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 codex-poolgit 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-pool)<a href="https://agentmods.dev/skills/lingtai-ai/lingtai/codex-pool"><img src="https://agentmods.dev/badge/skills/lingtai-ai/lingtai/codex-pool.svg" alt="Measured on agentmods" 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 | $0.00039 | $0.02615 |
| Opus 5 | $0.00019 | $0.01307 |
| Sonnet 5 | $0.00008 | $0.00523 |
| Haiku 4.5 | $0.00004 | $0.00262 |
Grade A, and why
preset-skill-codex-pool 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 — 197 lines — stays where its author put it; the contents beside it link to each section on GitHub.
codex-pool
codexPoolPreset() in tui/internal/preset/preset.go ships
provider codex-pool, exact model gpt-5.6-sol,
https://chatgpt.com/backend-api/codex, thinking: xhigh, and an empty
api_key_env because it selects from local ChatGPT OAuth token files. The
manifest declares vision parity with codex; pooling changes account
selection, not the model or endpoint. The editor's model row therefore
offers exactly the codex lineup — gpt-5.6-sol, gpt-5.6-terra,
gpt-5.6-luna, gpt-5.5, the latest two GPT-5.x generations under the TUI's
model-curation rule (tui/CONTRACT.md). See reference/codex/SKILL.md.
Template-specific settings
That manifest parity requires the companion kernel pool-vision dispatch support.
Kernel versions before the pool-vision fix can silently skip this capability
because codex-pool was absent from the vision-provider allow-list. Do not
claim current-main runtime parity before that companion support is merged and
verified. No separate official vision MCP is established; a native failure must
remain visible rather than falling back to generic OpenAI, guessing credentials,
or auto-loading an MCP.
Read the official Codex authentication and Codex models pages on demand. Verify the template’s model, endpoint, and capability fields in TUI source; never document pool membership or OAuth token contents here.
To check live OAuth quota/rate-limit state for one pooled account,
query that account's app-server directly: complete initialize, then send
the account/rateLimits/read request (params are structurally null),
and read the GetAccountRateLimitsResponse. This is per-account —
querying one pooled account's rate limits says nothing about the other
accounts in the pool, and the pool file itself carries no rate-limit or
credit data (it is refs + integer weights only, see below). Optionally
watch account/rateLimits/updated as a rolling supplement, never a
substitute. Full field-by-field routing, the official-272K-vs-measured-372K
distinction, and secret-safety rules live in
reference/operations/endpoint-capabilities/SKILL.md — do not restate or
re-derive that evidence here.
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 · 197 lines · 39 tokens per session scan A 83990ea2c8b7
preset-skill-codex-pool is a skill published in the GitHub repository Lingtai-AI/lingtai (696 stars, last pushed today), licensed Apache-2.0. It adds 39 tokens to every session and 2,615 once invoked, about $0.0002 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 2026-08-30.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
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…
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…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…
chronicle
Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…