diagnose

diagnose is a skill for Claude Code from helderberto/agent-skills. It costs 98 tokens per session (2,108 once invoked), scanned A, a copy of diagnosing-bugs, MIT.

A step-by-step method for finding difficult software bugs and speed problems. It works by reproducing the problem, narrowing its cause, testing explanations, measuring the code, applying a fix, and checking for regressions.

In plain words
What is it for?
Use it to investigate broken behavior, failing tests, crashes, or performance slowdowns, especially when the cause is not immediately clear.
Why use it?
It replaces guesswork with a repeatable process and a clear pass-or-fail signal, such as a failing test. It also calls for checking nearby design notes and hiding secrets in diagnostic output.

Skill for Claude Code

Written for Claude Code: effort in frontmatter.

Part of the hb plugin — 40 skills, 6 agents shipped together

Install

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.

agentmods
npx agentmods add skills/helderberto/agent-skills/diagnose
Any agent
npx skills add helderberto/agent-skills --skill diagnose
Clone the repo
git clone --depth 1 https://github.com/helderberto/agent-skills

Made for: Claude Code.

Or install hb, the plugin that ships this one along with the rest of its 40 skills, 6 agents.

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/helderberto/agent-skills/diagnose.svg)](https://agentmods.dev/skills/helderberto/agent-skills/diagnose)
Your own site
<a href="https://agentmods.dev/skills/helderberto/agent-skills/diagnose"><img src="https://agentmods.dev/badge/skills/helderberto/agent-skills/diagnose.svg" alt="Measured on agentmods" height="20"></a>
Per session 98 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,108 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. Scan, not verified.
Origin 80% copy Near-identical to another mod 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 $0.00098 $0.02108
Opus 5 $0.00049 $0.01054
Sonnet 5 $0.00020 $0.00422
Haiku 4.5 $0.00010 $0.00211

Measured 2d ago against content hash 6e347c43014a, 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 1 finding 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 2d 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

Phase 1 is done when you can name **one command** (script path, test invocation, curl) that you have **already run at least once** — show the invocation and its output, redacted — and that is:
Origin

This is a copy

80% identical to diagnosing-bugs — 79 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

skills/diagnose/SKILL.md · 136 lines

How it starts

The opening of the file, as written. The whole thing — 136 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Diagnose

A discipline for hard bugs. Skip phases only when explicitly justified.

When exploring the codebase, build a clear mental model of the relevant modules and check any ADRs or design notes in the area you're touching.

Redact

This skill has you show commands, outputs, and captured artifacts. Redact every secret first: write <REDACTED> in its place. Build loops against env vars so credentials stay in the environment, not in what you show. Captured artifacts (HAR files, log dumps) carry auth headers — quote only the lines that carry signal. If redacted output isn't enough to diagnose, say so and ask the user.

Phase 1 — Build a feedback loop

This is the skill. Everything else is mechanical. If you have a fast, deterministic, agent-runnable pass/fail signal for the bug, you will find the cause — bisection, hypothesis-testing, and instrumentation all just consume that signal. If you don't have one, no amount of staring at code will save you.

Spend disproportionate effort here. Be aggressive. Be creative. Refuse to give up.

Ways to construct one — try them in roughly this order

  1. Failing test at whatever seam reaches the bug — unit, integration, e2e.
  2. Curl / HTTP script against a running dev server.
  3. CLI invocation with a fixture input, diffing stdout against a known-good snapshot.
  4. Headless browser script (Playwright / Puppeteer) — drives the UI, asserts on DOM/console/network.
  5. Replay a captured trace. Save a real network request / payload / event log to disk; replay it through the code path in isolation.
  6. Throwaway harness. Spin up a minimal subset of the system (one service, mocked deps) that exercises the bug code path with a single function call.
  7. Property / fuzz loop. If the bug is "sometimes wrong output", run 1000 random inputs and look for the failure mode.
  8. Bisection harness. If the bug appeared between two known states (commit, dataset, version), automate "boot at state X, check, repeat" so you can git bisect run it.
  9. Differential loop. Run the same input through old-version vs new-version (or two configs) and diff outputs.
  10. HITL loop. Last resort. If a human must click, drive them with a structured script — show one instruction, wait for Enter, capture the answer (y/n, pasted error text) back to you — so the loop stays disciplined instead of ad-hoc.

Read the full file on GitHub · 136 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. 2d ago Changed · +32 tokens per session 6e347c43014a
  2. 6d ago First seen · 136 lines · 66 tokens per session scan A 34885f8e3b97

Subscribe to this mod's changes

diagnose is a skill published in the GitHub repository helderberto/agent-skills (14 stars, last pushed 4d ago), licensed MIT. It adds 98 tokens to every session and 2,108 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). It is 80% identical to diagnosing-bugs, differing in 79 lines, and is treated as a copy.