diagnostician

diagnostician is an agent for Claude Code from skyfox675/agents-skills. It costs 100 tokens per session (662 once invoked), scanned A, original, MIT.

A read-only investigation worker that reproduces browser problems and traces cloud failures in AWS logs, settings, and audit records.

In plain words
What is it for?
Use it to reproduce a bug, inspect browser errors and requests, check AWS logs and CloudTrail, and return redacted evidence with numbered reproduction steps.
Why use it?
It gathers evidence without changing code, cloud resources, or application data, so developers can identify the cause safely.

Agent for Claude Code

Written for Claude Code: installed under .claude/. Also seen: model in frontmatter.

Good fit Use it to reproduce a bug, inspect browser errors and requests, check AWS logs and CloudTrail, and return redacted evidence with numbered reproduction steps.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/skyfox675/agents-skills/diagnostician
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.

Clone the repo
git clone --depth 1 https://github.com/skyfox675/agents-skills

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 diagnostician

README.md
[![agentmods](https://agentmods.dev/badge/agents/skyfox675/agents-skills/diagnostician/github.svg)](https://agentmods.dev/agents/skyfox675/agents-skills/diagnostician)
Your own site
<a href="https://agentmods.dev/agents/skyfox675/agents-skills/diagnostician"><img src="https://agentmods.dev/badge/agents/skyfox675/agents-skills/diagnostician/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.

agentmods 80×15 button for diagnostician

Your own site · 80×15
<a href="https://agentmods.dev/agents/skyfox675/agents-skills/diagnostician"><img src="https://agentmods.dev/badge/agents/skyfox675/agents-skills/diagnostician.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 100 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 662 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 $0.00100 $0.00662
Opus 5 $0.00050 $0.00331
Sonnet 5 $0.00020 $0.00132
Haiku 4.5 $0.00010 $0.00066

Measured 10d ago against content hash 36a48490b96b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

diagnostician 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 10d 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/agents/diagnostician.md · 18 lines

What it actually says

You are diagnostician — reproduce and root-cause; mutate nothing.

Follow the browser-diagnosis skill for the browser side and the gh-issue-use-aws command's rules (and the jira-issue twins) for the cloud side:

  • AWS: identity first (aws sts get-caller-identity); only get-*/describe-*/list-*/log reads/CloudTrail lookups. Forbidden: anything that creates, updates, deletes, invokes, or starts (other than a read query). Secrets stay sealed.
  • Browser: use whichever browser MCP is connected (Chrome, Playwright, Cypress, or Chrome DevTools) per the browser-diagnosis capability map; work in your OWN isolated context; mutate only to reproduce the symptom, against test data; redact tokens/cookies; avoid native dialogs. If no browser MCP is available, hand the operator repro steps instead of faking it.
  • Never edit code or open a PR. Your deliverable is evidence: the failing request/response (redacted), log excerpts with ARN + account/region, console errors with timestamps, numbered repro steps, GIF path.
  • Rabbit-hole guard: if a probe fails 2–3×, stop and report what you tried.

Caveman output; evidence byte-exact; flag anything that needs operator action.

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. 10d ago First seen · 18 lines · 100 tokens per session scan A 36a48490b96b

Subscribe to this mod's changes

diagnostician is an agent published in the GitHub repository skyfox675/agents-skills (10 stars, last pushed 9d ago), licensed MIT. It adds 100 tokens to every session and 662 once invoked, about $0.0005 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 2026-08-31.