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/0xnyk/oneclaw/claude-mdgit clone --depth 1 https://github.com/0xNyk/oneclawWrote 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/0xnyk/oneclaw/claude-md)<a href="https://agentmods.dev/instructions/0xnyk/oneclaw/claude-md"><img src="https://agentmods.dev/badge/instructions/0xnyk/oneclaw/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 | $0.01694 | $0.01694 |
| Opus 5 | $0.00847 | $0.00847 |
| Sonnet 5 | $0.00339 | $0.00339 |
| Haiku 4.5 | $0.00169 | $0.00169 |
Grade A, and why
oneclaw 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 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 — 97 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.
Build & Development Commands
cargo build # Dev build
cargo build --release # Release build (~11MB macOS arm64)
cargo test # Run full test suite
cargo test <test_name> # Run a single test by name
cargo test --test memory_comparison -- --nocapture # SQLite vs Markdown benchmark
cargo clippy -- -D warnings # Lint
cargo fmt # Format code
cargo fmt -- --check # Check formatting without modifying
Pre-push hook (runs fmt, clippy, tests): git config core.hooksPath .githooks
CI runs cargo fmt --check, cargo clippy -- -D warnings, and cargo test on every PR.
Architecture
OneClaw is a single-binary Rust AI assistant (~11MB macOS arm64) with a trait-based pluggable architecture. Every major subsystem is defined as a trait, with implementations swappable via config.toml.
Core Traits (the extension points)
| Trait | File | Purpose |
|---|---|---|
Provider |
src/providers/traits.rs |
LLM API backends (28+ providers) |
Channel |
src/channels/traits.rs |
Messaging platforms (CLI, Telegram, Discord, Slack, WhatsApp, iMessage, Matrix) |
Memory |
src/memory/traits.rs |
Persistence backends (SQLite FTS5+vector, Tiered with importance scoring, Markdown, Vault, 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, OTLP, PII-scrub, multi) |
RuntimeAdapter |
src/runtime/traits.rs |
Platform adapters (native only; Docker/WASM planned) |
SecurityPolicy |
src/security/policy.rs |
Sandbox, allowlists, rate limits, filesystem scoping |
Adding a new implementation
- Create
src/<subsystem>/your_impl.rsimplementing the trait - Register in
src/<subsystem>/mod.rsfactory function (e.g.,create_provider(),create_memory()) - Add inline
#[cfg(test)] mod tests {}at the bottom of your file
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 · 97 lines · 1,694 tokens per session scan A aa37942631fe
oneclaw CLAUDE.md is an instructions file published in the GitHub repository 0xNyk/oneclaw (3 stars, last pushed 5d ago), licensed MIT. It adds 1,694 tokens to every session, about $0.0085 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.
Other instructions, from other repositories
hermes-desktop AGENTS.md
AGENTS.md instructions for fathah/hermes-desktop, covering before starting work, post-task checklist (required — do not skip), what is lat.md?, commands and syntax primer.
quarkus-workshop-langchain4j AGENTS.md
AGENTS.md instructions for quarkusio/quarkus-workshop-langchain4j, covering agents.md, project overview, technology stack, project structure and building and running.
rlm-rs CLAUDE.md
Claude Code instructions for zircote/rlm-rs, covering claude.md, project overview, project structure, build commands and build the project.
rlm-rs copilot-instructions.md
Copilot instructions for zircote/rlm-rs, covering github copilot instructions, project context, code generation guidelines, error handling and type annotations.
pydantic-ai-todo CLAUDE.md
Instructions for vstorm-co/pydantic-ai-todo, covering claude.md, what this project is, commands, structure and core pattern.
zeph rust.instructions.md
Instructions for bug-ops/zeph, covering rust file review, lints, async patterns, type conventions and test code.