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/ivrodriguezca/nuntius/claude-mdgit clone --depth 1 https://github.com/ivRodriguezCA/nuntiusWrote 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/ivrodriguezca/nuntius/claude-md)<a href="https://agentmods.dev/instructions/ivrodriguezca/nuntius/claude-md"><img src="https://agentmods.dev/badge/instructions/ivrodriguezca/nuntius/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 | $0.03117 | $0.03117 |
| Opus 5 | $0.01558 | $0.01558 |
| Sonnet 5 | $0.00623 | $0.00623 |
| Haiku 4.5 | $0.00312 | $0.00312 |
Grade A, and why
nuntius CLAUDE.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 6d 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 — 165 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
nuntius is an iOS framework (Objective-C, MIT) implementing X3DH + Double Ratchet on libsodium. It is the reference implementation for the Java/Kotlin/Swift ports in sibling directories.
SPEC.md is the contract, and it is normative. This file is orientation; where the two disagree,
SPEC.md wins and this file is the thing that is wrong. Every port is written against SPEC.md, not
against this code, and all four must interoperate byte-for-byte.
The library is experimental, published for research and study, and not recommended for production
environments. v4 is complete and unaudited — no external security review of the code or of the
specification — and SPEC.md §17 enumerates open risks and deliberate non-goals that are stated
rather than solved. That posture is not a reason to hold work to a lower standard; it is the reason
the standard is what it is, and it constrains how the project describes itself. Do not write
documentation, comments or commit messages that read as an endorsement for deployment. The README's
Read this first section is the canonical statement; keep new prose consistent with it.
Protocol version
The tree implements v4 only. The v3 protocol was deleted, not deprecated — sources, tests,
headers, and every pbxproj reference. See SPEC.md §14 for the thirteen confirmed defects that made
v3 cryptographically broken, and §2 for what v4 changed.
There is no v3 → v4 migration and no dual-stack mode (§10.6, §17.9). A v4 receiver rejects a first
byte that is not 0x04 with ERR_UNSUPPORTED_VERSION. Existing identities must be re-registered:
the identity key type itself changed.
If you find a reference to IREncryptionService, IRTripleDHService, IRDoubleRatchetService,
IRCurve25519KeyPair, IRRatchetHeader, IRAEADInfo, or IRConstants outside a comment explaining
what v3 got wrong, it is a mistake. The banned-API lint fails the build on them.
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.
- 6d ago First seen · 165 lines · 3,117 tokens per session scan A e28068d3a3ce
nuntius CLAUDE.md is an instructions file published in the GitHub repository ivRodriguezCA/nuntius (21 stars, last pushed 1mo ago), licensed MIT. It adds 3,117 tokens to every session, about $0.0156 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
FluidAudio copilot-instructions.md
Copilot instructions for FluidInference/FluidAudio, covering fluidaudio - agent development guide, build & test commands, architecture, critical rules and code style (swift-format config).
speech-swift AGENTS.md
AGENTS.md instructions for soniqo/speech-swift, covering agent instructions, communication style, workflow, running tests and benchmarks — sequential and memory-aware and git conventions.
legacy-lands-library AGENTS.md
Instructions for LegacyLands/legacy-lands-library, covering ✅ 开发与协作规范（学习与编程行为指南）, 1. 当你尝试编写一个新功能、添加新类或书写 javadoc 时, 2. 你必须制定清晰的 todo 任务清单，并在开发完成后遵循以下规则：, 3. 命名规范（类、字段、变量、方法） and 4. 数据处理优先使用 stream api（尤其是过滤、映射、聚合等操作）.
maui-labs AGENTS.md
AGENTS.md instructions for dotnet/maui-labs, covering agent instructions, repository overview, products, technology stack and building.
maui-labs testing.instructions.md
Instructions for dotnet/maui-labs, covering testing guide, test framework, test projects, running tests and all tests.
VCVio AGENTS.md
AGENTS.md instructions for Verified-zkEVM/VCVio, covering vcvio — ai agent guide, fast start, attribution, headers, and docstrings, module scopes and what this project is.