themis-qa-auditor

themis-qa-auditor is an agent for Claude Code from arsenelupin14/THEMIS. It costs 31 tokens per session (201 once invoked), scanned A, original, MIT.

A review agent for Themis, a project that must stay within its defined scope. It checks the project and reports either PASS or FAIL with blocking and non-blocking issues.

In plain words
What is it for?
Use it to audit Themis for scope drift, weak claims, missing conflict examples, missing compressed state, and failed tests.
Why use it?
It catches unsupported claims, missing tests, unsafe installation instructions, and other changes that could move Themis away from its intended design.

Agent for Claude Code

Written for Claude Code: a Claude Code subagent (agents/*.md). Also seen: model in frontmatter; installed under .agents/ (shared by several agents).

Good fit Use it to audit Themis for scope drift, weak claims, missing conflict examples, missing compressed state, and failed tests.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/arsenelupin14/themis/themis-qa-auditor
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/arsenelupin14/THEMIS

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 themis-qa-auditor

README.md
[![agentmods](https://agentmods.dev/badge/agents/arsenelupin14/themis/themis-qa-auditor/github.svg)](https://agentmods.dev/agents/arsenelupin14/themis/themis-qa-auditor)
Your own site
<a href="https://agentmods.dev/agents/arsenelupin14/themis/themis-qa-auditor"><img src="https://agentmods.dev/badge/agents/arsenelupin14/themis/themis-qa-auditor/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 themis-qa-auditor

Your own site · 80×15
<a href="https://agentmods.dev/agents/arsenelupin14/themis/themis-qa-auditor"><img src="https://agentmods.dev/badge/agents/arsenelupin14/themis/themis-qa-auditor.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 31 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 201 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 $0.00031 $0.00201
Opus 5 $0.00015 $0.00101
Sonnet 5 $0.00006 $0.00040
Haiku 4.5 $0.00003 $0.00020

Measured 10d ago against content hash 6e9abe5e29c9, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

themis-qa-auditor 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.

.agents/agents/themis-qa-auditor.md · 36 lines

What it actually says

You are the Themis QA Auditor.

Be skeptical.

Fail the project if:

  • Themis becomes a standalone CLI.
  • Themis becomes a web app.
  • Themis copies MiroFish code, prompts, or assets.
  • Themis claims prediction capability.
  • Themis exposes private chain of thought.
  • Themis allows empty agreement.
  • Themis examples lack conflict/challenge.
  • Themis lacks compressed state.
  • Tests fail.
  • Install docs make unsupported claims.

Output:

  • PASS / FAIL
  • blocking issues
  • non-blocking issues
  • exact files to fix
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 · 36 lines · 31 tokens per session scan A 6e9abe5e29c9

Subscribe to this mod's changes

themis-qa-auditor is an agent published in the GitHub repository arsenelupin14/THEMIS (4 stars, last pushed 2mo ago), licensed MIT. It adds 31 tokens to every session and 201 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 2026-08-31.

Related

Other agents, from other repositories