llms: Skill for Claude Code

.claude/skills/diagnose/SKILL.md

diagnose is a skill for Claude Code from matteocervelli/llms. It costs 40 tokens per session (1,880 once invoked), scanned A, original, MIT.

A read-only investigation process for bugs whose root cause is not yet known. It keeps hypotheses and findings so an investigation can continue later.

In plain words
What is it for?
Use it to investigate an unknown bug, compare possible causes, and produce a root-cause report before applying a fix.
Why use it?
It prevents premature fixes when the reason for the failure is unclear and gives the investigation a repeatable structure.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: mentions subagents.

This is matteocervelli/llms's own configuration. It tells Claude Code how to work on llms itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything llms configures →

Reuse

Borrowing it

Nothing to install: this file belongs to matteocervelli/llms. 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/matteocervelli/llms/main/.claude/skills/diagnose/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/matteocervelli/llms

Made for: Claude Code.

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.

agentmods badge for diagnose

README.md
[![agentmods](https://agentmods.dev/badge/skills/matteocervelli/llms/diagnose.svg)](https://agentmods.dev/skills/matteocervelli/llms/diagnose)
Your own site
<a href="https://agentmods.dev/skills/matteocervelli/llms/diagnose"><img src="https://agentmods.dev/badge/skills/matteocervelli/llms/diagnose.svg" alt="Measured on agentmods" height="20"></a>
Per session 40 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,880 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00040 $0.01880
Opus 5 $0.00020 $0.00940
Sonnet 5 $0.00008 $0.00376
Haiku 4.5 $0.00004 $0.00188

Measured 3d ago against content hash 8f2ad4dbc55e, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

diagnose 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 3d 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.

.claude/skills/diagnose/SKILL.md · 253 lines

How it starts

The opening of the file, as written. The whole thing — 253 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Diagnose Skill

Purpose

Investigation skill for bugs where the root cause is unknown. When you don't know why something is broken — just that it is — use /diagnose before reaching for /fix.

Key mechanism: spawns a fresh-context debugger subagent (Task tool) alongside a /review solve companion analysis. The main agent orchestrates, stays clean, and synthesizes results. Debug sessions persist in .claude/debug/<slug>.md so they survive context compaction and can be resumed.

Not for: applying a fix you already understand (use /fix), or quick one-line patches (use /quick).


When to Use

/quick /fix /diagnose /implementation
Root cause known? Yes Yes No Yes
Code changes Yes Yes No (read-only) Yes
Subagent isolation No No Yes (fresh 200k context) No
Companion analysis No No Yes (/review solve) No
Output Commit Commit Root cause report PR

Usage

/diagnose "auth token not working"          # start new session
/diagnose --resume auth-token               # resume session by slug
/diagnose --list                            # show all active sessions
/diagnose --close auth-token               # mark session resolved
/diagnose --issue 42                        # pull symptoms from GitHub issue
/diagnose --issue 42 "login fails on iOS"   # issue + free-form description

Workflow

Step 1: Collect Symptoms

Ask the user for (or pull from gh issue view <N> if --issue provided):

  • Expected — what should happen
  • Actual — what is happening
  • Error — exact error message or stack trace (if any)
  • Timeline — when did this start, what changed recently
  • Reproduction — minimal steps to reproduce

Read the full file on GitHub · 253 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.

  1. 3d ago First seen · 253 lines · 40 tokens per session scan A 8f2ad4dbc55e

Subscribe to this mod's changes

diagnose is a skill published in the GitHub repository matteocervelli/llms (25 stars, last pushed 3mo ago), licensed MIT. It adds 40 tokens to every session and 1,880 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 2026-09-03.

Related

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…

ChromeDevTools/chrome-devtools-mcp · 99 tokens

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.

open-metadata/OpenMetadata · 37 tokens

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.

emdash-cms/emdash · 43 tokens

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.

emdash-cms/emdash · 48 tokens

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…

zebbern/claude-code-guide · 71 tokens

byted-util-volcengine-detect-retry

An orchestration workflow for Volcengine Cloud Detect, a service that checks websites or network endpoints from test locations.

bytedance/agentkit-samples · 101 tokens