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.
curl -O https://raw.githubusercontent.com/pillaiharish/opencode-ollama-steroids/main/AGENTS.mdgit clone --depth 1 https://github.com/pillaiharish/opencode-ollama-steroidsWrote 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.
[](https://agentmods.dev/instructions/pillaiharish/opencode-ollama-steroids/agents-md)<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>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.
| Model | Per session | Once 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 |
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.
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_DIRor a relative folder name such asproduct-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:
- Read
AGENTS.md. - Read the current prompt file under
agent-sessions/<project-slug>/<prompt-id>/PROMPT_CODER.md. - Read previous redacted handoff files if present.
- Create a scoped plan.
- Request reviewer plan feedback before implementation when the workflow requires it.
- Implement only the approved scope.
- Run the required validation commands.
- Write implementation notes, test results, fixes, and current state under the current session folder.
- Fix blocking issues only inside the approved scope.
- 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
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.
- 6d ago First seen · 244 lines · 1,732 tokens per session scan A 69bf8090106b
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.
Other instructions, from other repositories
plan-forge dapr.instructions.md
Dapr patterns for .NET — building blocks, component config, sidecar architecture, multi-tenant isolation, workflows, state management, secrets.
plan-forge caching.instructions.md
Caching patterns for .NET — IDistributedCache, Redis, in-memory, cache-aside, TTL strategies.
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.
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.
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).
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).