Borrowing it
Nothing to install: this file belongs to bachkukkik/template-agentic-ready-repo. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/bachkukkik/template-agentic-ready-repo/main/.agents/skills/root-cause/SKILL.mdgit clone --depth 1 https://github.com/bachkukkik/template-agentic-ready-repoWrote 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/bachkukkik/template-agentic-ready-repo/root-cause)<a href="https://agentmods.dev/skills/bachkukkik/template-agentic-ready-repo/root-cause"><img src="https://agentmods.dev/badge/skills/bachkukkik/template-agentic-ready-repo/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/bachkukkik/template-agentic-ready-repo/root-cause"><img src="https://agentmods.dev/badge/skills/bachkukkik/template-agentic-ready-repo/root-cause.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 | $0.00048 | $0.00626 |
| Opus 5 | $0.00024 | $0.00313 |
| Sonnet 5 | $0.00010 | $0.00125 |
| Haiku 4.5 | $0.00005 | $0.00063 |
Grade A, and why
root-cause 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 5d 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 — 35 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Root Cause
Shared rule (both tracks): the first plausible hit is a hypothesis, not the answer. Widen before you commit — list several possible causes, or read across several sources — then rule each in or out with evidence. Stopping at the first thing that fits is the failure mode this skill exists to prevent.
Which track?
- Requirement / setup / "why does X fail" answerable from docs, knowledge, or config → Evidence Track
- Live bug / test failure / wrong runtime behavior needing a code-level explanation → Debugging Track
- Bug that traces to an external system's unmet requirement → Evidence first (find the requirement), then Debugging (locate & fix the violating code).
- Unsure → start Evidence. A found requirement usually feeds the debugging anyway; guessing wrong here is cheaper than mis-starting Debugging.
Evidence Track
Widen: one source is rarely the whole answer. Read across sources; a single doc may be partial, outdated, or version/context-specific. Keep reading until the sources agree or you understand why they differ.
Gate before answering: every claim you rely on must trace to something you actually read — not memory, not inference from a title. Check it matches the user's version/context. If sources conflict, say so; don't silently pick one.
Stop: if you can't find support after a real search, say what's missing rather than guess-filling. "I couldn't find X" beats a confident wrong answer.
Debugging Track
Rule: don't fix until you can say "X causes Y causes symptom Z, and my fix changes X." Can't fill that in? Keep digging, don't guess.
Widen before you dig: list every plausible cause first (a few, not one). The first cause that fits is a hypothesis — bugs often have more than one contributing cause. Rule each in or out with evidence before committing. Digging deep into the first guess just makes a wrong guess more confident.
Dig by asking "why does that happen?" upstream from where the error shows to where it starts. Use only the effort the bug needs: a typo's chain is one line; an intermittent/async/multi-layer bug needs reproducing and narrowing until the cause is undeniable. Reach for logs or git bisect only when reasoning can't localize it.
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.
- 5d ago First seen · 35 lines · 48 tokens per session scan A 47bdde4cf611
root-cause is a skill published in the GitHub repository bachkukkik/template-agentic-ready-repo (2 stars, last pushed 5d ago), licensed Apache-2.0. It adds 48 tokens to every session and 626 once invoked, about $0.0002 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 2026-09-05.
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.