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/sprklai/zenii/claude-mdgit clone --depth 1 https://github.com/sprklai/zeniiWrote 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/sprklai/zenii/claude-md)<a href="https://agentmods.dev/instructions/sprklai/zenii/claude-md"><img src="https://agentmods.dev/badge/instructions/sprklai/zenii/claude-md.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 5.1 | $0.03364 | $0.03364 |
| Opus 5 | $0.01682 | $0.01682 |
| Sonnet 5 | $0.00673 | $0.00673 |
| Haiku 4.5 | $0.00336 | $0.00336 |
Grade C, and why
zenii CLAUDE.md scanned grade C with 2 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 5d 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.
Hidden instructionshighPrompt injection
Directives inside HTML comments, invisible characters or bidirectional overrides are read by the model and not by the person reviewing the file.
<!-- rtk-instructions v2 --> Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
rtk curl <url> # Compact HTTP responses (70%) How it starts
The opening of the file, as written. The whole thing — 299 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md -- Zenii
Project Overview
Zenii is a Rust workspace producing 5 binaries (Desktop, Mobile, CLI, TUI, Daemon) from a single shared core. All clients communicate via HTTP+WebSocket gateway (axum at 127.0.0.1:18981).
v2 Philosophy
- Use proven crates, don't hand-roll --
sysinfo,websearch,rig-core,ignoreover custom implementations. - Port patterns, not code -- port v1 design (trait-based tools, security policy, memory abstraction) adapted to v2 conventions.
- Lean by default -- feature-gate optional modules. Default binary includes only core operation.
- Single shared core -- ALL business logic in
zenii-core. Binary crates are thin shells (<100 lines).
Tech Stack
Rust 2024 | Tokio | rig-core | rusqlite + sqlite-vec | axum | Svelte 5 + Tauri 2 | openclaw-channels | comrak + Tera
Commands
cargo check --workspace # Compile check
cargo test --workspace # Run all tests
cargo clippy --workspace # Lint
cargo run -p zenii-daemon # Start daemon
cargo run -p zenii-cli -- chat # CLI chat
cd web && bun run dev # Frontend dev
cd crates/zenii-desktop && cargo tauri dev # Desktop app
./scripts/build.sh --target native --release # Build binaries
Workspace Structure
→ Full module detail in docs/architecture.md
crates/zenii-core/ # Shared library — ALL business logic, NO Tauri dep
crates/zenii-desktop/ # Tauri 2 shell (macOS, Windows, Linux)
crates/zenii-mobile/ # Tauri 2 shell (iOS, Android)
crates/zenii-cli/ # clap CLI (thin wrapper)
crates/zenii-tui/ # ratatui TUI (thin wrapper)
crates/zenii-daemon/ # Headless daemon (thin wrapper)
web/ # Svelte 5 frontend (shared by desktop + mobile)
docs/ # Architecture diagrams, phase details, process flows
plans/ # Detailed per-phase implementation plans
tests/ # Per-phase test plans and results
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.
- 5d ago First seen · 299 lines · 3,364 tokens per session scan C 212d7c95c565
zenii CLAUDE.md is an instructions file published in the GitHub repository sprklai/zenii (23 stars, last pushed 26d ago), licensed MIT. It adds 3,364 tokens to every session, about $0.0168 per session on Opus 5. A static security scan graded it C with 2 findings (hidden instructions, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other instructions, from other repositories
zeph rust.instructions.md
Instructions for bug-ops/zeph, covering rust file review, lints, async patterns, type conventions and test code.
rag-ferrite AGENTS.md
AGENTS.md instructions for lelabdev/rag-ferrite, covering rag-ferrite — moteur rag personnel (rust), stack, architecture, décisions d'architecture and structure du code.
turso AGENTS.md
AGENTS.md instructions for tursodatabase/turso, covering turso agent guidelines, quick reference, testing, running tests and test organization.
cli AGENTS.md
AGENTS.md instructions for googleworkspace/cli, covering agents.md, project overview, build & test, changesets and architecture.
azure-sdk-for-rust resourcemanager.instructions.md
Instructions for Azure/azure-sdk-for-rust, a project described as: This repository is for the active development of the Azure SDK for Rust. For consumers of the SDK we recommend visiting Docs.rs and looking up the docs for any of libraries in the SDK.
intelligent-terminal rust.instructions.md
Concise Rust coding conventions for this repository.