agentmods.dev

deterministic

A local tool for validating intermediate representations and checking them against policy packs. It also compares exported results to detect drift, meaning unexpected differences over time.

In plain words
What is it for?
Use it to run IR and IR-LINT checks, apply policies, and compare exports for drift.
Why use it?
It helps identify validation failures, policy violations, and changes between an expected export and a later one without relying on a cloud service.

MCP server for Claude CodeCodexCursor

1 2d ago A scan tokens not measured no licence
View the source file archradhq/arch-deterministic
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.

agentmods
npx agentmods add mcp/archradhq/arch-deterministic/deterministic
Clone the repo
git clone --depth 1 https://github.com/archradhq/arch-deterministic

Made for: Claude Code, Codex, Cursor.

Per session not measured What this adds to a session before it is invoked.
When invoked not measured Not applicable: nothing here is loaded into a session.
Security scan A 0 findings. Scan, not verified.
Origin unknown No closer match found in the catalogue.
Security

Grade A, and why

deterministic 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 yesterday.

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.

server.json · 10 lines

The source is not reproduced here

No licence file

A repository with no LICENSE is all rights reserved by default, so the body is not copied here. The metadata, the measurements and the link are.

Read it on GitHub

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. yesterday First seen · 10 lines scan A 69a2d0248672

Subscribe to this mod's changes

deterministic is an MCP server published in the GitHub repository archradhq/arch-deterministic (1 stars, last pushed 2d ago), with no licence file. Its token cost is not measured: an MCP server costs its tool schemas, not its config file. 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.

Backend and APIsCode reviewDeterministicPlanningarchitectureclicodegenexpressfastapi
Related

Other mcp servers, from other repositories

knossos

MCP server "knossos" as configured in AraneaDev/Knossos-MCP. Launched with tools/mcp-serve --allow-root=..

AraneaDev/Knossos-MCP · not measured

strata

MCP server "strata" as configured in stratalib/strata. Runs C:\Users\user\Desktop\ALL PROJECTS\Recall V2\dist\src\mcp-server.js with node. Needs 1 environment variable to run.

stratalib/strata · not measured

figwright

MCP server "figwright" as configured in awdr74100/figwright. Runs packages/mcp/dist/index.mjs with node.

awdr74100/figwright · not measured

mcp-adr-analysis-server

AI-powered MCP server for analyzing Architectural Decision Records (ADRs). Runs locally from the mcp-adr-analysis-server npm package. Needs 4 environment variables to run.

tosin2013/mcp-adr-analysis-server · not measured

knowledge-inbox

MCP server "knowledge-inbox" as configured in lyc403223157-source/knowledge-inbox. Runs locally from the knowledge-inbox Python package.

lyc403223157-source/knowledge-inbox · not measured

reelier

Agents make claims, Reelier writes receipts - record an agent workflow once, replay it deterministically at 0 tokens, and get an asserted receipt on every run. Runs locally from the reelier npm package.

seldonframe/reelier · not measured