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 diagnosisgit 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/diagnosis)<a href="https://agentmods.dev/skills/lingtai-ai/lingtai/diagnosis"><img src="https://agentmods.dev/badge/skills/lingtai-ai/lingtai/diagnosis/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/diagnosis"><img src="https://agentmods.dev/badge/skills/lingtai-ai/lingtai/diagnosis.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 2 findings, up to high
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 →
- high Rogue Agent · line 26 Skill modifies its own code, configuration, or behavior at runtime. Self-modification enables an agent to escalate privileges, disable safety constraints, or install persistent backdoors.Fix: Prevent the skill from modifying its own code, SKILL.md, or configuration files. Treat skill files as read-only at runtime.
- high Rogue Agent · line 42 Skill modifies its own code, configuration, or behavior at runtime. Self-modification enables an agent to escalate privileges, disable safety constraints, or install persistent backdoors.Fix: Prevent the skill from modifying its own code, SKILL.md, or configuration files. Treat skill files as read-only at runtime.
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 | $0.00024 | $0.00695 |
| Opus 5 | $0.00012 | $0.00347 |
| Sonnet 5 | $0.00005 | $0.00139 |
| Haiku 4.5 | $0.00002 | $0.00069 |
Grade A, and why
lingtai-update-diagnosis 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 12d 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.
What it actually says
Failure diagnosis
Nested lingtai-update reference. Start with read-only identity checks:
lingtai-tui doctor
lingtai-tui version
command -v lingtai-tui lingtai-portal
If /update-tui says unknown, inspect the reported executable and the
TUI-owned ~/.lingtai-tui/install.json; do not substitute Homebrew. If a
source update fails, confirm its prefix/bin directory still exists and that the
requested tag is a strict vX.Y.Z release. If a Homebrew-to-native migration
fails, the reported failure line names the exact step (installer command,
install.json verification, binary version, or Python runtime) and confirms
the original Homebrew install is untouched and still usable; fix the reported
native-installer error, then retry with lingtai-tui self-update. Do not
substitute brew update or brew upgrade in this migration flow. The migration
step itself never uninstalls, unlinks, or deletes the Homebrew
formula/keg — do not suggest brew uninstall as part of recovering from a
migration failure; a failed migration has nothing to clean up. A successful
binary update still requires a fresh process: quit and relaunch the TUI.
If /update-tui or a startup prompt reports the native install as ready but
the migration as not complete, this is not a failure to diagnose: install.sh
and every artifact check succeeded, but the resolved lingtai-tui on PATH is
still the Homebrew one — typically because Homebrew's bin dir (for example
/opt/homebrew/bin on Apple Silicon) comes before install.sh's default native
bin dir on PATH. This state is expected to repeat on every subsequent
interactive launch until the human answers "y" to the concrete
"Remove the old Homebrew installation now? [y/N]" prompt (default No, so a
declined or non-interactive launch leaves it pending), or reorders PATH so the
native bin dir resolves first. self-update and doctor only ever report
this state and the manual brew uninstall lingtai-ai/lingtai/lingtai-tui
command — they never prompt or uninstall. It does not re-run the installer on
each detection.
For source-build failures, separate Go module fetches from the portal's
npm ci/frontend build. On asset download failure the installer is designed to
fall back to a source build; record the release tag, OS/architecture, and the
first actionable error rather than retrying blindly. Never paste environment
dumps, tokens, or private paths into reports. Python import, venv, or kernel
errors are outside this skill; follow the kernel's system-manual
runtime/kernel update manual.
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.
- 12d ago First seen · 54 lines · 24 tokens per session scan A 03c24380a9c8
lingtai-update-diagnosis is a skill published in the GitHub repository Lingtai-AI/lingtai (673 stars, last pushed yesterday), licensed Apache-2.0. It adds 24 tokens to every session and 695 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
debug-optimize-lcp
Guides debugging and optimizing Largest Contentful Paint (LCP) using Chrome DevTools MCP tools. Use this skill whenever the user asks about LCP performance, slow page loads, Core Web Vitals optimization, or wants to understand why their page's main content takes too long to appear. Also use when the user mentions…
systematic-debugging
Use when debugging a failing test, build error, or runtime issue that isn't immediately obvious. Guides a 4-phase root cause analysis instead of random fix attempts.
diagnose
Trace from a reproduced symptom to the source code that causes it. Pin the specific file and approximate line, rate confidence in the cause and clarity of the fix independently, and always propose a concrete fix.
repro-admin
Reproduce an EmDash admin UI bug. Attach a container, start the demo dev server, drive the admin with agent-browser using the dev-bypass session, and capture the reproduction as screenshots plus a replayable transcript.
log-error-digest
Analyze log files to troubleshoot errors, identify peak error periods, and produce error clustering, frequency statistics, and time distribution reports. Supports JSON, syslog, and Nginx formats with automatic detection. Use when a user uploads a .log file and asks to analyze errors, find patterns, debug issues, or…
byted-util-volcengine-detect-retry
An orchestration workflow for Volcengine Cloud Detect, a service that checks websites or network endpoints from test locations.