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 dev-guide-skillgit 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/dev-guide-skill)<a href="https://agentmods.dev/skills/lingtai-ai/lingtai/dev-guide-skill"><img src="https://agentmods.dev/badge/skills/lingtai-ai/lingtai/dev-guide-skill.svg" alt="Measured on agentmods" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Agent Snooping · line 116 Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
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 | $0.00086 | $0.01901 |
| Opus 5 | $0.00043 | $0.00950 |
| Sonnet 5 | $0.00017 | $0.00380 |
| Haiku 4.5 | $0.00009 | $0.00190 |
Grade A, and why
lingtai-tui-dev 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 — 170 lines — stays where its author put it; the contents beside it link to each section on GitHub.
LingTai TUI/Portal Development
Read this skill before every development task in this repository. It owns the
workflow, not the architecture facts or interface promises. Follow its links
instead of copying the root documents into this file. This repository ships the
Go side of LingTai: lingtai-tui, lingtai-portal, and install.sh. The
Python kernel lives in the sibling lingtai-kernel repository and is launched
as a subprocess; this repository never imports it.
First establish the task and baseline
- Re-read the latest human or maintainer instruction. Separate the requested change from suggested follow-up work and from unauthorized side effects.
- Name the selected baseline: normally live
origin/main, or an explicit tag or commit chosen by the maintainer. - Work in a real repository worktree. Before analysis or editing, prove the
worktree is clean and
HEADequals the selected baseline. A directory name or recorded SHA without equality is not enough. This repository's convention is.worktrees/<slug>/on a fresh branch offorigin/main. - Use a focused branch and keep unrelated local/runtime worktrees untouched. Both this repository and its sibling kernel see concurrent branches and stashed WIPs; editing the main checkout has repeatedly lost in-flight work.
See README.md and CLAUDE.md for the public
orientation and the Claude Code entry rules that route here.
Read the distributed systems before editing
Use progressive disclosure in this order:
- Read root
ANATOMY.md, then descend through the nearest child anatomy (tui/ANATOMY.md,portal/ANATOMY.md, or a per-package anatomy) until cited code answers where the relevant files, connections, composition, and state live. - Read root
CONTRACT.md. If the component is governed, read its paired local contract before changing its interface or expected behavior. - Read the cited code and narrow tests. Anatomy is navigation, not evidence in place of code; Contract is the normative promise, not a description to weaken when implementation drifts.
- Load a narrower manual only when the task needs its commands, examples, or
troubleshooting. Do not preload unrelated references. The Anatomy/Contract
convention is defined by the root
ANATOMY.mdandCONTRACT.mdthemselves; the bundledlingtai-tui-anatomyskill is a legacy citation-navigation aid for the existing per-package anatomies and awaits a separate alignment, so prefer the root documents where they differ. The shippedlingtai-dev-guideskill owns the deeper per-topic procedures (setup, gotchas, releasing, PR deliverables). This root skill routes into those; it does not copy them.
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 · 170 lines · 86 tokens per session scan A 30b970b9ff41
lingtai-tui-dev is a skill published in the GitHub repository Lingtai-AI/lingtai (696 stars, last pushed today), licensed Apache-2.0. It adds 86 tokens to every session and 1,901 once invoked, about $0.0004 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
ast-grep
Guide for writing ast-grep rules to perform structural code search and analysis. Use when users need to search codebases using Abstract Syntax Tree (AST) patterns, find specific code structures, or perform complex code queries that go beyond simple text search. This skill should be used when users ask to search for…
golang-testing
Production-ready Golang tests — table-driven tests, testify suites and mocks, parallel tests, fuzzing, fixtures, goroutine leak detection with goleak, snapshot testing, code coverage, integration tests, idiomatic test naming. Use when writing or reviewing Go tests, choosing a testing approach, setting up Go test CI…
golang-samber-oops
Structured error handling in Golang with samber/oops — error builders, stack traces, error codes, error context, error wrapping, error attributes, user-facing vs developer messages, panic recovery, and logger integration. Apply when using or adopting samber/oops, or when the codebase already imports…
golang-uber-fx
Golang application framework using uber-go/fx — fx.New, fx.Provide, fx.Invoke, fx.Module, fx.Lifecycle hooks, fx.Annotate (name/group/As), fx.Decorate, fx.Supply, fx.Replace, fx.WithLogger, and signal-aware Run(). Apply when using or adopting uber-go/fx, when the codebase imports go.uber.org/fx, or when wiring…
ax-go-agent-optimize
Use when writing Go code with github.com/ax-llm/ax/packages/go for agent optimization, verified agent-playbook evolution, evaluators, judges, optimizer artifacts, BootstrapFewShot, and GEPA.
gmeasure
Benchmark and measure Go code with gmeasure — an Experiment groups named Measurements, recorded via RecordValue/RecordDuration/MeasureDuration or repeated Sample/SampleValue/SampleDuration with SamplingConfig, timed inline with a Stopwatch, summarized through GetStats/Stats (StatMin/Max/Mean/Median/StdDev…