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 agents/zyqzyq/unfour/project_stategit 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/agents/zyqzyq/unfour/project_state)<a href="https://agentmods.dev/agents/zyqzyq/unfour/project_state"><img src="https://agentmods.dev/badge/agents/zyqzyq/unfour/project_state.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 | $0.00000 | $0.02561 |
| Opus 5 | $0.00000 | $0.01281 |
| Sonnet 5 | $0.00000 | $0.00512 |
| Haiku 4.5 | $0.00000 | $0.00256 |
Grade A, and why
PROJECT_STATE 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 4d 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 — 142 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Project State
Scan Metadata
- Scanned at: 2026-06-14 (release readiness smoke verification pass)
- Branch: main
- Base commit:
1a542cb— fix(release): address smoke verification blockers - Working tree: Clean (no source code changes in this pass)
- Release status: Technically stable but not ready for early basic release. Live SSH server verification is the current release gate.
Tech Stack
- Desktop shell: Tauri 2 (Rust + WebView)
- Frontend: React 19, TypeScript, Vite, Tailwind CSS, Radix UI, TanStack Query, Zustand
- Backend: Rust, Tokio, SQLite, PostgreSQL, and MySQL via sqlx, russh (SSH native), keyring (OS credential storage with platform-native backends)
- Build: pnpm workspace (7 packages), Cargo workspace (7 crates + Tauri adapter)
- Test: Vitest (frontend), Cargo Test (Rust)
Current Phase
The application is technically stable: all automated tests pass (98 Rust, 60 frontend), the production build succeeds, Windows keychain is runtime-verified, and browser UI smoke passes. However, the app is not ready for early basic release because live SSH server verification — the core use case for the Terminal module — remains NOT VERIFIED against a reachable SSH server.
SSH authentication UX — including private-key authentication, SecretStore-backed key references, host-key fingerprint management, and terminal streaming — is code-complete. SQLite, PostgreSQL, and MySQL/MariaDB database paths are implemented and were live-verified in a previous checkpoint (not rerun in this smoke pass; see Verification Results). The keyring crate now uses platform-native backends: windows-native (Windows Credential Manager), apple-native (Apple Keychain), and crypto-rust + sync-secret-service (Linux Secret Service). Windows Credential Manager create/read/delete is runtime-verified for four credential categories. Apple Keychain and Linux Secret Service are configured but not runtime-verified.
UI module split is in progress. Terminal, Database, Workspace, and Command-Client packages have been extracted from packages/app-shell. Workspace dialogs, window controls, and the title bar are extracted into dedicated component files within apps/desktop/src/components/. Semantic token replacement is complete. Lint warnings reduced from 64 to 53. packages/app-shell contains only the AppShell layout composition wrapper (2 source files).
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.
- 4d ago First seen · 142 lines · 0 tokens per session scan A 3ce682d424ec
PROJECT_STATE is an agent published in the GitHub repository zyqzyq/Unfour (2 stars, last pushed today), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 2,561 tokens. 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 agents, from other repositories
altai-implementer
Implements one bounded ALTAI roadmap slice and its tests. Default working agent for roadmap PRs.
altai-explorer
Read-only ALTAI repository exploration. Use when file ownership or existing patterns are unclear before implementing a roadmap item.
altai-reviewer
Read-only diff review for a risky ALTAI PR. Reports actionable findings only.
altai-test-triage
Triages failing tests/logs into product defects, flaky tests, environment problems, and pre-existing failures.
Test Engineer
Writes tests first, then implementation. Strict TDD.
researcher
Sample subagent that does focused research on a single question.