Borrowing it
Nothing to install: this file belongs to Wardell-Stephen-CurryII/OpenNova. 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/Wardell-Stephen-CurryII/OpenNova/master/AGENTS.mdgit clone --depth 1 https://github.com/Wardell-Stephen-CurryII/OpenNovaWrote 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/wardell-stephen-curryii/opennova/agents-md)<a href="https://agentmods.dev/instructions/wardell-stephen-curryii/opennova/agents-md"><img src="https://agentmods.dev/badge/instructions/wardell-stephen-curryii/opennova/agents-md/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/instructions/wardell-stephen-curryii/opennova/agents-md"><img src="https://agentmods.dev/badge/instructions/wardell-stephen-curryii/opennova/agents-md.svg" alt="Reviewed on agentmods" width="80" 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 | $0.01668 | $0.01668 |
| Opus 5 | $0.00834 | $0.00834 |
| Sonnet 5 | $0.00334 | $0.00334 |
| Haiku 4.5 | $0.00167 | $0.00167 |
Grade A, and why
OpenNova 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 10d 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 — 130 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
This file describes the current OpenNova repository for coding agents and contributors.
Project
OpenNova 0.4.3 is a Python 3.11+ terminal AI coding agent. Textual is the only interactive interface; the legacy interactive CLI and standalone opennova tui command have been removed. The Click entry point remains for launching the TUI, setup/inspection commands, and one-shot non-interactive tasks.
Core capabilities include multi-provider LLM access, a ReAct runtime, 40 built-in tools, Plan/Act workflows, persistent sessions, transcript replay, context compression, layered memory, Skills, trusted plugins, hooks, MCP, worktrees, local automation, checkpoints, and security policies.
Setup and commands
uv sync
uv sync --dev
uv run opennova init
# Textual TUI
uv run opennova
uv run opennova --resume
uv run opennova --continue
# One-shot tasks
uv run opennova run "Read README.md"
uv run opennova run --plan "Refactor session persistence"
uv run opennova run --provider deepseek -m deepseek-v4-pro "Review src/"
# Inspection
uv run opennova --version
uv run opennova list-tools
uv run opennova config
Do not document opennova tui; it is not a command. Do not describe the removed line-oriented interactive CLI as a current interface.
Verification
LC_ALL=en_US.UTF-8 LANG=en_US.UTF-8 PYTHONUTF8=1 uv run pytest
uv run ruff check src/ tests/
uv run ruff format --check src/ tests/
uv run mypy src/opennova
For focused work, run the smallest relevant pytest file first. The UTF-8 environment avoids Python startup failures when the repository path contains Chinese characters.
Architecture
src/opennova/main.py: Click entry point for TUI startup, one-shot tasks, setup, and inspectionsrc/opennova/cli/: Textual workbench, dialogs, message blocks, tool cards, slash commands, and Windows driver supportsrc/opennova/runtime/: Agent orchestration, ReAct loop, canonical events, state, and persistence bridgesrc/opennova/providers/: OpenAI, Anthropic, and DeepSeek providers plus factorysrc/opennova/tools/: tool base/registry and 40 built-in toolssrc/opennova/session/: JSONL v2 snapshots, runtime events, legacy loading, and resume metadatasrc/opennova/memory/: context compression, working/project memory, retrieval, and layered memorysrc/opennova/planning/: plan data and plannersrc/opennova/security/: guardrails, permission rules, command/network policy, redaction, audit, file sandbox, and process sandboxsrc/opennova/skills/: directory-basedSKILL.mddiscovery, namespacing, activation, and bundled skillssrc/opennova/mcp/: stdio/SSE connectors, remote tools, and resourcessrc/opennova/plugins.pyandsrc/opennova/hooks.py: trusted project extensionssrc/opennova/automation.py: local scheduler and daemon supportsrc/opennova/checkpoints.pyandsrc/opennova/transcript.py: rollback metadata and exportssrc/opennova/sdk.py: headlessOpenNovaClientand normalizedSDKEvent
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.
- 10d ago First seen · 130 lines · 1,668 tokens per session scan A d13a7280ff98
OpenNova AGENTS.md is an instructions file published in the GitHub repository Wardell-Stephen-CurryII/OpenNova (22 stars, last pushed 1mo ago), licensed MIT. It adds 1,668 tokens to every session, about $0.0083 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
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).
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 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).
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.