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 skills add tari-project/tari-ootle --skill google-geminigit clone --depth 1 https://github.com/tari-project/tari-ootleWrote 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/skills/tari-project/tari-ootle/google-gemini)<a href="https://agentmods.dev/skills/tari-project/tari-ootle/google-gemini"><img src="https://agentmods.dev/badge/skills/tari-project/tari-ootle/google-gemini/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/skills/tari-project/tari-ootle/google-gemini"><img src="https://agentmods.dev/badge/skills/tari-project/tari-ootle/google-gemini.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 | $0.00014 | $0.13387 |
| Opus 5 | $0.00007 | $0.06693 |
| Sonnet 5 | $0.00003 | $0.02677 |
| Haiku 4.5 | $0.00001 | $0.01339 |
Grade A, and why
google-gemini 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 yesterday.
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.
This is a copy
97% identical to aider — 14 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 1,332 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Use these instructions when building Tari Ootle templates (WASM smart contracts) and client applications on the Tari L2 network.
Overview
Tari Ootle is a decentralized application platform built on the Tari Layer 2 network. You build templates (smart contracts) in Rust, compile them to WASM (wasm32-unknown-unknown), publish them to the network, and interact with deployed components (instances of templates) via transactions.
Key concepts:
- Template — A Rust module annotated with
#[template]that defines the logic and state structure. Compiled to WASM and deployed to the network. - Component — A live instance of a template on-chain. Holds state (struct fields) and exposes public methods.
- Resource — A native digital asset (fungible token or non-fungible NFT). Created with
ResourceBuilder. Cannot be copied or accidentally destroyed. - Vault — An on-chain container that holds exactly one type of resource. Must be stored in a component before the function returns.
- Bucket — A temporary container for resources during a transaction. Used to move assets between vaults or to/from method calls.
- Transaction — A set of instructions (CallFunction, CallMethod, etc.) that are signed, submitted, and executed atomically.
Crate ecosystem:
| Crate | Purpose | Used In |
|---|---|---|
tari_template_lib |
Core template library: prelude, ResourceBuilder, Vault, Bucket, ComponentManager, CallerContext, emit_event, rand, macros (args!, rule!, metadata!) |
Templates (WASM) |
tari_template_lib_types |
Shared types: Amount, ComponentAddress, ResourceAddress, NonFungibleId, AccessRule, OwnerRule, Metadata |
Templates & client |
tari_ootle_transaction |
TransactionBuilder and args! macro for constructing transactions |
Client & tests |
ootle-rs |
Client wallet and Indexer provider: sign, submit, watch transactions; builtin template helpers (faucet) | Client apps |
tari_template_test_tooling |
Local test harness (dev-dependency): compile templates to WASM and run against the engine in-process | Tests only |
Important macro distinction:
args!(fromtari_template_lib::prelude) — used inside templates for cross-template calls (alias forinvoke_args!)args!(fromtari_ootle_transaction) — used in test code and client code forTransactionBuilder,TemplateTest::call_function, andcall_method. ProducesVec<NamedArg>.
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.
- yesterday Changed · +65 lines 611542085c14
- 9d ago First seen · 1,267 lines · 14 tokens per session scan A 19478c311d38
google-gemini is a skill published in the GitHub repository tari-project/tari-ootle (28 stars, last pushed yesterday), licensed BSD-3-Clause. It adds 14 tokens to every session and 13,387 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. It is 97% identical to aider, differing in 14 lines, and is treated as a copy.
Other skills, from other repositories
cw-gates
Use before claiming any Codewhale change is done, green, or ready to land: the focused-to-broad verification ladder, the budget checks CI enforces, and the rules for what counts as a passing test.
feishu
Work with Feishu or Lark bots, docs, sheets, bitables, approval flows, and OpenAPI/MCP setup without hardcoding credentials.
interview
Ask one useful structured question at a time only when material product/implementation choices are genuinely missing; remember answers and produce a brief/spec. Discoverable facts should be investigated instead of asked.
verify
Exercise the real app/API/CLI and collect observable evidence; tests alone do not count as end-to-end verification.
tuicr
Use tuicr's review CLI to read and add comments in active TUI review sessions, and launch tuicr in cmux, tmux, Zellij, or Herdr when a user needs an interactive review pane.
dd-code-generation
Use pup CLI for immediate Datadog operations or generate code for integration into applications.