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 OKHP3/skillz --skill okhp3-custom-gpt-buildergit clone --depth 1 https://github.com/OKHP3/skillzWrote 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/okhp3/skillz/okhp3-custom-gpt-builder)<a href="https://agentmods.dev/skills/okhp3/skillz/okhp3-custom-gpt-builder"><img src="https://agentmods.dev/badge/skills/okhp3/skillz/okhp3-custom-gpt-builder/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/okhp3/skillz/okhp3-custom-gpt-builder"><img src="https://agentmods.dev/badge/skills/okhp3/skillz/okhp3-custom-gpt-builder.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 | $0.00103 | $0.04366 |
| Opus 5 | $0.00051 | $0.02183 |
| Sonnet 5 | $0.00021 | $0.00873 |
| Haiku 4.5 | $0.00010 | $0.00437 |
Grade A, and why
okhp3-custom-gpt-builder 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 10d 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 — 387 lines — stays where its author put it; the contents beside it link to each section on GitHub.
okhp3-custom-gpt-builder
OverKill Hill P³ · overkillhill.com · github.com/OKHP3
A production-grade methodology for designing, building, testing, and maintaining OpenAI Custom GPTs. Treats GPT creation as product engineering, not prompt tinkering.
Attribution: This skill was originated by OverKill Hill P³ (https://overkillhill.com) and is licensed under CC BY 4.0. Attribution is required in all derivative works. See
LICENSE.md.
Current-platform verification rule
Platform details change frequently. Before stating limits, feature availability, pricing, model behavior, GPT Builder constraints, Actions/App compatibility, Gemini Gem capabilities, or Copilot agent behavior as definitive, verify against current official documentation or clearly label the statement as unverified. Prefer stable design principles over brittle platform trivia.
What This Skill Covers
This skill guides the full lifecycle of Custom GPT development:
- Product definition (job-to-be-done, user, scope, acceptance criteria)
- Instruction architecture (layered system prompt, no-contradictions rule)
- Knowledge engineering (file selection, structure, retrieval optimization)
- Capability and tool configuration (toggles, Actions, Apps/MCP/connectors)
- Testing and evaluation (golden prompt sets, adversarial cases, red-team)
- Publishing and governance (visibility, versioning, maintenance)
- Cross-platform comparison (GPT vs. Gem vs. Copilot declarative agent)
- Repo-native packaging (manifest, overlays, evals, references, and source-of-truth discipline)
For detailed reference on any section, consult the corresponding file in references/ and the package map in MANIFEST.md.
Core Principle
If a Custom GPT cannot outperform a well-written one-off prompt, it does not deserve to exist as a GPT.
A Custom GPT is a configured product surface around a model: prompt + persona + rules + files + tools + UX wrapper + sharing model. Not a new model. Not fine-tuning. Not automatically an autonomous agent. It is a packaged, reusable ChatGPT configuration for a specific job.
What ships with it
12 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- CHANGELOG.md 2.4 KB
- evals/evals.json 15 KB
- LICENSE.md 1.9 KB
- MANIFEST.md 4.1 KB
- references/actions-and-apps.md 6.1 KB
- references/eval-and-redteam.md 10 KB
- references/instruction-architecture.md 11 KB
- references/knowledge-engineering.md 8.9 KB
- references/platform-comparison.md 10.0 KB
- references/quality-tiers.md 11 KB
- references/repo-overlay.md 1.1 KB
- references/taxonomy.md 13 KB
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.
- 10d ago First seen · 387 lines · 103 tokens per session scan A 8f8a9b22e802
okhp3-custom-gpt-builder is a skill published in the GitHub repository OKHP3/skillz (3 stars, last pushed yesterday), licensed MIT. It adds 103 tokens to every session and 4,366 once invoked, about $0.0005 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
vastai-sdk
Vast.ai Python SDK — high-level API for GPU instances, volumes, serverless endpoints, and billing.
pm-aarrr
A post-launch product-growth workflow based on AARRR: acquiring users, activating them, retaining them, earning revenue, and gaining referrals.
pm-docs
A workflow for producing product documents such as PRDs, BRDs, and MRDs. These are structured documents describing what a product needs, its business case, and its market.
product-marketing-copywriter
A marketing-copy tool that analyzes audience problems and product benefits, then creates promotional headlines and body text. Marketing copy is writing intended to explain and promote a product.
pm-position
A guided process for defining a product’s market position, value, audience, competitive difference, business model, pricing, and revenue plan. The instructions are written mainly in Chinese.
pm-retro
A retrospective workflow for reviewing a finished agile iteration, recording what happened, and choosing improvements for the next cycle.