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 rules/mannansaood/termi/00-project-overviewgit clone --depth 1 https://github.com/MannanSaood/termiWhat 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 | $0.00584 | $0.00584 |
| Opus 5 | $0.00292 | $0.00292 |
| Sonnet 5 | $0.00117 | $0.00117 |
| Haiku 4.5 | $0.00058 | $0.00058 |
Grade A, and why
00-project-overview 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 — 54 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Termi — Project Overview
Termi is a pre-alpha Android terminal emulator: a Rust core (PTY, ANSI parsing, VFS/SAF bridge) driving a Jetpack Compose UI over JNI. The differentiated bet is a capability-aware virtual filesystem that tells users upfront what will and won't work on Android's Storage Access Framework (chmod, symlinks, etc.), instead of silently failing the way Termux does.
Repo layout
rust/— the core engine.cargo build/cargo testwith no flags builds and tests the platform-independent logic (PTY, terminal, VFS, capability system) on a plain host toolchain. No Android SDK/NDK needed for this. Use--features androidto additionally compile the JNI boundary against the realjnicrate (type-checks on host; only truly runs on-device).android/— Kotlin/Compose app. Calls into the Rust core via JNI.docs/— architecture, roadmap, limitations, andPHASE1_STATUS.md(what's actually implemented vs. scaffolded — read this before assuming a feature exists).packages/— package manager scaffolding (mostly unbuilt, see status doc).
Ground truth over vibes
Before claiming a feature is done, working, or tested, check
docs/PHASE1_STATUS.md and run the actual tests (see
10-rust-core.mdc / the run-tests-and-debug skill). This project has a
documented history of README claims running ahead of actual code — don't
repeat that pattern in commit messages, docstrings, or chat responses.
Current priority order (Phase 1)
On-device hotspot (handoff): Compose PTY transcript / streaming — see
docs/PHASE1_STATUS.md. Commands can succeed in the child while the UI
drops lines. Do not treat that as a missing mkdir syscall until pwd -P
and adb ls are checked.
Then the original Phase 1 order:
- Safety cleanup (
clippy::unwrap_usedenforced — see30-safety-and-testing.mdc) - VFS/SAF capability system (
rust/src/vfs/— the actual product) - Keyboard UX (
android/.../CommandToolbar.kt— cheap, high-visibility) - Package manager, session polish
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 · 54 lines · 584 tokens per session scan A cc70629348ee
00-project-overview is a cursor rule published in the GitHub repository MannanSaood/termi (8 stars, last pushed 2d ago), licensed MIT. It adds 584 tokens to every session, about $0.0029 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 cursor rules, from other repositories
cursorrules
You are an expert in SceneView, the #1 open-source 3D & AR SDK for Android and iOS.
compose-accessibility
Compose accessibility rules for TalkBack — icons, headings, Canvas, live regions, focus, modals, and attribute preservation.
testing-conventions
Testing conventions — JUnit 4, Kotest property tests, instrumented tests, what to test when.
compose-coroutines
Compose scroll/coroutine patterns — prevent programmatic scroll from being mistaken for user scroll, cancellation-safe flag resets.
ios-viewmodel
ViewModels conform to ObservableObject and expose state via @Published properties.
compose-ui
Compose UI conventions — Material 3, recomposition optimization, Compose-only UI, theming.