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 scasella/codex-gpt-pro --skill gpt-progit clone --depth 1 https://github.com/scasella/codex-gpt-proWrote 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/scasella/codex-gpt-pro/gpt-pro)<a href="https://agentmods.dev/skills/scasella/codex-gpt-pro/gpt-pro"><img src="https://agentmods.dev/badge/skills/scasella/codex-gpt-pro/gpt-pro.svg" alt="Measured on agentmods" 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 | $0.00130 | $0.01152 |
| Opus 5 | $0.00065 | $0.00576 |
| Sonnet 5 | $0.00026 | $0.00230 |
| Haiku 4.5 | $0.00013 | $0.00115 |
Grade A, and why
gpt-pro 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 8d 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 — 60 lines — stays where its author put it; the contents beside it link to each section on GitHub.
GPT Pro
Use the in-app browser, or the user's already-authenticated default browser via Computer Use when needed, to send the user's prompt to ChatGPT Pro and wait for the final answer.
Route Selection
- Check which browser-control routes are available in the current Codex session before navigating:
- Browser Use / Playwright route: available when
mcp__playwright__browser tools or equivalent in-app browser tools are present. - Computer Use route: available when
mcp__computer_use__tools are present. - If tool availability is unclear and
tool_searchexists, search for Playwright/browser navigation tools and Computer Use desktop-control tools.
- Browser Use / Playwright route: available when
- If neither route is available, report that this skill requires Browser Use/Playwright or Computer Use and stop.
- If exactly one route is available, use that route.
- If both routes are available, check for a saved default route in
preferences.jsonnext to thisSKILL.md. - If the current user prompt explicitly requests
playwright,Browser Use,in-app browser,Computer Use, or the default browser, use that as the current-run route even when a saved default exists. - If both routes are available and no saved default exists, ask the user which route to use by default going forward. Treat this as a separate preference question, not as a request to reroute the current run. Ask it even when the current prompt explicitly requested a one-off route, and keep the one-off route for the current run unless the user says otherwise:
playwright: use Browser Use / in-app browser by default.computer-use: use Computer Use with the user's already-authenticated default browser by default.
- After the user chooses, save the preference as JSON in
preferences.jsonnext to thisSKILL.md, for example:
{
"default_route": "playwright"
}
- If the saved preference is missing, malformed, or names an unavailable route, ignore it for the current run and ask again when both routes are available.
- If the preference file cannot be written, continue with the selected route for the current request and tell the user that the default was not saved.
What ships with it
1 file 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.
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.
- 8d ago First seen · 60 lines · 130 tokens per session scan A ffe53f4d1d23
gpt-pro is a skill published in the GitHub repository scasella/codex-gpt-pro (4 stars, last pushed 4mo ago), licensed MIT. It adds 130 tokens to every session and 1,152 once invoked, about $0.0006 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
libgdx-bitmap-font-text
Use when writing libGDX Java/Kotlin code involving text rendering (BitmapFont, GlyphLayout, BitmapFontCache), NinePatch scalable graphics, DistanceFieldFont, or color markup language. Use when debugging wrong text position, blurry scaled fonts, text measurement, or NinePatch stretching issues.
libgdx-android-backend
Use when writing libGDX Java/Kotlin code targeting Android — AndroidApplication launcher, AndroidApplicationConfiguration, AndroidManifest.xml setup, Android lifecycle mapping to libGDX, OpenGL context loss on pause, file access (internal/local/external with permissions), Android input (back button, accelerometer…
migrate-intellij-util
Optimize memory usage, consistency, and performance by migrating standard Java/Kotlin classes to IntelliJ's specialized com.intellij.util implementations.
authoring-java-sdk-tasks
Writes Airflow task logic in Java, Kotlin, or any JVM language using the Airflow Java SDK. Use when the user wants to implement Airflow tasks in Java/JVM, asks about @Builder.Dag/@Builder.Task/@Builder.XCom, the Task/BundleBuilder interfaces, reading connections/variables/XComs from Java, the JSON-to-Java type…
null-safety
Use when annotating nullability in Spring Boot 3 / Spring Framework 6 code, integrating Kotlin, or adding static nullability checks without assuming Spring Framework 7 JSpecify defaults.
littlejs-conventions
LittleJS game engine (littlejsengine) conventions — REQUIRED before answering, writing, editing, reviewing, or debugging ANY LittleJS code, including one-line questions about a snippet. TRIGGER whenever "LittleJS" appears, or the code uses…