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 Lingtai-AI/lingtai --skill codexgit clone --depth 1 https://github.com/Lingtai-AI/lingtaiWrote 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/lingtai-ai/lingtai/codex)<a href="https://agentmods.dev/skills/lingtai-ai/lingtai/codex"><img src="https://agentmods.dev/badge/skills/lingtai-ai/lingtai/codex/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/lingtai-ai/lingtai/codex"><img src="https://agentmods.dev/badge/skills/lingtai-ai/lingtai/codex.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00020 | $0.01426 |
| Opus 5.5 | $0.00008 | $0.00570 |
| Sonnet 5.5 | $0.00004 | $0.00285 |
| Haiku 4.5 | $0.00002 | $0.00143 |
Grade A, and why
preset-skill-codex 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 15d 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 — 114 lines — stays where its author put it; the contents beside it link to each section on GitHub.
codex preset revision
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.
Template-specific settings
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.
TUI surfaces to revise
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.
Public model-directory picker
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,
config.RefreshCodexPublicModels (tui/internal/config/codex_public_models.go)
fetches the fixed public directory
https://raw.githubusercontent.com/openai/codex/main/codex-rs/models-manager/models.json
(bounded ~5s/~2MiB, last-good cache under <globalDir>/cache/, offline
static fallback on any failure) and retains entries whose display_name
starts with the exact case-sensitive prefix GPT — no numeric-generation,
visibility, or account-entitlement filter. The retained display_name is the
displayed label; the entry's slug is what gets persisted into
manifest.llm.model. This is public metadata, not proof the current account
can use a listed model — treat every entry as a suggestion and let the actual
run be the entitlement check. A saved/custom id absent from the live/cached
list keeps rendering (hollow) and keeps working; pressing c on the model
row opens a free-text custom entry for any account-specific or brand-new id.
A completed refresh never changes a saved preset's model, an agent's active
preset, or its thinking level, and never gates Save. To inspect live OAuth
quota instead, complete the app-server initialize handshake, send
account/rateLimits/read with structurally null params, and optionally
observe account/rateLimits/updated; read usedPercent, windowDurationMins, and
resetsAt without exposing secrets.
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.
- 15d ago Changed · +18 lines 0ce865349a1f
- 19d ago Changed · +18 lines c052cb20a1ae
- 23d ago Changed · +5 lines cbe05839050b
- 1mo ago Changed · +19 lines · -1 tokens per session f392e9f7283c
- 1mo ago First seen · 54 lines · 21 tokens per session scan A 57202454670c
preset-skill-codex is a skill published in the GitHub repository Lingtai-AI/lingtai (507 stars, last pushed 6d ago), licensed Apache-2.0. It adds 20 tokens to every session and 1,426 once invoked, about $0.0001 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.
Other skills, from other repositories
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…