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 agentmods add skills/hoavdc/codexkit/codexkit-root-cause-analyzernpx skills add hoavdc/CodexKit --skill codexkit-root-cause-analyzergit clone --depth 1 https://github.com/hoavdc/CodexKitWrote 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/hoavdc/codexkit/codexkit-root-cause-analyzer)<a href="https://agentmods.dev/skills/hoavdc/codexkit/codexkit-root-cause-analyzer"><img src="https://agentmods.dev/badge/skills/hoavdc/codexkit/codexkit-root-cause-analyzer.svg" alt="Measured on agentmods" 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 | $0.00076 | $0.01090 |
| Opus 5 | $0.00038 | $0.00545 |
| Sonnet 5 | $0.00015 | $0.00218 |
| Haiku 4.5 | $0.00008 | $0.00109 |
Grade A, and why
codexkit-root-cause-analyzer 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 yesterday.
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 — 111 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Root Cause Analyzer
Purpose
Move beyond symptomatic fixes to identify true root causes of recurring problems, using proven analytical methods and producing actionable corrective actions.
When to use
- a problem has occurred more than once despite previous fixes
- a production incident needs thorough investigation
- quality defects are increasing and the cause is unclear
- customer complaints cluster around a specific area
- post-mortem or incident review
When not to use
- the cause is obvious and the fix is straightforward
- strategic planning (use strategy tools)
- risk identification for future events (use risk-register)
Inputs
- problem statement (what happened, when, how bad)
- impact data (who was affected, financial cost, customer impact)
- timeline of events leading to the problem
- previous fix attempts and their outcomes
- relevant process or system documentation
- available data or metrics related to the problem
Procedure
- Define the problem precisely:
- What is happening vs. what should be happening?
- When did it start? How often does it occur?
- What is the quantified impact?
- Template: "[Thing] is [problem] resulting in [impact] since [when]"
- Choose analysis method based on problem type:
- 5 Whys: for linear causation chains (simple to moderate)
- Ishikawa / Fishbone: for complex problems with multiple potential causes
- 6M categories: Man, Machine, Method, Material, Measurement, Mother Nature (Environment)
- Pareto Analysis: when multiple causes contribute and you need to prioritize
- 80/20 rule: find the 20% of causes responsible for 80% of the impact
- Execute analysis:
- For 5 Whys: ask "why?" iteratively until you reach a systemic cause (typically 3–7 levels). Stop when the answer points to a process, policy, or system — not a person.
- For Ishikawa: brainstorm causes in each 6M category, then validate with data.
- For Pareto: list all contributing causes, quantify frequency or impact, sort descending, calculate cumulative %.
- Validate root cause — confirm it is:
- Actionable (you can do something about it)
- Preventable (fixing it prevents recurrence)
- Systemic (not blaming an individual)
- Define corrective actions (CAPA framework):
- Containment: immediate actions already taken
- Corrective Action: fix the root cause
- Preventive Action: prevent recurrence in similar processes
- Each action: What | Who | When | Verification method
- Define recurrence metrics — how will you know it's fixed?
What ships with it
4 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- yesterday First seen · 111 lines · 76 tokens per session scan A d0c9befa5781
codexkit-root-cause-analyzer is a skill published in the GitHub repository hoavdc/CodexKit (21 stars, last pushed 3mo ago), licensed MIT. It adds 76 tokens to every session and 1,090 once invoked, about $0.0004 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
reducing-aigc-detection
Systematically reduce AIGC detection rates in academic papers (Chinese/English). Analyzes detection reports, identifies high-impact sections, applies multi-layer rewriting strategies preserving formatting/footnotes, and verifies results. Supports 维普/知网/Turnitin platforms.
architecting-security
安全架构与治理：威胁建模 (STRIDE/PASTA/LINDDUN)、零信任身份架构、IAM/SSO/MFA/PAM、合规框架 (SOC2/PCI/HIPAA/GDPR)、DLP、隐私工程、安全控制设计。Use when designing security architecture, threat modeling new systems, implementing zero-trust identity, designing IAM/SSO/PAM, building compliance evidence chains, or planning privacy-by-design.
building-agent-systems
AI agent and LLM system engineering reference covering single-agent dev (ReAct, tool calling, plan-execute), multi-agent coordination (swarm, role decomposition, file locking), LLM security (prompt injection, jailbreak defense, output filtering), RAG architecture (chunking, hybrid retrieval, rerank), and prompt…
cultivating-personas
Distills AI agent voice patterns from conversation into a Persona Voice Card v1.0 (self/user/language/register/emojipolicy/flourish only — no judgment-shaped fields), validates schema + content safety + differentiation, and routes contributions through the existing submission portal. Use when the user wants to…
defending-applications
Application security defense knowledge for builders. Covers Web/API/GraphQL hardening (XSS/SQLi/SSRF/IDOR/BOLA/Mass Assignment/deserialization/upload/path traversal), authentication/authorization (OAuth 2.0/OIDC/JWT/Session/Cookie/SAML/SSO), and LLM application security (prompt injection, jailbreak, RAG poisoning…
detecting-and-responding
蓝队与紫队工程：检测规则编写、SIEM/EDR 调优、事件响应、数字取证、威胁狩猎、ATT&CK 映射、紫队演练闭环。Use when writing Sigma/YARA detection rules, tuning SIEM noise, responding to security incidents, conducting forensic analysis, hunting threats, or running purple team exercises.