agentmods.dev

quality-oracle: Instructions file for Claude Code

CLAUDE.md

quality-oracle CLAUDE.md is an instructions file for Claude Code from assister-xyz/quality-oracle. It costs 906 tokens per session, scanned A, original, MIT.

A project instruction file for working on Laureum.ai, a service that evaluates the quality of AI agents. It records the project's technology, data stores, evaluation process, and quality checks.

In plain words
What is it for?
It is for developing and testing the Laureum.ai service, which uses FastAPI, MongoDB, Redis, and several language-model providers to score agent responses.
Why use it?
It gives an assisting agent the project context needed to work in the right codebase and follow its existing checks. Without it, the agent may use the wrong port, data names, architecture, or workflow.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: mentions CLAUDE.md; positional $N argument.

This is assister-xyz/quality-oracle's own configuration. It tells Claude Code how to work on quality-oracle 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 quality-oracle configures →

Needs its repository: it reads a path above its own folder, which exists only inside the repository. The line is Part of **assisterr-workflow**. See `../assisterr-workflow/CLAUDE.md` for full workflow, sizing, spec lifecycle, memory entities, and agent routing..

not rated 0repo 4mo ago A scan 906 tokens original MIT
View source ↗ assister-xyz/quality-oracle
Reuse

Borrowing it

Nothing to install: this file belongs to assister-xyz/quality-oracle. 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/assister-xyz/quality-oracle/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/assister-xyz/quality-oracle

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 quality-oracle CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/assister-xyz/quality-oracle/claude-md/github.svg)](https://agentmods.dev/instructions/assister-xyz/quality-oracle/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/assister-xyz/quality-oracle/claude-md"><img src="https://agentmods.dev/badge/instructions/assister-xyz/quality-oracle/claude-md/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 quality-oracle CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/assister-xyz/quality-oracle/claude-md"><img src="https://agentmods.dev/badge/instructions/assister-xyz/quality-oracle/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 906 This file is loaded in full into every session.
When invoked 906 The same file — it is already loaded in full.
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 $0.00906 $0.00906
Opus 5 $0.00453 $0.00453
Sonnet 5 $0.00181 $0.00181
Haiku 4.5 $0.00091 $0.00091

Measured 9d ago against content hash 23fe5b471faa, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

quality-oracle CLAUDE.md 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 9d 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.md · 76 lines

How it starts

The opening of the file, as written. The whole thing — 76 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Laureum.ai (Quality Oracle)

Part of assisterr-workflow. See ../assisterr-workflow/CLAUDE.md for full workflow, sizing, spec lifecycle, memory entities, and agent routing.

Project Context

  • Port: 8002
  • Stack: FastAPI + Motor (MongoDB) + Redis
  • Brand: Laureum.ai (standard: AQVC — Agent Quality Verifiable Credential)
  • MongoDB prefix: quality__ (collections: evaluations, scores, score_history, attestations, question_banks, api_keys)
  • Redis prefix: qo: (score cache, badge cache, attestation verify cache, rate limits)
  • LLM Judge: Multi-provider (Cerebras, Groq, Gemini, DeepSeek, OpenAI, OpenRouter, Mistral) with ConsensusJudge (2-judge parallel + tiebreaker)
  • Domain agent: 32-implement-py handles this repo

Architecture

3-level evaluation pipeline:

  • Level 1 (Manifest): Schema completeness, descriptions, input schemas
  • Level 2 (Functional): MCP SSE connection → list tools → generate test cases → call tools → LLM judge responses
  • Level 3 (Domain Expert): Calibrated question bank with weighted scoring

6-axis scoring: accuracy(35%), safety(20%), process_quality(10%), reliability(15%), latency(10%), schema_quality(10%). Production correlation: POST /v1/feedback → GET /v1/correlation/{target_id} (anti-sandbagging, confidence adjustment).

JWT attestation via Ed25519 (AQVC format). MCP SDK SSE + Streamable HTTP dual transport. A2A v0.3 compliant Agent Card. Webhook-first async delivery for Level 2+.

x402 payment layer: Level 1 free, Level 2 $0.01, Level 3 $0.05 (base). Tier discounts: developer 20%, team 40%, marketplace 60%. Tokens: USDC + SOL on Solana. X-Payment header with tx_sig:token:network format. GET /v1/pricing for pricing table.

Running Locally

source .venv/bin/activate && unset GROQ_API_KEY && python3 -m uvicorn src.main:app --host 0.0.0.0 --port 8002 --reload

Important: Always unset GROQ_API_KEY before starting — a shell env variable overrides the .env key rotation pool.

Read the full file on GitHub · 76 lines

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. 9d ago First seen · 76 lines · 906 tokens per session scan A 23fe5b471faa

Subscribe to this mod's changes

quality-oracle CLAUDE.md is an instructions file published in the GitHub repository assister-xyz/quality-oracle (0 stars, last pushed 4mo ago), licensed MIT. It adds 906 tokens to every session, about $0.0045 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.

EvaluationTestingai-agentsmcpmcp-serverqualitytrust
Related

Other instructions, from other repositories

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,153 tokens

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 6,785 tokens

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).

microsoft/vscode · 5,001 tokens

langchain AGENTS.md

AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.

langchain-ai/langchain · 4,469 tokens

deepseek-harness AGENTS.md

AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.

deepseek-ai/deepseek-harness · 3,735 tokens