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.
npx agentmods add instructions/amszuidas/mini-opencode/claude-mdgit clone --depth 1 https://github.com/amszuidas/mini-opencodeWhat 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 | $0.00744 | $0.00744 |
| Opus 5 | $0.00372 | $0.00372 |
| Sonnet 5 | $0.00149 | $0.00149 |
| Haiku 4.5 | $0.00074 | $0.00074 |
Grade A, and why
mini-opencode 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 2d 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 — 70 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
Commands
# Install dependencies
uv sync
# Run the agent on a target project
uv run -m mini_opencode /path/to/project
# Build the package
uv build
# Start LangGraph dev server (for graph visualization)
make dev
# Opens at: https://smith.langchain.com/studio/?baseUrl=http://127.0.0.1:2024
# Lint/format
ruff check .
ruff format .
No automated test suite is currently present.
Configuration
Copy config.example.yaml to config.yaml and .example.env to .env. The config supports:
- models.chat_model: LLM provider (deepseek, kimi, openai) with API key via
$ENV_VAR - tools.enabled: List of optional tools (
web_search,web_fetch,bocha_web_search) - tools.mcp_servers: Dynamic MCP tool servers (streamable_http or stdio transport)
Architecture
Agent Layer (src/mini_opencode/agents/)
create_coding_agent() in coding_agent.py builds the LangGraph agent via deepagents.create_deep_agent(). It wires together:
- The LLM (from
models/chat_model.py) - Built-in deepagents tools (file ops:
read_file,write_file,edit_file,glob,grep; shell:execute; task management:write_todos; sub-agents:task) - Optional custom tools from
tools/(web search, date, MCP) - Jinja2-rendered system prompt from
prompts/templates/coding_agent.md MemorySavercheckpointer for conversation state- Auto-discovered skills from the target project's
skills/directory
CLI Layer (src/mini_opencode/cli/)
Textual-based TUI with:
app.py(ConsoleApp): Root Textual app, 3:4 left/right split layoutcontrollers/agent_controller.py: Core logic — initializes agent, streams responses viaastream(), routes tool calls to UI panels (terminal tools →TerminalView, file tools →EditorViewtabs, todos →TodoView)controllers/command_controller.py: Handles slash commands (/clear,/exit)- Components:
chat/,editor/,terminal/,todo/undercli/components/
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.
- 2d ago First seen · 70 lines · 744 tokens per session scan A bdc0fb058de2
mini-opencode CLAUDE.md is an instructions file published in the GitHub repository amszuidas/mini-opencode (118 stars, last pushed 6mo ago), licensed MIT. It adds 744 tokens to every session, about $0.0037 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.
Other instructions, from other repositories
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
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).
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.
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.
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).
next.js AGENTS.md
Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.