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 FeiZhuLulu/kimi-code-skills --skill error-doctorgit clone --depth 1 https://github.com/FeiZhuLulu/kimi-code-skillsWrote 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/feizhululu/kimi-code-skills/error-doctor)<a href="https://agentmods.dev/skills/feizhululu/kimi-code-skills/error-doctor"><img src="https://agentmods.dev/badge/skills/feizhululu/kimi-code-skills/error-doctor/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/feizhululu/kimi-code-skills/error-doctor"><img src="https://agentmods.dev/badge/skills/feizhululu/kimi-code-skills/error-doctor.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00030 | $0.02280 |
| Opus 5 | $0.00015 | $0.01140 |
| Sonnet 5 | $0.00006 | $0.00456 |
| Haiku 4.5 | $0.00003 | $0.00228 |
Grade A, and why
error-doctor scanned grade A with 1 finding 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 10d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
Diagnosis: Check if the URL is reachable (`curl -I`), check DNS, check proxy settings. How it starts
The opening of the file, as written. The whole thing — 239 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Error Doctor — Structured Error Diagnosis
Purpose
Transform a confusing error message into: the key error, root cause hypotheses, verification steps, and a minimal fix. This skill diagnoses first, fixes second — it does not jump to editing code before understanding the problem.
Kimi Code Usage
Manual invocation:
/skill:error-doctor
This skill may be automatically invoked when the agent detects a failed Bash command, build error, or test failure.
Diagnosis Workflow
1. Locate the Error
Identify where the error came from:
| Source | How to get it |
|---|---|
| User pasted text | Read directly from the conversation |
| Recent Bash output | The last Bash tool execution with non-zero exit |
| Build log | Look for the build command output in the conversation |
| Test output | Look for the test command output in the conversation |
If the output is long (> 50 lines), use Grep to find the key error:
Grep pattern: (?i)(error|fatal|panic|exception|traceback|failed|FAILED)
If the error comes from Kimi session or debug files (wire.jsonl, tasks/, exported debug zip), treat them as sensitive local data. Do not paste or summarize credential-like content. Redact paths, tokens, and command outputs that may contain secrets.
2. Extract the Key Error
From the error output, identify the primary error. Most tools emit a mix of warnings, info, and errors. Focus on:
- The first error in a chain (subsequent errors are often cascading)
- Lines with
error,Error,ERROR,fatal,FATAL,panic - Lines with
Exception,Traceback,FAILED - The exit code
Ignore:
- Warnings that are not errors
- Info lines
- Decorative borders or formatting
- Stack frames from
node_modules, vendor directories, or standard libraries (focus on your own code)
3. Classify the Error
Route into one of these categories:
Syntax / Parse
Signals: SyntaxError, Unexpected token, Parse error, error: expected
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.
- 10d ago First seen · 239 lines · 30 tokens per session scan A 9f25eaa27dbb
error-doctor is a skill published in the GitHub repository FeiZhuLulu/kimi-code-skills (5 stars, last pushed 2mo ago), licensed MIT. It adds 30 tokens to every session and 2,280 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
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.