opencode-ollama-steroids: Instructions file for Codex

AGENTS.md

opencode-ollama-steroids AGENTS.md is an instructions file for Codex, OpenCode from pillaiharish/opencode-ollama-steroids. It costs 1,732 tokens per session, scanned A, original, Apache-2.0.

A set of rules for an OpenCode workspace that uses Ollama, a tool for running AI models locally or through configured services. It describes the workspace layout and roles for builder and reviewer agents.

In plain words
What is it for?
Use it when planning, coding, reviewing, and reporting work across the configured product repository and agent sessions.
Why use it?
It reduces the risk of exposing private prompts, logs, user data, tokens, or machine-specific file paths in public files.

Instructions file for CodexOpenCode

Written for Codex and OpenCode: the file is AGENTS.md. Also seen: mentions AGENTS.md; mentions OpenCode.

This is pillaiharish/opencode-ollama-steroids's own configuration. It tells Codex and OpenCode how to work on opencode-ollama-steroids 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 opencode-ollama-steroids configures →

Reuse

Borrowing it

Nothing to install: this file belongs to pillaiharish/opencode-ollama-steroids. 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/pillaiharish/opencode-ollama-steroids/main/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/pillaiharish/opencode-ollama-steroids

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 opencode-ollama-steroids AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/pillaiharish/opencode-ollama-steroids/agents-md.svg)](https://agentmods.dev/instructions/pillaiharish/opencode-ollama-steroids/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/pillaiharish/opencode-ollama-steroids/agents-md"><img src="https://agentmods.dev/badge/instructions/pillaiharish/opencode-ollama-steroids/agents-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 1,732 This file is loaded in full into every session.
When invoked 1,732 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 5.1 $0.01732 $0.01732
Opus 5 $0.00866 $0.00866
Sonnet 5 $0.00346 $0.00346
Haiku 4.5 $0.00173 $0.00173

Measured 6d ago against content hash 69bf8090106b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

opencode-ollama-steroids 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 6d 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 · 244 lines

How it starts

The opening of the file, as written. The whole thing — 244 lines — stays where its author put it; the contents beside it link to each section on GitHub.

OpenCode + Ollama Agent Rules

These rules define a public-safe control workspace for a two-agent OpenCode + Ollama workflow.

The workspace contains shared instructions, OpenCode config, local prompt/session folders, and a product repository. Do not add private prompts, raw logs, screenshots, usernames, emails, tokens, customer data, private repo details, or local absolute paths to public files.

Workspace layout

Control workspace:

.

Product repository, configured locally through project.local.env:

${PRODUCT_DIR:-product-repo}

Agent session material:

agent-sessions/<project-slug>/<prompt-id>/

Required path rule:

  • Use relative paths only.
  • Do not use absolute paths starting with /Users, /home, /var/folders, C:\Users, or other machine-specific prefixes.
  • The product repo must be referenced through PRODUCT_DIR or a relative folder name such as product-repo.
  • Do not copy private prompt text into public docs.

Agents

minimax-builder

Model: ollama/minimax-m3:cloud Model family: minimax-m

Role: planner, coder, test runner, implementation reporter.

Responsibilities:

  1. Read AGENTS.md.
  2. Read the current prompt file under agent-sessions/<project-slug>/<prompt-id>/PROMPT_CODER.md.
  3. Read previous redacted handoff files if present.
  4. Create a scoped plan.
  5. Request reviewer plan feedback before implementation when the workflow requires it.
  6. Implement only the approved scope.
  7. Run the required validation commands.
  8. Write implementation notes, test results, fixes, and current state under the current session folder.
  9. Fix blocking issues only inside the approved scope.
  10. Stop after current prompt completion.

The builder may edit product code and run commands, but it must not:

  • commit
  • push
  • rebase
  • force-push
  • start the next prompt
  • weaken tests to pass
  • delete unrelated files
  • edit reviewer-only files
  • publish raw prompts or raw sessions
  • write files outside the product repo or current session folder unless explicitly instructed

Read the full file on GitHub · 244 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. 6d ago First seen · 244 lines · 1,732 tokens per session scan A 69bf8090106b

Subscribe to this mod's changes

opencode-ollama-steroids AGENTS.md is an instructions file published in the GitHub repository pillaiharish/opencode-ollama-steroids (5 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 1,732 tokens to every session, about $0.0087 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.