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/nullclaw/nullclaw/claude-mdgit clone --depth 1 https://github.com/nullclaw/nullclawWhat 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 | $0.02439 | $0.02439 |
| Opus 5 | $0.01220 | $0.01220 |
| Sonnet 5 | $0.00488 | $0.00488 |
| Haiku 4.5 | $0.00244 | $0.00244 |
Grade A, and why
nullclaw 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 yesterday.
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 — 158 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.
Mandatory Reference
Read AGENTS.md before any code change. It is the authoritative engineering protocol covering architecture, naming conventions, anti-patterns, change playbooks, and validation requirements.
Build & Test Commands
# Requires exactly Zig 0.16.0 (verify: zig version)
zig build # dev build
zig build -Doptimize=ReleaseSmall # release build (target: <1 MB binary)
zig build test --summary all # run all 5,300+ tests (must pass with 0 leaks)
zig fmt src/ # format all source files
zig fmt --check src/ # check formatting (used by pre-commit hook)
Primary validation command is zig build test --summary all (project-wide). Individual files can still be run with zig test <file>.zig when needed.
Build Flags
zig build -Dchannels=telegram,cli # compile only specific channels (default: all)
zig build -Dengines=base,sqlite # compile only specific memory engines (default: base,sqlite)
zig build -Dtarget=x86_64-linux-musl # cross-compile for target triple
zig build -Dversion=2026.3.1 # override CalVer version string
Channel tokens: all, none, or comma-separated names (cli, telegram, discord, slack, signal, matrix, web, nostr, irc, email, imessage, whatsapp, mattermost, lark, dingtalk, line, onebot, qq, maixcam).
Engine tokens: base/minimal (enables none, markdown, memory, api), sqlite, lucid, redis, lancedb, postgres, all.
Git Hooks
Activate once per clone:
git config core.hooksPath .githooks
- pre-commit: blocks if
zig fmt --check src/fails - pre-push: blocks if
zig build test --summary allfails
Project Overview
NullClaw is an autonomous AI assistant runtime written in Zig 0.16.0. Hard constraints: 678 KB binary, ~1 MB peak RSS, <2 ms startup. Every dependency and abstraction has a measurable size/memory cost. Only two external dependencies: vendored SQLite (with build-time SHA256 hash verification) and websocket.zig (pinned commit).
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.
- yesterday First seen · 158 lines · 2,439 tokens per session scan A 69880daa48db
nullclaw CLAUDE.md is an instructions file published in the GitHub repository nullclaw/nullclaw (8,053 stars, last pushed 1mo ago), licensed MIT. It adds 2,439 tokens to every session, about $0.0122 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
openclaw AGENTS.md
AGENTS.md instructions for openclaw/openclaw, covering agents.md, start, repair doctrine, product doctrine and clawsweeper review policy.
openclaw copilot.instructions.md
Copilot instructions for openclaw/openclaw, covering openclaw codebase patterns, tech stack, anti-redundancy rules, source of truth locations and formatting utilities (src/infra/).
openclaw CLAUDE.md
Claude Code instructions for openclaw/openclaw, a project described as: Your own personal AI assistant. Any OS. Any Platform. The lobster way. 🦞.
FERAL-AI CLAUDE.md
Instructions for FERAL-AI/FERAL-AI, covering claude.md — feral / asos, what this is, layout, commands and rather than restating it.
vouch CLAUDE.md
Instructions for vouchdev/vouch, covering claude.md — orientation for claude code working on vouch, north star, architecture (90 seconds), build + test + ship and from a clone.
clawlet AGENTS.md
Instructions for mosaxiv/clawlet, covering repository guidelines, project structure, build, test, and development commands, build a local binary and run from source.