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 VoDaiLocz/kilo-kit-mcp --skill root-causegit clone --depth 1 https://github.com/VoDaiLocz/kilo-kit-mcpWrote 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/vodailocz/kilo-kit-mcp/root-cause)<a href="https://agentmods.dev/skills/vodailocz/kilo-kit-mcp/root-cause"><img src="https://agentmods.dev/badge/skills/vodailocz/kilo-kit-mcp/root-cause/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/vodailocz/kilo-kit-mcp/root-cause"><img src="https://agentmods.dev/badge/skills/vodailocz/kilo-kit-mcp/root-cause.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 Memory Poisoning · line 277 Skill manipulates agent memory, state, or stored context. Memory corruption can alter personality, override safety rules, or cause unpredictable behavior.Fix: Protect agent memory and state from modification by untrusted content. Use read-only memory for critical instructions and validate all state changes.
- high Memory Poisoning · line 297 Skill manipulates agent memory, state, or stored context. Memory corruption can alter personality, override safety rules, or cause unpredictable behavior.Fix: Protect agent memory and state from modification by untrusted content. Use read-only memory for critical instructions and validate all state changes.
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 | $0.02233 |
| Opus 5 | $0.00026 | $0.01117 |
| Sonnet 5 | $0.00010 | $0.00447 |
| Haiku 4.5 | $0.00005 | $0.00223 |
Grade A, and why
root-cause-analysis 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 9d 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 — 361 lines — stays where its author put it; the contents beside it link to each section on GitHub.
🔬 Root Cause Analysis Skill
Philosophy: Don't stop at the first "why" — dig until you hit bedrock.
When to Use
Use this skill when:
- Systematic debugging found the bug but not WHY it exists
- Issue keeps recurring despite fixes
- Bug seems to have multiple contributing factors
- You need to prevent similar bugs in the future
- There's a systemic/architectural issue suspected
Do NOT use this skill when:
- Bug is simple and obvious
- Time is extremely limited (use quick-fix)
- Just need to patch, not understand
Prerequisites
Before starting:
- Bug has been identified (what is happening)
- Have access to relevant code and history
- Understand the system architecture (high level)
- Have time for thorough analysis (~30-60 mins)
Process
Phase 1: PROBLEM DEFINITION 📝
Goal: Clearly define what we're analyzing.
Steps:
-
State the Problem Precisely
Template: "When [condition], the system [actual behavior] instead of [expected behavior]." Example: "When a user submits a login form with special characters, the system returns a 500 error instead of validating input." -
Gather Impact Data
- How often does it occur?
- Who/what is affected?
- What's the business impact?
- How long has it been happening?
-
Document Timeline
- When did it first appear?
- Any recent changes before first occurrence?
- Has it gotten better/worse?
Output: Clear problem statement with context.
Phase 2: THE 5 WHYS ANALYSIS 🔍
Goal: Drill down to fundamental causes.
Method:
Start: Problem Statement
│
├─ Why? → First-level cause
│ │
│ ├─ Why? → Second-level cause
│ │ │
│ │ ├─ Why? → Third-level cause
│ │ │ │
│ │ │ ├─ Why? → Fourth-level cause
│ │ │ │ │
│ │ │ │ └─ Why? → ROOT CAUSE
Rules:
- Each answer must be factual, not speculative
- If multiple answers possible at a level, branch and explore all
- Stop when you reach something actionable
- "Human error" is NEVER a root cause — dig deeper
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.
- 9d ago First seen · 361 lines · 51 tokens per session scan A f72eeb8288f9
root-cause-analysis is a skill published in the GitHub repository VoDaiLocz/kilo-kit-mcp (26 stars, last pushed 4d ago), licensed Apache-2.0. It adds 51 tokens to every session and 2,233 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 2026-09-03.
Other skills, from other repositories
godmode-engineering
BDB Engineering Godmode, enforcing strict Domain-Driven Design, TypeScript strictness, and Clean Architecture. Use when implementing backend/fullstack features or running the systematic 5-step debugging triage.
debugger
Debugging specialist for errors, test failures, and unexpected category: library behavior. Use proactively when encountering any issues.
agent-qa-result-triage
Triage failed Agent QA runs with MCP evidence, artifacts, logs, fixed failure categories, confidence, and actionable next steps.
audit-context-building
Enables ultra-granular, line-by-line code analysis to build deep architectural context before vulnerability or bug finding.
hns-lsel-curator
Local Self-Evolution Loop (LSEL) curator — the CLUSTER + drain engine for the GOOS-local PROPOSE→APPLY seam closure (SPEC-LSEL-LOCAL-EVOLUTION-001). Companion-offset drain of .moai/lessons-inbox.jsonl with a drain-side severity filter that drops the 65% Bash-timeout/sandbox noise, eventkey clustering with a frequency…
langsmith-tracing
LangSmith tracing and debugging setup for LLM applications. Configure observability, capture traces, and enable debugging for LangChain/LangGraph agents.