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/ston-fi/ton-rs/agents-mdgit clone --depth 1 https://github.com/ston-fi/ton-rsWrote 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/ston-fi/ton-rs/agents-md)<a href="https://agentmods.dev/instructions/ston-fi/ton-rs/agents-md"><img src="https://agentmods.dev/badge/instructions/ston-fi/ton-rs/agents-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 | $0.00764 | $0.00764 |
| Opus 5 | $0.00382 | $0.00382 |
| Sonnet 5 | $0.00153 | $0.00153 |
| Haiku 4.5 | $0.00076 | $0.00076 |
Grade A, and why
ton-rs 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 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.
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 — 92 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ton-rs agent guide
Repository
This workspace contains public Rust libraries for TON:
ton_core: cells, addresses, TLB primitives, and provider traits.ton: block and contract types, wallets, clients, and optional emulators.ton_macros: derives and attributes used by the two libraries.examplesandbenchmarks: consumers, not reusable API crates.
Use the rust-library-review workflow for public API, dependency, feature,
serialization, documentation, or release changes.
Boundaries
Keep provider-neutral types in ton_core. Networking, contract wrappers, wallet
logic, and native tonlib adapters belong in ton. Procedural macros must emit
paths that work when dependencies are renamed.
Do not add convenience re-exports or parallel constructors. Prefer the existing module-qualified paths and one canonical construction path.
Public API
- Mark open errors, enums, returned state, responses, and result records
#[non_exhaustive]so variants and fields can grow compatibly. - Keep fixed TLB/TL wire records exhaustive when callers must construct them and adding a field would change serialization. Document this exception near the type or in its crate guide.
- A non-exhaustive struct must have a constructor, builder, or another supported construction path.
- Keep Rustdoc short and behavioral. Document errors, panics, ownership, timeouts, caching, and feature requirements when relevant.
- Public enum additions, serialized names, feature changes, and dependency types are compatibility-sensitive even when code still compiles.
Any public surface change must review the applicable AGENTS.md, README,
Rustdoc, examples, tests, package include rules, and changelog.
TON invariants
- Cell limits are 1023 data bits and four references.
- TLB prefixes, field order, reference layout, and signed-message layout are wire contracts. Never change them as cleanup.
TVMStackpops from the end; serialized stack order is reversed while reading.- Wallet code and initial data determine the address. Signing layout differs by wallet version.
- Provider state requested for a transaction must describe that exact transaction. Do not silently substitute latest state.
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 · 92 lines · 764 tokens per session scan A 83cf69ba1090
ton-rs AGENTS.md is an instructions file published in the GitHub repository ston-fi/ton-rs (172 stars, last pushed 3d ago), licensed Apache-2.0. It adds 764 tokens to every session, about $0.0038 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 2026-08-30.
Other instructions, from other repositories
spark CLAUDE.md
Claude Code instructions for buildonspark/spark, covering spark repository, setup, components, code quality guidelines and comments.
bsv-wallet-cli CLAUDE.md
Claude Code instructions for Calhooon/bsv-wallet-cli, covering bsv-wallet-cli, architecture, conventions, development and build.
cardano-init CLAUDE.md
Claude Code instructions for input-output-hk/cardano-init, covering claude.md, project overview, commands, build and run.
StellarX-Workshop-Template-2026 CLAUDE.md
Instructions for ALGOREX-PH/StellarX-Workshop-Template-2026, covering stellarx workshop starter — project notes for ai tools, stack / versions, testnet reference, stellar gotchas (these waste the most time) and where things live.
cli AGENTS.md
AGENTS.md instructions for googleworkspace/cli, covering agents.md, project overview, build & test, changesets and architecture.
turso AGENTS.md
AGENTS.md instructions for tursodatabase/turso, covering turso agent guidelines, quick reference, testing, running tests and test organization.