Borrowing it
Nothing to install: this file belongs to zyqzyq/Unfour. 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/zyqzyq/Unfour/main/AGENTS.mdgit clone --depth 1 https://github.com/zyqzyq/UnfourWrote 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/zyqzyq/unfour/agents-md)<a href="https://agentmods.dev/instructions/zyqzyq/unfour/agents-md"><img src="https://agentmods.dev/badge/instructions/zyqzyq/unfour/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/zyqzyq/unfour/agents-md"><img src="https://agentmods.dev/badge/instructions/zyqzyq/unfour/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 | $0.00788 | $0.00788 |
| Opus 5.5 | $0.00315 | $0.00315 |
| Sonnet 5.5 | $0.00158 | $0.00158 |
| Haiku 4.5 | $0.00079 | $0.00079 |
Grade A, and why
Unfour 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 1mo 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 — 63 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Unfour Repository Instructions
Unfour is a lightweight IDE-style desktop developer tool built on Tauri 2, React, TypeScript, and Rust. Its core modules are API Client, SSH Terminal, Database, and Workspace.
Architecture and security invariants
- Feature business state and components belong in their owning packages or
crates.
packages/app-shellowns global layout, navigation, route assembly, and module slots only; no request execution, SQL editing/execution, SSH session state, feature mock data, or large feature components. packages/uiowns reusable, feature-neutral primitives; no business logic or feature imports. Feature packages must not depend on app-shell, other feature packages, workspace-local, or a future workspace-sync package.- Shared frontend contracts come from
packages/command-client,packages/workspace-core, andpackages/ui. workspace-core owns shared workspace state; workspace-local reserves local lifecycle, persistence, import/export, recent-workspace, and migration behavior. - Frontend interaction lives in React/TypeScript; execution and security
boundaries live in Rust. Frontend backend calls use command-client.
Business actions follow
adapter -> CommandBus -> service -> driver. Tauri and MCP adapters must not duplicate domain logic. apps/desktop/src-tauriis the desktop adapter/composition layer; shared Tauri composition lives incrates/unfour-app, capabilities in owning crates.- Every persisted business record carries
workspace_id, except truly global app configuration. - Persist credential references, never plaintext passwords, private keys,
passphrases, or tokens in SQLite. Redact
authorization,cookie,proxy-authorization,x-api-key, andx-auth-tokenin logs, history, and local activity details. - Cloud-bound local mutations retain durable outbox intent in the business
transaction regardless of login, active account, entitlement, pause, offline,
or worker state. Each local workspace has at most one durable Cloud Sync
owner
(account_id, cloud_workspace_id); mutations and repair resolve that owner and never fan out across historical bindings. - New user-visible frontend copy uses the shared i18n provider/hook and locale keys. Do not create package-local translation systems. MCP tool names, schemas, command names/keys, event names, request metadata keys, and stable error codes stay English; localize only UI-facing messages.
- Unfour's UI style is fixed. Its only design authorities are design.md, design-system.md, and interaction-guidelines.md. Use relevant sections for UI work; do not generate a competing design system.
- Add dependencies only when the task requires them and document the reason. Keep changes scoped and preserve uncommitted user work.
- Current release readiness and verification evidence belong in
docs/release/anddocs/testing/;docs/archive/is historical context. Internal engineering and agent docs do not need translations unless requested.
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.
- 1mo ago Changed · -105 lines · -740 tokens per session 612c04c78280
- 2mo ago Changed · +6 lines · +89 tokens per session daf4c0ac67dd
- 2mo ago First seen · 162 lines · 1,439 tokens per session scan A 58db1f010d7a
Unfour AGENTS.md is an instructions file published in the GitHub repository zyqzyq/Unfour (2 stars, last pushed yesterday), licensed Apache-2.0. It adds 788 tokens to every session, about $0.0032 per session on Opus 5.5. 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.
Unfour AGENTS.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| Unfour AGENTS.mdzyqzyq/Unfour | Instructions file | 2 | yesterday | Apache-2.0 | A | 788 | Codex, OpenCode |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 9,719 | GitHub Copilot |
| next.js AGENTS.mdvercel/next.js | Instructions file | 143k | yesterday | MIT | A | 7,461 | Codex, OpenCode |
| langchain AGENTS.mdlangchain-ai/langchain | Instructions file | 149k | yesterday | MIT | A | 4,680 | Codex, OpenCode |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 5,516 | GitHub Copilot |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 3,093 | GitHub Copilot |
| deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness | Instructions file | 274k | 2d ago | MIT | A | 4,313 | Codex, OpenCode |