ollama-agent AGENTS.md

ollama-agent AGENTS.md is an instructions file for Codex, OpenCode from arrase/ollama-agent. It costs 389 tokens per session, scanned A, original, MIT.

Repository-specific instructions for developing and testing the ollama-agent command-line tool and interactive terminal application. They describe its Python commands, coding rules, dependencies, and architecture.

In plain words
What is it for?
Use them when modifying ollama-agent, running its unit tests, installing it in editable mode, or understanding its agent runtime and checkpointing setup.
Why use it?
They give a coding agent the project rules it must follow, reducing inconsistent changes and incorrect test or installation commands.

Instructions file for CodexOpenCode

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/arrase/ollama-agent/agents-md
Clone the repo
git clone --depth 1 https://github.com/arrase/ollama-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 ollama-agent AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/arrase/ollama-agent/agents-md.svg)](https://agentmods.dev/instructions/arrase/ollama-agent/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/arrase/ollama-agent/agents-md"><img src="https://agentmods.dev/badge/instructions/arrase/ollama-agent/agents-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 389 This file is loaded in full into every session.
When invoked 389 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 $0.00389 $0.00389
Opus 5 $0.00195 $0.00195
Sonnet 5 $0.00078 $0.00078
Haiku 4.5 $0.00039 $0.00039

Measured 4d ago against content hash 582389b68a22, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

ollama-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 4d 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 · 32 lines

What it actually says

Ollama Agent - AI Agent Guidelines

This repository contains the ollama-agent CLI and interactive REPL application built on top of DeepAgents, LangChain, and LangGraph.

Development & Test Commands

  • Run Unit Tests:
    .venv/bin/python -m unittest discover -s tests
    
  • Install in Editable Mode:
    .venv/bin/pip install -e .
    

Coding Conventions & Engineering Rules

  • KISS & Zero Defensive Bloat: Write minimal, straightforward code. Avoid artificial abstractions, unnecessary wrappers, or unsolicited fallbacks. Fail fast and fail loud when invariants are violated.
  • Top-Level Imports Only: All import and from ... import statements must reside at the very top of each Python file (PEP 8 standard). Never use function-level or inline imports.
  • Virtual Environment: Always execute Python scripts, tools, and test suites using the project's virtual environment (.venv/bin/python).
  • Dependency Management: Dependencies are declared strictly in pyproject.toml.

Architecture & Context

  • Agent Runtime: Stateful graph orchestration using deepagents.create_deep_agent and langgraph-checkpoint-sqlite checkpointing.
  • Memory & Guidelines:
    • ~/.ollama-agent/MEMORY.md: Long-term persistent user memory across sessions.
    • AGENTS.md: Project-specific instructions loaded into memory at startup.
  • REPL & TUI: Interactive Textual-based interface in ollama_agent/interfaces/repl.py.
  • RAG Engine: Vector store queries via Qdrant and Ollama embeddings in ollama_agent/rag/.
  • MCP & Skills: Subagent tools via Model Context Protocol and the Agent Skills specification.
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. 4d ago First seen · 32 lines · 389 tokens per session scan A 582389b68a22

Subscribe to this mod's changes

ollama-agent AGENTS.md is an instructions file published in the GitHub repository arrase/ollama-agent (20 stars, last pushed yesterday), licensed MIT. It adds 389 tokens to every session, about $0.0019 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 2026-08-30.