags
[
  "saas",
  "ideogram",
  "authentication"
]
model
inherit
effort
high
compatibility
Designed for Claude Code; live Ideogram work requires network access and prepaid API credit

README badge

README badge for jeremylongshore/tons-of-skills-marketplace/ideogram-install-auth