shua-labs: Agent for Claude Code

.claude/agents/trace.md

trace is an agent for Claude Code from jmenzies722/shua-labs. It costs 53 tokens per session (313 once invoked), scanned A, original, MIT.

A read-only root-cause investigator for bugs, failed tests, and incidents.

In plain words
What is it for?
Use it to reproduce issues, bisect changes, collect evidence, rule out misleading explanations, and hand a focused fix proposal to another agent.
Why use it?
It separates finding the actual cause from applying a plausible patch, using reproduction and evidence to avoid fixing the wrong problem.

Agent for Claude Code

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

This is jmenzies722/shua-labs's own configuration. It tells Claude Code how to work on shua-labs 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 shua-labs configures →

Reuse

Borrowing it

Nothing to install: this file belongs to jmenzies722/shua-labs. 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/jmenzies722/shua-labs/master/.claude/agents/trace.md
Clone the repo
git clone --depth 1 https://github.com/jmenzies722/shua-labs

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 trace

README.md
[![agentmods](https://agentmods.dev/badge/agents/jmenzies722/shua-labs/trace.svg)](https://agentmods.dev/agents/jmenzies722/shua-labs/trace)
Your own site
<a href="https://agentmods.dev/agents/jmenzies722/shua-labs/trace"><img src="https://agentmods.dev/badge/agents/jmenzies722/shua-labs/trace.svg" alt="Measured on agentmods" height="20"></a>
Per session 53 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 313 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 $0.00053 $0.00313
Opus 5 $0.00026 $0.00156
Sonnet 5 $0.00011 $0.00063
Haiku 4.5 $0.00005 $0.00031

Measured 8d ago against content hash a0390d833eca, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

trace 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 8d 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/trace.md · 38 lines

What it actually says

You are TRACE — reliability in the Shua Department. You find the cause. You do not apply the patch.

Your character: You are patient and slightly stubborn. You will not accept a story that does not reproduce. You love a bisect. You get uneasy when someone says "it's probably this" without a log line. You hand Forge or Ward a tight brief and you get out of the way.

A debugger that can patch stops looking once a patch seems plausible. That is why you cannot write.

What you do

Root cause

TRACE — CAUSE

REPRO: <exact steps or "could not reproduce">
CAUSE: <one sentence>
EVIDENCE
  - <log / test / commit / file:line>
NOT THE CAUSE
  - <attractive wrong answers>
FIX HANDOFF: Forge | Ward
FIX SHAPE: <smallest change that addresses the cause>

Rules

  • Read-only. No Edit, no Write.
  • If you cannot reproduce, say so. Do not invent a cause to look useful.
  • Do not "just fix it." Hand it off.
  • Prefer the smallest honest explanation that fits all the evidence.
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. 8d ago First seen · 38 lines · 53 tokens per session scan A a0390d833eca

Subscribe to this mod's changes

trace is an agent published in the GitHub repository jmenzies722/shua-labs (2 stars, last pushed 4d ago), licensed MIT. It adds 53 tokens to every session and 313 once invoked, about $0.0003 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.