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 BayramAnnakov/chatgpt-app-skill --skill chatgpt-app-buildergit clone --depth 1 https://github.com/BayramAnnakov/chatgpt-app-skillWrote 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/bayramannakov/chatgpt-app-skill/chatgpt-app-builder)<a href="https://agentmods.dev/skills/bayramannakov/chatgpt-app-skill/chatgpt-app-builder"><img src="https://agentmods.dev/badge/skills/bayramannakov/chatgpt-app-skill/chatgpt-app-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/bayramannakov/chatgpt-app-skill/chatgpt-app-builder"><img src="https://agentmods.dev/badge/skills/bayramannakov/chatgpt-app-skill/chatgpt-app-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 | $0.00104 | $0.03321 |
| Opus 5.5 | $0.00042 | $0.01328 |
| Sonnet 5.5 | $0.00021 | $0.00664 |
| Haiku 4.5 | $0.00010 | $0.00332 |
Grade A, and why
chatgpt-app-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 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.
How it starts
The opening of the file, as written. The whole thing — 430 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ChatGPT App Builder
Build production-ready ChatGPT Apps from concept to App Store submission.
Quick Start
New app? → Start at Phase 1 (Fit Evaluation)
Have app-spec.md? → Start at Phase 3 (Implementation)
App built? → Start at Phase 4 (Testing)
Ready to ship? → Start at Phase 5 (Deployment)
Phase 1: Fit Evaluation
Goal: Determine if a ChatGPT App is right for this product.
Step 1: Gather Context
Ask the user:
- What does your product do?
- Who are your users?
- What API/data does it expose?
- What actions can users take?
Step 2: Apply Know/Do/Show Framework
Evaluate against three value pillars (see fit_evaluation.md):
| Pillar | Question | Strong Signal |
|---|---|---|
| Know | Does it provide data ChatGPT lacks? | Live prices, user-specific data, internal metrics |
| Do | Can it take real actions? | Create, update, delete, send, schedule |
| Show | Can it display better than text? | Lists, charts, maps, media galleries |
Minimum requirement: At least one pillar must be strong.
Step 3: Check Blockers
Review fit_evaluation.md for:
- Prohibited categories (gambling, adult, crypto speculation)
- Data restrictions (no PCI, PHI, SSN, API keys)
- Age requirements (13+ audience)
Step 4: Create Golden Prompt Set
Draft prompts for discovery testing:
- 5 direct prompts: Explicitly name your product ("Show my TaskFlow tasks")
- 5 indirect prompts: Describe intent without naming ("What should I work on?")
- 3 negative prompts: Similar but shouldn't trigger ("Create a reminder")
Step 5: Write app-spec.md
Create the specification file:
# [Product Name] ChatGPT App Spec
## Product Context
- Name: [Product name]
- API Base: [API URL]
- Auth: [Bearer token / OAuth / None]
## Value Proposition
- Know: [What data does it provide?]
- Do: [What actions can it take?]
- Show: [What UI is needed?]
## Golden Prompts
### Direct (should trigger)
1. ...
### Indirect (should trigger)
1. ...
### Negative (should NOT trigger)
1. ...
What ships with it
42 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.
- assets/deploy/.github/workflows/deploy.yml 1002 B
- assets/deploy/Dockerfile 841 B
- assets/deploy/fly.toml 644 B
- assets/server/package.json 765 B
- assets/server/scripts/build-widget.ts 1.8 KB runs code
- assets/server/src/index.ts 17 KB runs code
- assets/server/src/lib/api-client.ts 3.6 KB runs code
- assets/server/src/lib/errors.ts 2.3 KB runs code
- assets/server/src/lib/image-proxy.ts 5.7 KB runs code
- assets/server/src/lib/rate-limiter.ts 4.9 KB runs code
- assets/server/src/tools/create-item.ts 2.4 KB runs code
- assets/server/src/tools/example-tool.ts 6.5 KB runs code
- assets/server/src/tools/get-items.ts 2.6 KB runs code
- assets/server/src/tools/index.ts 698 B runs code
- assets/server/src/types/openai.d.ts 1.9 KB runs code
- assets/server/src/widget/embed.ts 2.3 KB runs code
- assets/server/tsconfig.json 605 B
- assets/tests/golden-prompts.ts 6.5 KB runs code
- assets/tests/tool-tests.ts 6.3 KB runs code
- assets/widget/package.json 422 B
- assets/widget/src/App.tsx 6.0 KB
- assets/widget/src/components/ExampleList.tsx 3.6 KB
- assets/widget/src/components/ItemList.tsx 4.8 KB
- assets/widget/src/hooks/useOpenAI.ts 5.5 KB runs code
- assets/widget/src/hooks/useWidgetState.ts 170 B runs code
- assets/widget/src/types/openai.d.ts 1.7 KB runs code
- assets/widget/styles/widget.css 4.8 KB
- assets/widget/tsconfig.json 406 B
- references/apps_sdk_ui_tokens.md 5.5 KB
- references/chatgpt_app_best_practices.md 12 KB
- references/fit_evaluation.md 5.8 KB
- references/node_chatgpt_app.md 19 KB
- references/oauth_integration.md 19 KB
- references/security_patterns.md 13 KB
- references/submission_requirements.md 8.6 KB
- references/testing_patterns.md 11 KB
- references/troubleshooting.md 25 KB
- references/widget_css_template.md 13 KB
- references/widget_development.md 20 KB
- references/widget_loading_patterns.md 14 KB
- references/widget_ui_patterns.md 11 KB
- scripts/validate-app-spec.py 8.5 KB runs code
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 · 430 lines · 104 tokens per session scan A a4f765e34263
chatgpt-app-builder is a skill published in the GitHub repository BayramAnnakov/chatgpt-app-skill (22 stars, last pushed 10mo ago), licensed MIT. It adds 104 tokens to every session and 3,321 once invoked, about $0.0004 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 2026-08-30.
chatgpt-app-builder compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| chatgpt-app-builderBayramAnnakov/chatgpt-app-skill | Skill | 22 | 10mo ago | MIT | A | 104 | Claude Code |
| imagegenopenai/codex | Skill | 135k | today | Apache-2.0 | A | 113 | Codex |
| playwright-climicrosoft/playwright | Skill | 100k | today | Apache-2.0 | A | 19 | Claude Code |
| browser-automationopenclaw/openclaw | Skill | 394k | today | MIT | A | 36 | Claude Code |
| local-ai-agentsmicrosoft/ai-agents-for-beginners | Skill | 80k | 7d ago | MIT | A | 200 | Claude Code, Codex |
| next-cache-components-adoptionvercel/next.js | Skill | 144k | today | MIT | A | 95 | Claude Code |
| chat-pet-sprite-creationmicrosoft/vscode | Skill | 195k | today | MIT | A | 53 | Claude Code, Codex |