Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →lingtai-ai/preset-skill-codex
Official-source-led manual for the TUI `codex` template.
Passed 25 of 25 test cases with the skill, and 4 of 25 without it.
and 37 more in the full report
21 fixed4 passed either way0 still failing0 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 21 test cases the skill fixed. Same model, same prompt, with and without the skill.
When turning on the Paid Codex credits toggle in the terminal or desktop preset editor, state the manifest JSON field name and its default boolean value.
| Checked | Without skill | With skill |
|---|---|---|
| identifies manifest.llm.codex_allow_credits as the JSON field | Missed | Passed |
| states that the paid credits field defaults Off | Passed | Passed |
The instructions your model reads when the skill loads.
Use this child for the named built-in codex preset — the first-run default
template. codexPreset in tui/internal/preset/preset.go ships provider codex,
gpt-5.6-sol, https://chatgpt.com/backend-api/codex, ChatGPT OAuth with an
empty api_key_env, thinking xhigh, web_search on DuckDuckGo, and vision
inheriting the agent's own (Codex) provider. It is not the OpenAI API
preset: an OpenAI API key or an OpenAI-compatible endpoint uses the openai
family (reference/openai/SKILL.md), and several ChatGPT accounts behind one
endpoint use an external pool such as sub2api / subs-pool through that same
openai family.
Since 2026-09-30 the picker's model lineup is fetched, not hand-curated: see "Public model-directory picker" below before assuming the old docs-page-comparison workflow still applies to the live list. Never inspect or print OAuth token contents.
Start at codexPreset in tui/internal/preset/preset.go, which pins the
constructor/default to config.DefaultCodexModelOptions()[0]
(tui/internal/config/codex_public_models.go) — currently gpt-5.6-sol: public
Astra documentation is positive, but exact authenticated OAuth-route
availability is not, so the offline default does not silently promote Astra.
Revise codexThinkingOptions in tui/internal/tui/preset_editor.go when Codex's
reasoning choices change; the service tier row offers normal/fast (fast is
sent as priority). Preserve the /codex base_url suffix, empty api_key_env,
OAuth identity (codex_auth_path account binding), and explicit xhigh default.
Follow the Codex-specific checklist in tui/internal/tui/SKILL.md. The
latest-two-generation rule in tui/CONTRACT.md no longer governs Codex — see
that contract's "Codex exception" and the next section — but still governs
Claude Code's CLI aliases.
Codex's model row is per-editor state
(PresetEditorModel.codexModels), not a providerModels map entry — there is
no static list to edit when a new model ships. On preset-editor entry,
test cases passed, vs 4 / 25 without
Published skills whose descriptions closely match this one, with their headline benchmark lift.
More skills from the same source and nearby in the registry, with their headline benchmark lift.