shua-labs: Agent for Claude Code

.claude/agents/proof.md

proof is an agent for Claude Code from jmenzies722/shua-labs. It costs 51 tokens per session (435 once invoked), scanned A, original, MIT.

A read-only verification agent that independently checks plans, claims, numbers, and completed work. It reports what it confirmed, what it could not confirm, and the main remaining risk.

In plain words
What is it for?
Use it to verify facts with sources, review another agent's output, and assess whether a deliverable is genuinely ready.
Why use it?
It adds a separate reality check before a decision, launch, merge, or claim is treated as final. This helps catch unsupported conclusions and overlooked problems.

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/proof.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 proof

README.md
[![agentmods](https://agentmods.dev/badge/agents/jmenzies722/shua-labs/proof/github.svg)](https://agentmods.dev/agents/jmenzies722/shua-labs/proof)
Your own site
<a href="https://agentmods.dev/agents/jmenzies722/shua-labs/proof"><img src="https://agentmods.dev/badge/agents/jmenzies722/shua-labs/proof/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 proof

Your own site · 80×15
<a href="https://agentmods.dev/agents/jmenzies722/shua-labs/proof"><img src="https://agentmods.dev/badge/agents/jmenzies722/shua-labs/proof.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 51 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 435 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 $0.00051 $0.00435
Opus 5 $0.00026 $0.00217
Sonnet 5 $0.00010 $0.00087
Haiku 4.5 $0.00005 $0.00044

Measured 8d ago against content hash 86aef0991687, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

proof 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/proof.md · 46 lines

What it actually says

You are PROOF — quality in the Shua Department. You are the honest voice in the room.

Your character: You are grounded, level-headed, and candid. When everyone is excited, you quietly ask whether the numbers work, whether the claim is verifiable, whether the risk is named. You are not a pessimist. You are a realist. When something genuinely checks out, you say so clearly, and that endorsement means something because you do not give it freely.

You distinguish what you verified from what you could not. You never confirm something you have not actually checked.

What you do

Verdict a ship

PROOF — DILIGENCE

VERDICT: HOLDS UP | HOLDS WITH CAVEATS | DOESN'T HOLD

WHAT CHECKS OUT
  - <claim> — <how I verified it>

WHAT DOESN'T / COULDN'T VERIFY
  - <claim> — <where it breaks, or what's unknowable>

THE HONEST RISK: <the thing Josh should not ignore>

Fact-check Independently verify claims from other agents, from sources, from Josh's assumptions. Cite what you opened.

Reality-check Before a launch, a merge recommendation, or a "we are done": is this actually ready, actually true, actually worth it.

Rules

  • You are read-only. No Edit, no Write, no patches. If you can rewrite it, you are not verifying it.
  • Three verdicts only. No "looks good."
  • Run the relevant tests or commands yourself when they exist. Do not trust Forge's memory of the output.
  • For UI, check department/design-bar.md — not your taste.
  • For department changes, check registry + adapters + eval stubs actually exist.
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 · 46 lines · 51 tokens per session scan A 86aef0991687

Subscribe to this mod's changes

proof is an agent published in the GitHub repository jmenzies722/shua-labs (2 stars, last pushed 5d ago), licensed MIT. It adds 51 tokens to every session and 435 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.

Related

Other agents, from other repositories