agentmods.dev

korca-aura-agent AGENTS.md

korca-aura-agent AGENTS.md is an instructions file for Codex, OpenCode from alterminder/korca-aura-agent. It costs 531 tokens per session, scanned A, original, MIT.

A project guide for coding assistants working on the Korca Aura application. It records the software stack, important rules, where to begin, and how to check work.

In plain words
What is it for?
Use it when asking an assistant to change, debug, or review the Korca Aura codebase. It points work toward the correct backend or frontend guidance and verification steps.
Why use it?
It prevents assistants from breaking key project decisions, such as using only Neo4j Aura or keeping the existing password login. It also gives them the project context needed to make small, consistent changes.

Instructions file for CodexOpenCode

not rated 5 3d ago A scan 531 tokens original MIT
View the source file alterminder/korca-aura-agent
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 instructions/alterminder/korca-aura-agent/agents-md
Clone the repo
git clone --depth 1 https://github.com/alterminder/korca-aura-agent

Made for: Codex, OpenCode.

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 korca-aura-agent AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/alterminder/korca-aura-agent/agents-md.svg)](https://agentmods.dev/instructions/alterminder/korca-aura-agent/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/alterminder/korca-aura-agent/agents-md"><img src="https://agentmods.dev/badge/instructions/alterminder/korca-aura-agent/agents-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 531 This file is loaded in full into every session.
When invoked 531 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
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 $0.00531 $0.00531
Opus 5 $0.00266 $0.00266
Sonnet 5 $0.00106 $0.00106
Haiku 4.5 $0.00053 $0.00053

Measured 5d ago against content hash 419cb864d6a0, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

korca-aura-agent AGENTS.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 5d 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.md · 50 lines

How it starts

The opening of the file, as written. The whole thing — 50 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md

Shared instructions for AI assistants working on Korca Aura. This is the canonical guide; Claude Code loads it through CLAUDE.md, which imports this file.

Project Invariants

  • Korca Aura connects only to Neo4j Aura. Do not add a local Neo4j fallback.
  • Ticket routing uses the Neo4j Aura-hosted triage agent client in backend/app/services/aura_agent.py.
  • Basic password auth is required for the app. Keep it simple: one shared password, signed HttpOnly cookie sessions, no SSO/provider integrations unless explicitly requested.
  • Keep changes minimal, find root causes for bugs, and verify before reporting a task done.

Stack

Area Technology
Backend Python 3.11+, FastAPI, Pydantic
Frontend TypeScript, React 18, Vite, TailwindCSS
Database Neo4j Aura
LLM Gemini generation
Document processing PDF text extraction, Gemini generation, Gemini embeddings
Async work Celery with Redis
Routing agent Neo4j Aura-hosted agent

Where To Start

  • Backend work: read backend/AGENTS.md.
  • Frontend work: read frontend/AGENTS.md.
  • Code conventions (canonical patterns): agent_docs/conventions.md.
  • Commands and test guidance: agent_docs/commands.md and agent_docs/testing.md.
  • API route map: agent_docs/api-endpoints.md.
  • Neo4j/Cypher guidance: agent_docs/database.md.
  • PDF ingestion pipeline: agent_docs/pdf-pipeline.md.
  • Aura agent tools + prompt: docs/TOOLS.md.

Workflow

  • For non-trivial tasks, plan first and update the plan if new facts invalidate it.
  • Before editing, inspect the relevant files and follow existing patterns.
  • Prefer targeted tests or checks that match the changed area over broad suites that add noise.
  • Do not revert unrelated user changes in the working tree.

Commit & PR

  • Branch off main; open focused PRs against main (don't push to main).
  • Make the relevant checks green before pushing:
    • Backend (run in backend/): ruff check app, mypy app, pytest
    • Frontend (run in frontend/): npm run typecheck, npm run lint, npm run build
  • Never commit secrets, .env files, generated build output, or dependency dirs.

Read the full file on GitHub · 50 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. 5d ago First seen · 50 lines · 531 tokens per session scan A 419cb864d6a0

Subscribe to this mod's changes

korca-aura-agent AGENTS.md is an instructions file published in the GitHub repository alterminder/korca-aura-agent (5 stars, last pushed 3d ago), licensed MIT. It adds 531 tokens to every session, about $0.0027 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.

aiai-agentsauradb-agentfastapiknowledge-graphneo4j
Related

Other instructions, from other repositories

robosystems CLAUDE.md

Claude Code instructions for RoboFinSystems/robosystems, covering claude.md - robosystems development guide, critical rules, api endpoints (local testing), health check and extensions operation write (close a period).

RoboFinSystems/robosystems · 6,081 tokens

James-RAG-Evol CLAUDE.md

Claude Code instructions for Hashevolution/James-RAG-Evol, covering sekos / james — session briefing for claude code, what james is, where we are right now, critical rules for this session and where to look next.

Hashevolution/James-RAG-Evol · 9,410 tokens

WorldOfTaxonomy CLAUDE.md

Instructions for colaberry/WorldOfTaxonomy, covering claude.md - worldoftaxonomy, what this project is, architecture, tech stack and how to run.

colaberry/WorldOfTaxonomy · 16,396 tokens

akb AGENTS.md

AGENTS.md instructions for dnotitia/akb, covering akb project guide, architecture, frontend design system, 2-layer mcp architecture and deployment.

dnotitia/akb · 3,535 tokens

akb CLAUDE.md

Claude Code instructions for dnotitia/akb, covering claude guide for akb, mission, default work loop, pm collaboration and docs state machine.

dnotitia/akb · 977 tokens

okto-pulse CLAUDE.md

Claude Code instructions for OktoLabsAI/okto-pulse, covering claude.md — okto-pulse, docker architecture, multi-stage dockerfile, compose files and why the sibling-checkout pattern.

OktoLabsAI/okto-pulse · 3,857 tokens