oneclaw AGENTS.md

oneclaw AGENTS.md is an instructions file for Codex, OpenCode from 0xNyk/oneclaw. It costs 690 tokens per session, scanned A, original, MIT.

Repository instructions for OneClaw, a small single-file Rust AI assistant with replaceable providers, messaging channels, and memory storage.

In plain words
What is it for?
Use them to build, test, format, and lint the project, or to understand its interchangeable AI providers, messaging platforms, and memory backends.
Why use it?
They define the architecture and checks required before committing Rust changes.

Instructions file for CodexOpenCode

Install

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.

agentmods
npx agentmods add instructions/0xnyk/oneclaw/agents-md
Clone the repo
git clone --depth 1 https://github.com/0xNyk/oneclaw

Made for: Codex, OpenCode.

Wrote 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.

agentmods badge for oneclaw AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/0xnyk/oneclaw/agents-md.svg)](https://agentmods.dev/instructions/0xnyk/oneclaw/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/0xnyk/oneclaw/agents-md"><img src="https://agentmods.dev/badge/instructions/0xnyk/oneclaw/agents-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 690 This file is loaded in full into every session.
When invoked 690 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00690 $0.00690
Opus 5 $0.00345 $0.00345
Sonnet 5 $0.00138 $0.00138
Haiku 4.5 $0.00069 $0.00069

Measured 3d ago against content hash 71b8130a0350, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

oneclaw 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 3d 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.

AGENTS.md · 62 lines

How it starts

The opening of the file, as written. The whole thing — 62 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md

Build & Development

cargo build                    # Dev build
cargo build --release          # Release build (~3.4MB optimized binary)
cargo test                     # Run full test suite
cargo test <test_name>         # Run a single test by name
cargo clippy -- -D warnings    # Lint (must pass before commit)
cargo fmt                      # Format code
cargo fmt -- --check           # Check formatting without modifying

Validation Checklist

Before committing any Rust changes:

  1. cargo fmt
  2. cargo clippy -- -D warnings
  3. cargo test (full suite) or cargo test <name> (targeted)

Architecture

OneClaw is a single-binary Rust AI assistant (~3.4MB) with trait-based pluggable architecture. Every major subsystem is a trait with implementations swappable via config.toml.

Core Traits

Trait File Purpose
Provider src/providers/traits.rs LLM API backends (22+ providers)
Channel src/channels/traits.rs Messaging platforms (CLI, Telegram, Discord, Slack, WhatsApp, iMessage, Matrix)
Memory src/memory/traits.rs Persistence backends (SQLite with hybrid FTS5+vector search, Markdown, noop)
Tool src/tools/traits.rs Agent capabilities (shell, file_read/write, memory_store/recall/forget, browser)
Observer src/observability/traits.rs Metrics/logging (noop, log, multi)
SecurityPolicy src/security/policy.rs Sandbox, allowlists, rate limits, filesystem scoping

Adding a New Implementation

  1. Create src/<subsystem>/your_impl.rs implementing the trait
  2. Register in src/<subsystem>/mod.rs factory function
  3. Add inline #[cfg(test)] mod tests {} at the bottom of your file

Key Patterns

  • Factory functions in each module's mod.rs create trait objects from config strings
  • ReliableProvider wraps any Provider with retry + fallback chain (src/providers/reliable.rs)
  • Config is a single Config struct (src/config/schema.rs) loaded from ~/.oneclaw/config.toml

Read the full file on GitHub · 62 lines

Changes

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.

  1. 3d ago First seen · 62 lines · 690 tokens per session scan A 71b8130a0350

Subscribe to this mod's changes

oneclaw AGENTS.md is an instructions file published in the GitHub repository 0xNyk/oneclaw (2 stars, last pushed 3d ago), licensed MIT. It adds 690 tokens to every session, about $0.0034 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 2026-08-31.

Related

Other instructions, from other repositories