What is root-cause-analysis?

A read-only process for finding the verified underlying cause of errors from logs, exceptions, stack traces, or terminal failures. It traces the failure to the responsible code and checks relevant configuration and dependencies.

Use it to investigate application crashes, failing commands, exception traces, configuration problems, dependency issues, and permanent fixes.

It separates the actual cause from symptoms and avoids temporary workarounds that may hide the problem. The process requires stating the cause and how the failure happens before proposing code changes.

How lsampaioweb/ai-instructions configures Cursor

Reuse

Borrowing it

Nothing to install: this file belongs to lsampaioweb/ai-instructions. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/lsampaioweb/ai-instructions/main/.cursor/skills/root-cause-analysis/SKILL.md

Clone the repo

git clone --depth 1 https://github.com/lsampaioweb/ai-instructions

Made for: Cursor.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/lsampaioweb/ai-instructions/root-cause-analysis/github.svg)](https://agentmods.dev/skills/lsampaioweb/ai-instructions/root-cause-analysis)

Your own site

<a href="https://agentmods.dev/skills/lsampaioweb/ai-instructions/root-cause-analysis"><img src="https://agentmods.dev/badge/skills/lsampaioweb/ai-instructions/root-cause-analysis/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/lsampaioweb/ai-instructions/root-cause-analysis"><img src="https://agentmods.dev/badge/skills/lsampaioweb/ai-instructions/root-cause-analysis.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 76 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 607 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

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	$0.00076	$0.00607
Opus 5.5	$0.00030	$0.00243
Sonnet 5.5	$0.00015	$0.00121
Haiku 4.5	$0.00008	$0.00061

Measured 1mo ago against content hash 08b000dda3f9, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

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 1mo 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.

.cursor/skills/root-cause-analysis/SKILL.md · 72 lines

How it starts

The opening of the file, as written. The whole thing — 72 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Root Cause and Permanent Fixes

Arguments

Required: error logs, stack traces, or terminal output.

1. Trace the Failure

Trace analysis: Parse the stack trace or log to isolate the originating line, class, and feature package.
Context verification: Check the active environment configuration, dependency manifests, or runtime properties when systemic context is missing.
Diagnostics: Run targeted checks, such as terminal commands or file searches, to verify framework behavior, documented defects, or version-specific edge cases.

2. Resolution Rules

State the verified Root Cause and failure mechanism before writing or proposing any code modifications.
Do not apply temporary workarounds.
Do not bypass visibility modifiers.
Do not suppress exceptions.
Do not inject unapproved dependencies.
Code fixes must adhere to packaging conventions and data-access patterns defined by the active project architecture.
Code fixes must respect dependency boundaries and detected runtime version constraints.
Correct broken interface contracts when they cause the failure.
Align data schemas when schema mismatch causes the failure.
Fix lifecycle and boundary violations when they cause the failure.

3. Safety Guards

Execution boundary: Apply code fixes only after presenting the plan and receiving the user's explicit confirmation.
Safety Gate: Never generate speculative code fixes when the root cause cannot be verified with high confidence.
Truncated/Ambiguous Logs: If the log is truncated or missing critical details, stop and prompt for the specific missing block.
Fallback Output: If unresolved, output:
- List of attempted verification steps.
- Precise technical uncertainties remaining.
- The single next decisive diagnostic action for the developer to execute.

4. Review Plan Layout

Use this exact markdown schema:

Scope

Target: <error logs, stack traces, or terminal output>
Mode: <read-only | apply-after-confirmation>

Read the full file on GitHub · 72 lines

Changes

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.

1mo ago Changed · +22 lines · +29 tokens per session 08b000dda3f9
2mo ago First seen · 50 lines · 47 tokens per session scan A 750f88d2d535

Subscribe to this mod's changes

root-cause-analysis is a skill published in the GitHub repository lsampaioweb/ai-instructions (1 stars, last pushed 5d ago), licensed MIT. It adds 76 tokens to every session and 607 once invoked, about $0.0003 per session on Opus 5.5. 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 2026-08-31.

Debugging

root-cause-analysis next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
root-cause-analysislsampaioweb/ai-instructions	Skill	1	5d ago	MIT	A	76	Cursor
systematic-debuggingopen-metadata/OpenMetadata	Skill	16k	yesterday	Apache-2.0	A	37	Claude Code
log-error-digestzebbern/claude-code-guide	Skill	4.7k	3d ago	MIT	A	71	Claude Code, Codex
cwv-optimizeradobe/skills	Skill	319	yesterday	Apache-2.0	A	112	Claude Code
ci-fixersipyourdrink-ltd/bernstein	Skill	1.2k	yesterday	Apache-2.0	A	15	Claude Code, Codex
incident-response-incident-responsermyndharis/antigravity-skills	Skill	1.9k	23d ago	MIT	A	36	Claude Code
triaging-web-analytics-supportPostHog/posthog	Skill	41k	yesterday	none	A	151	Claude Code, Codex

ai-instructions: Skill for Cursor