Borrowing it
Nothing to install: this file belongs to tari-project/tari-ootle. 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/tari-project/tari-ootle/development/AGENTS.mdgit 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/instructions/tari-project/tari-ootle/agents-md)<a href="https://agentmods.dev/instructions/tari-project/tari-ootle/agents-md"><img src="https://agentmods.dev/badge/instructions/tari-project/tari-ootle/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/tari-project/tari-ootle/agents-md"><img src="https://agentmods.dev/badge/instructions/tari-project/tari-ootle/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 | $0.01728 | $0.01728 |
| Opus 5.5 | $0.00691 | $0.00691 |
| Sonnet 5.5 | $0.00346 | $0.00346 |
| Haiku 4.5 | $0.00173 | $0.00173 |
Grade A, and why
tari-ootle 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 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 — 127 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Tari Ootle - Agent Cheatsheet
Before Every Commit
CI rejects unformatted code. Rust formatting needs the pinned nightly: stable rustfmt skips the nightly-only
options in rustfmt.toml with a warning, so cargo fmt on stable passes locally and fails CI.
rustup toolchain install nightly-2025-12-05 --component rustfmt
cargo +nightly-2025-12-05 fmt --all
cargo +nightly-2025-12-05 fmt --all -- --check # must pass; CI runs this
If the commit touches .ts/.tsx files, also run pnpm run fmt (CI runs pnpm run fmt:check).
Project Structure
- The project is called "Ootle" or "Tari Ootle" (not "DAN" or "Tari DAN")
- Crates are in
crates/, applications inapplications/, clients inclients/ - Wallet daemon package:
tari_ootle_walletd(inapplications/tari_walletd/) - Wallet CLI:
tari_wallet_cli(inapplications/tari_wallet_cli/) - Transaction manifest parser:
tari_transaction_manifest(incrates/transaction_manifest/) - Transaction types/instructions:
tari_ootle_transaction(incrates/transaction/) - Template lib types (OwnerRule, RistrettoPublicKeyBytes, etc.):
tari_template_lib_types(incrates/template_lib_types/) - CBOR serialization:
tari_bor(incrates/tari_bor/) - wraps ciborium, re-exports serde
Code Comments
IMPORTANT: Comments must help a future reader understand code that isn't self-explanatory — non-obvious invariants, the reason for a non-obvious approach, tricky edge cases. They must NOT narrate changes.
- When fixing a bug, lint, or doing a refactor, do not add a comment explaining what was wrong or why you changed it. The corrected code no longer has the issue, so such a comment describes a problem that isn't in the code — it serves no future reader.
- Rationale for a fix belongs in the commit message and PR description, not in the source.
- Never answer a reviewer in a code comment. When addressing review feedback, the justification goes in the reply on the review thread; the source gets only what a reader who never saw the review needs. A comment that argues for the new code over what the reviewer objected to is narrating a change — the thing it contrasts against isn't in the file.
- Write present-tense statements of intent/invariant ("X must be Y because Z"), never history ("changed this from A to B", "without this guard X would happen", "previously this did A").
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 · 127 lines · 1,728 tokens per session scan A a0c590e82326
tari-ootle AGENTS.md is an instructions file published in the GitHub repository tari-project/tari-ootle (29 stars, last pushed yesterday), licensed BSD-3-Clause. It adds 1,728 tokens to every session, about $0.0069 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 2026-11-03.
tari-ootle AGENTS.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| tari-ootle AGENTS.mdtari-project/tari-ootle | Instructions file | 29 | yesterday | BSD-3-Clause | A | 1,728 | 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 |