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.
npx skills add phazurlabs/install-labs --skill custom-gpt-packaginggit clone --depth 1 https://github.com/phazurlabs/install-labsWrote 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.
[](https://agentmods.dev/skills/phazurlabs/install-labs/custom-gpt-packaging)<a href="https://agentmods.dev/skills/phazurlabs/install-labs/custom-gpt-packaging"><img src="https://agentmods.dev/badge/skills/phazurlabs/install-labs/custom-gpt-packaging/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.
<a href="https://agentmods.dev/skills/phazurlabs/install-labs/custom-gpt-packaging"><img src="https://agentmods.dev/badge/skills/phazurlabs/install-labs/custom-gpt-packaging.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00086 | $0.04446 |
| Opus 5 | $0.00043 | $0.02223 |
| Sonnet 5 | $0.00017 | $0.00889 |
| Haiku 4.5 | $0.00009 | $0.00445 |
Grade A, and why
custom-gpt-packaging 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 9d 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.
How it starts
The opening of the file, as written. The whole thing — 438 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Custom GPT Packaging for the GPT Store
Complete reference for building, configuring, publishing, and maintaining Custom GPTs — OpenAI's zero-install distribution format for conversational AI agents.
What Is a Custom GPT?
A Custom GPT is a configured ChatGPT instance that combines four building blocks into a single shareable agent:
| Building Block | What It Does | Limit |
|---|---|---|
| System Instructions | Defines personality, behavior, process, and boundaries | ~8,000 characters recommended |
| Knowledge Files | Documents searched via RAG to ground responses in your data | 20 files, 512 MB each |
| GPT Actions | OpenAPI schemas that let the GPT call external APIs | Multiple actions per GPT |
| Built-in Capabilities | Code Interpreter, DALL-E image generation, web browsing | Toggle on/off per GPT |
Key mental model: A Custom GPT is ChatGPT with a preset personality, private knowledge, and optional API superpowers. Users click "Start Chat" and get a specialized agent instantly — zero installation, zero configuration, zero technical knowledge required.
When to Build a Custom GPT
Build a Custom GPT when:
- Your audience is non-technical — They will never run a terminal command or install a package. They open ChatGPT and talk.
- The tool is conversational — The primary interface is back-and-forth dialogue, not a dashboard or CLI.
- Maximum reach matters — ChatGPT has 200M+ weekly active users. The GPT Store is the largest AI agent marketplace.
- Zero friction is critical — No install, no signup (beyond existing ChatGPT account), no onboarding. Click and use.
- Local execution is not required — Everything runs in OpenAI's cloud. The user's device is just a chat window.
Do NOT build a Custom GPT when:
- You need persistent local state or file system access
- The agent must run offline
- Data privacy requirements prohibit sending data to OpenAI
- You need sub-second latency for tool calls
- The workflow is better served by a structured UI than a conversation
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.
- 9d ago First seen · 438 lines · 86 tokens per session scan A 831d703fb9dd
custom-gpt-packaging is a skill published in the GitHub repository phazurlabs/install-labs (3 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 86 tokens to every session and 4,446 once invoked, about $0.0004 per session on Opus 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 2026-08-31.
Other skills, from other repositories
local-ci
Run GitHub Actions workflows locally with pause-on-failure for AI-agent-driven CI iteration.
local-ci
Run GitHub Actions CI locally with Local CI to validate changes before pushing. Use when testing, running checks, or validating code changes.
chronicle
Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…
generate-run-commands
Generate or modify run commands for the current session. Use when the user wants to set up or update run commands that appear in the session's Run button.
verify-behavior
Verify or reproduce visible product behavior by driving the real UI with pi-computer-use's checked tools, requiring verified expect postconditions and durable state evidence for meaningful UI flows. Use when triage needs visual reproduction, implementation needs behavioral proof, review needs interactive confirmation…
memory
Retrieve relevant durable BB memories or save verified knowledge useful to future threads.