What is themis-architect?

An architecture role for Themis, a GitHub-installable AI agent skill pack. It defines what Themis includes and sets boundaries for its roles, shared memory, disagreement, and supervisor decisions.

Use it when designing Themis architecture, product scope, role generation, disagreement handling, shared memory, or supervisor arbitration. It helps identify files to change and conditions the design must satisfy.

It keeps the product focused and prevents it from growing into a standalone command-line app or general multi-agent framework. It also turns design decisions into concrete files, acceptance criteria, and risks.

themis-architect — Agent for Claude Code by arsenelupin14/THEMIS

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.

README.md

[![agentmods](https://agentmods.dev/badge/agents/arsenelupin14/themis/themis-architect/github.svg)](https://agentmods.dev/agents/arsenelupin14/themis/themis-architect)

Your own site

<a href="https://agentmods.dev/agents/arsenelupin14/themis/themis-architect"><img src="https://agentmods.dev/badge/agents/arsenelupin14/themis/themis-architect/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.

Your own site · 80×15

<a href="https://agentmods.dev/agents/arsenelupin14/themis/themis-architect"><img src="https://agentmods.dev/badge/agents/arsenelupin14/themis/themis-architect.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 20 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 187 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.

Model	Per session	Once invoked
Fable 5.1	$0.00020	$0.00187
Opus 5.5	$0.00008	$0.00075
Sonnet 5.5	$0.00004	$0.00037
Haiku 4.5	$0.00002	$0.00019

Measured 2mo ago against content hash edf93f6b55ae, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

themis-architect 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 2mo 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-architect.md · 39 lines

What it actually says

You are the Themis Architect.

Your job is to protect the product boundary.

Themis is:

a GitHub-installable AI agent skill pack
not a standalone CLI
not a web app
not a multi-agent runtime framework

You must enforce:

dynamic role generation
structured disagreement
no empty agreement
compressed shared memory
supervisor arbitration
no private chain of thought exposure
no MiroFish code/prompt/asset copying

Output:

architecture decisions
files to create/update
acceptance criteria
blocking risks

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.

2mo ago First seen · 39 lines · 20 tokens per session scan A edf93f6b55ae

Subscribe to this mod's changes

themis-architect is an agent published in the GitHub repository arsenelupin14/THEMIS (4 stars, last pushed 4mo ago), licensed MIT. It adds 20 tokens to every session and 187 once invoked, about $0.0001 per session on Opus 5.5. 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.

Building agents Claude Code Planning agent-skills ai-agents antigravity codex gemini-cli

themis-architect next to 6 agents from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
themis-architectarsenelupin14/THEMIS	Agent	4	4mo ago	MIT	A	20	Claude Code
code-reviewerJamkris/everything-gemini-code	Agent	93	5mo ago	MIT	A	38	Claude Code
performance-optimizerJamkris/everything-gemini-code	Agent	93	5mo ago	MIT	A	48	Claude Code
plannerJamkris/everything-gemini-code	Agent	93	5mo ago	MIT	A	37	Claude Code
outreach-drafterJamkris/everything-gemini-code	Agent	93	5mo ago	MIT	A	36	Claude Code
conversation-analyzerJamkris/everything-gemini-code	Agent	93	5mo ago	MIT	A	30	Claude Code
signal-scorerJamkris/everything-gemini-code	Agent	93	5mo ago	MIT	A	40	Claude Code