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 runtime-self-checkgit 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/runtime-self-check)<a href="https://agentmods.dev/skills/lingtai-ai/lingtai/runtime-self-check"><img src="https://agentmods.dev/badge/skills/lingtai-ai/lingtai/runtime-self-check/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/runtime-self-check"><img src="https://agentmods.dev/badge/skills/lingtai-ai/lingtai/runtime-self-check.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 | $0.00100 | $0.04511 |
| Opus 5.5 | $0.00040 | $0.01804 |
| Sonnet 5.5 | $0.00020 | $0.00902 |
| Haiku 4.5 | $0.00010 | $0.00451 |
Grade A, and why
dev-guide-runtime-self-check 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 1mo 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 — 374 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Runtime Self-Check
Nested lingtai-dev-guide reference. This is a deep diagnostic library selected
only when a cutover, observed failure, or suspected mismatch raises a provenance
or lifecycle question. Kernel system-manual →
reference/refresh-precheck/SKILL.md is the single owner of ordinary agent
refresh sequencing; this reference neither repeats nor initiates that
transaction.
Core principle
Probe, confirm, and report only the assertion named by the trigger. Diagnosis is
read-only. A rebuild, editable reinstall, relink, source update, process stop, or
clean relaunch needs separate exact authorization and its owning procedure. Never
paste secrets into a report: redact tokens, keys, chat IDs, and private absolute
paths, preferring <your-lingtai-checkout> / ~/.lingtai-tui/... forms.
When to use
- A source/venv/interpreter-selector or editable-install cutover needs one exact runtime provenance assertion.
- A TUI-binary cutover needs binary, symlink, build, or PATH provenance.
- Changed or failing MCP source needs its specific module-source assertion, or MCP boot/tool behaviour suggests a source mismatch.
- On-disk source and live behaviour disagree, including a suspected long-lived service/adapter/cache mismatch.
- A proven inherited
PYTHONPATHmismatch needs source diagnosis or the separately authorized clean-relaunch recovery.
Ordinary same-runtime reload does not use this deep checklist. A routine
reload or preset swap with no provenance question routes directly to kernel
system-manual → reference/refresh-precheck/SKILL.md.
Source/venv cutover diagnostic handoff
A merged change or correct-looking checkout is not proof of what the live agent imports. Keep the owner boundary explicit:
- The update/build owner uses the relevant §1 probe to identify the exact runtime interpreter, imported source/package, HEAD/version, and intended selectors. Any source update or reinstall remains that owner's separately authorized action; stop rather than modify a protected dirty checkout.
- That owner freezes and hands off the cutover target evidence. Kernel
system-manual→reference/refresh-precheck/SKILL.mdowns the transaction and its targeted receipt; this diagnostic does not restate either. - Use only the assertion the trigger needs: §1 for import provenance, §6 when source is present but live behaviour still disagrees, §2–§3 for a TUI-binary cutover, or §4 for changed/failing MCP source.
- Report only the selected evidence under §7's redaction rules.
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.
- 1mo ago Changed · +12 lines · -22 tokens per session 3cae58f5fc14
- 1mo ago First seen · 362 lines · 122 tokens per session scan A 1b5248fb7c42
dev-guide-runtime-self-check is a skill published in the GitHub repository Lingtai-AI/lingtai (507 stars, last pushed 6d ago), licensed Apache-2.0. It adds 100 tokens to every session and 4,511 once invoked, about $0.0004 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
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.
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…
deck-retro
Run a fully local agent-deck retrospective over the user's own transcripts, Recall index and logs. Use when a user wants to find recurring failures or take their own finding from investigation through synthetic reproduction, a user-filed issue, a test-first fix and contributor PR handoff. Also use for weekly usage…
cwv-optimizer
Diagnose and fix Core Web Vitals issues on AEM Edge Delivery Services pages. Goes deeper than generic CWV advice by understanding EDS-specific performance patterns including the 100KB LCP budget, E-L-D loading phases, block rendering behavior, and third-party script impact. Produces specific fixes for LCP, CLS, and…
incident-response-incident-response
Coordinate production incident triage, mitigation, investigation, recovery, and follow-up. Use when responding to outages or other incidents that require structured operational coordination.