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 debug-troubleshootgit 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/debug-troubleshoot)<a href="https://agentmods.dev/skills/lingtai-ai/lingtai/debug-troubleshoot"><img src="https://agentmods.dev/badge/skills/lingtai-ai/lingtai/debug-troubleshoot/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/debug-troubleshoot"><img src="https://agentmods.dev/badge/skills/lingtai-ai/lingtai/debug-troubleshoot.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 | $0.00051 | $0.04182 |
| Opus 5 | $0.00026 | $0.02091 |
| Sonnet 5 | $0.00010 | $0.00836 |
| Haiku 4.5 | $0.00005 | $0.00418 |
Grade A, and why
dev-guide-debug-troubleshoot 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 today.
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 — 349 lines — stays where its author put it; the contents beside it link to each section on GitHub.
LingTai Debug & Troubleshoot Reference
Nested lingtai-dev-guide reference. Read this after the top-level router sends you here.
Read the
lingtai-kernel-anatomyskill first. It owns the concepts — lifecycle states, memory layers, mail protocol, tool surface — that every section below assumes. This document is only the diagnosis-and-recovery procedure; the per-section concept map is at the end.
Quick Diagnosis Decision Tree
Problem?
├── Process issues?
│ ├── Peer unresponsive → §1.1
│ ├── Peer OOM / crashed → §1.2
│ └── Cannot spawn avatar → §1.3
├── Memory issues?
│ ├── Post-molt amnesia → §2.1
│ ├── Codex entries missing → §2.2
│ ├── Pad not loaded → §2.3
│ └── Molt imminent, critical operations incomplete → §2.4
├── Communication issues?
│ ├── Pigeon not delivered → §3.1
│ ├── Pigeon bounced "No agent at X" → §3.2
│ └── Scheduled pigeon not firing → §3.3
└── Tool issues?
├── Tool timeout → §4.1
├── Tool not found → §4.2
└── Tool output truncated → §4.3
1. Process Issues
1.1 Peer Unresponsive
Pigeons go unanswered; the peer is in contacts but silent. Possible states: busy (long LLM turn), stuck (LLM timeout/upstream error), asleep (energy depleted or lulled), suspended (process dead), or wrong address.
Diagnose in order — system(show) (your own health) → email(contacts) (verify the address) → email(send, address=<peer>, message="ping") → the heartbeat:
ls -la <work-dir>/.lingtai/<peer>/.agent.heartbeat
cat <work-dir>/.lingtai/<peer>/.agent.heartbeat
Fresh (< 5 min) = busy, just wait. Stale (> 5 min) = stuck or crashed. No file = probably no agent at that address. For a whole network at once, use the sweep in §5.
Action. With karma: system(interrupt, address=<peer>) for a stuck LLM turn, system(cpr, address=<peer>) to revive a suspended agent. Without karma: report to parent with evidence (heartbeat timestamp, last contact time).
Pitfalls. Repeated probe emails waste resources and cannot wake a suspended process; CPR without nirvana privileges fails silently. Asleep ≠ suspended — asleep agents wake on email, suspended ones need CPR first. Check the heartbeat before choosing to wait, interrupt, or CPR.
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.
- today Changed · +9 lines 15d49a71f6a7
- 10d ago First seen · 340 lines · 51 tokens per session scan A a94400f8cc4c
dev-guide-debug-troubleshoot is a skill published in the GitHub repository Lingtai-AI/lingtai (670 stars, last pushed yesterday), licensed Apache-2.0. It adds 51 tokens to every session and 4,182 once invoked, about $0.0003 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.