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/cuecrux/crux/claude-mdgit clone --depth 1 https://github.com/CueCrux/CruxWrote 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/cuecrux/crux/claude-md)<a href="https://agentmods.dev/instructions/cuecrux/crux/claude-md"><img src="https://agentmods.dev/badge/instructions/cuecrux/crux/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 | $0.00494 | $0.00494 |
| Opus 5 | $0.00247 | $0.00247 |
| Sonnet 5 | $0.00099 | $0.00099 |
| Haiku 4.5 | $0.00049 | $0.00049 |
Grade A, and why
Crux 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.
What it actually says
Crux Daemon — Claude Code Instructions
Scope
These rules apply when working inside the Crux/ repository.
Build & Test
cargo build --release # Build Crux Daemon (CPU-only)
cargo test --workspace # Run all tests
cargo fmt --check # Check formatting
cargo clippy --workspace -- -D warnings # Lint
Architecture
- 28 Rust crates in a workspace under
crates/— full atlas:docs/agent/CODEMAP.md(seeAGENTS.mdfor the agent reading order) corecruxd— HTTP (axum, port 14800) + gRPC (tonic) daemoncorecruxctl— CLI tool with subcommandscorecrux-retrieval— BM25 + graph + dense-cosine signal fusion (CPU path). The dense lane is a free, uncapped local capability via a pluggableDenseProvider(exact CPU cosine in the CE; GPU.ccxein the dataplane). Better dense (reranking) and extraction are the metered upsell — never a clip on local dense. See ExecPlandense-lane-and-extraction-upsell-2026-06-26.corecrux-storage— Append-only shard store with sealed segmentscorecrux-receipts— Ed25519 CROWN receipt signing- GPU/CUDA acceleration requires a dataplane-enabled distribution (not included in this repo)
Key Rules
- No GPU/CUDA code. Crux Daemon is CPU-only. No
--features cuda, no CUDA imports, no GPU readiness checks. - No proprietary crates.
corecrux-analytics,corecrux-decision,corecrux-coordinatordo NOT exist in this repo. - Licence headers. Every
.rsfile must start with the Apache-2.0 header (copyright +SPDX-License-Identifier: Apache-2.0). Run./scripts/check-licence-headers.shto check. - Port 14800. The Crux Daemon HTTP port. Do not change this default.
Licence
Apache License, Version 2.0. See LICENSE. Open source (OSI-approved).
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 · 36 lines · 494 tokens per session scan A f51286445da4
Crux CLAUDE.md is an instructions file published in the GitHub repository CueCrux/Crux (2 stars, last pushed 6d ago), licensed Apache-2.0. It adds 494 tokens to every session, about $0.0025 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
openhuman AGENTS.md
AGENTS.md instructions for tinyhumansai/openhuman, covering openhuman, repository layout, runtime scope, ios client (experimental, non-shipping) and commands (from repo root).
plur CLAUDE.md
Claude Code instructions for plur-ai/plur, covering claude.md, what is plur, development, package dependency and version bumps.
openhuman CLAUDE.md
Claude Code instructions for tinyhumansai/openhuman, a project described as: OpenHuman is an open source personal AI for Mac, Windows and Linux — local-first memory, agent orchestration, and deep research.
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.
blz AGENTS.md
Instructions for outfitter-dev/blz, covering blz repository instructions for ai agents, important, working memory, use blz and 🚀 quick start for agents.