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 deepseekgit 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/deepseek)<a href="https://agentmods.dev/skills/lingtai-ai/lingtai/deepseek"><img src="https://agentmods.dev/badge/skills/lingtai-ai/lingtai/deepseek/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/deepseek"><img src="https://agentmods.dev/badge/skills/lingtai-ai/lingtai/deepseek.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 | $0.00784 |
| Opus 5 | $0.00010 | $0.00392 |
| Sonnet 5 | $0.00004 | $0.00157 |
| Haiku 4.5 | $0.00002 | $0.00078 |
Grade A, and why
preset-skill-deepseek 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 yesterday.
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 — 68 lines — stays where its author put it; the contents beside it link to each section on GitHub.
deepseek preset revision
Use this child for the named built-in deepseek preset. deepseekPreset in tui/internal/preset/preset.go:1321 uses provider deepseek, model deepseek-v4-pro, https://api.deepseek.com, DEEPSEEK_API_KEY, OpenAI compatibility, web_search, and skills. It has no built-in vision capability. The editor also offers DeepSeek API, OpenCode Go, and Custom base_url rows.
Template-specific settings
Read the official DeepSeek models and pricing and models API. For the native route, authenticated GET https://api.deepseek.com/models is the served-list check. OpenCode Go is a separate gateway: query its authenticated GET https://opencode.ai/zen/go/v1/models and keep only DeepSeek IDs served there; do not use the native list as proof for Go. Preserve the route-specific credential and model spelling.
The picker currently carries deepseek-v4-pro and deepseek-v4-flash, both modelHasVision false. The experimental deepseek-v4-flash-vision-exp entry is not part of the stock picker or vision contract. OpenCode Go is scoped to DeepSeek IDs for this provider; other Go models belong in Custom. The native API row and Go row select DEEPSEEK_API_KEY and OPENCODE_GO_API_KEY respectively; an edited native built-in receives a numbered DEEPSEEK_1_API_KEY-style slot.
TUI surfaces to revise
Start at deepseekPreset in tui/internal/preset/preset.go. Revise providerModels["deepseek"] and its modelHasVision entries in tui/internal/tui/preset_editor.go for picker or vision changes. Revise ProviderRegionURLs and ProviderDefaultEnv for base_url/env behavior; the constructor remains text-only unless a reviewed native vision route is wired. Follow tui/internal/tui/SKILL.md and tui/CONTRACT.md.
Reviewed deterministic revision
Prepare an evidence-bound manifest and explicit input, then run lingtai-tui presets revise --manifest PATH --input PATH --mode dry-run|check|apply [--output-dir PATH]. Review the JSON plan, use dry-run/check before apply, and apply only to a new explicit output directory. revision.go validates hashes, route bindings, and evidence and preserves unowned bytes. This amendment does not change the current deepseek values; it records the experimental vision exclusion.
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.
- yesterday Changed · +7 lines · -1 tokens per session f21bc256a051
- 10d ago First seen · 61 lines · 21 tokens per session scan A 78b3a7e8eaff
preset-skill-deepseek is a skill published in the GitHub repository Lingtai-AI/lingtai (670 stars, last pushed yesterday), licensed Apache-2.0. It adds 20 tokens to every session and 784 once invoked, about $0.0001 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…
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…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
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…