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/zhing2006/krew-cli/claude-mdgit clone --depth 1 https://github.com/zhing2006/krew-cliWhat 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 | $0.01074 | $0.01074 |
| Opus 5 | $0.00537 | $0.00537 |
| Sonnet 5 | $0.00215 | $0.00215 |
| Haiku 4.5 | $0.00107 | $0.00107 |
Grade A, and why
krew-cli 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 2d 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.
This is a copy
94% identical to krew-cli AGENTS.md — 4 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 90 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.
Project Overview
krew-cli is a multi-AI-agent collaborative CLI tool written in Rust. Users chat with multiple LLMs (GPT, Claude, Gemini, etc.) simultaneously in one terminal using @ addressing and # whisper (private messages). See PDD for product design and TDD for technical design.
Build & Development Commands
# Build
cargo build # Debug build
cargo build --release # Release build
# Run
cargo run # Run the CLI (krew-cli crate)
# Test
cargo test # Run all tests
cargo test -p krew-core # Run tests for a specific crate
cargo test test_name # Run a single test by name
# Lint & Format
cargo fmt --all # Format all code
cargo fmt --all -- --check # Check formatting (CI)
cargo clippy --all-targets --all-features -- -D warnings # Lint with warnings as errors
# Check (fast compile check without codegen)
cargo check --all-targets
IMPORTANT: Always run cargo fmt --all and cargo clippy --all-targets --all-features -- -D warnings before committing.
Architecture
Cargo workspace with 6 crates under crates/:
krew-cli CLI entry + TUI (clap, ratatui)
└── krew-core Session management, Agent Loop, routing, slash commands
├── krew-llm LLM provider abstraction (OpenAI/Anthropic/Google/OpenAI-Compatible)
├── krew-tools Tool system (8 built-in tools) + MCP client
├── krew-storage TOML session persistence (.krew/sessions/)
└── krew-config TOML config loading (.krew/settings.toml)
Key Design Patterns
- Agent Loop: Serial execution per
reply_order— each agent completes its full loop (including tool calls) before the next starts, so later agents see earlier agents' responses. - Message routing:
@nameaddressing +#namewhisper (private messages). Whisper messages are only visible to target agents; others see placeholders. - Built-in tools enforce path boundary — all file operations must be within session cwd.
- Error types:
anyhowfor application-level errors (krew-cli,krew-core),thiserrorfor library crate error definitions (krew-llm,krew-tools,krew-storage,krew-config).
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.
- 2d ago First seen · 90 lines · 1,074 tokens per session scan A 90f1dc47012e
krew-cli CLAUDE.md is an instructions file published in the GitHub repository zhing2006/krew-cli (140 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 1,074 tokens to every session, about $0.0054 per session on Opus 5. A static security scan graded it A with 0 findings. It is 94% identical to krew-cli AGENTS.md, differing in 4 lines, and is treated as a copy.
Other instructions, from other repositories
cli AGENTS.md
Instructions for googleworkspace/cli, covering agents.md, project overview, build & test, changesets and architecture.
turso AGENTS.md
Instructions for tursodatabase/turso, covering turso agent guidelines, quick reference, testing, running tests and test organization.
intelligent-terminal rust.instructions.md
Concise Rust coding conventions for this repository.
azure-sdk-for-rust resourcemanager.instructions.md
Instructions for Azure/azure-sdk-for-rust, a project described as: This repository is for the active development of the Azure SDK for Rust. For consumers of the SDK we recommend visiting Docs.rs and looking up the docs for any of libraries in the SDK.
Browser4 CLAUDE.md
Instructions for platonai/Browser4, covering browser4 — project context for claude, architecture, key dispatch chain (cli → browser), batch commands and e2e test structure.
azure-sdk-for-rust cosmos.instructions.md
Instructions for Azure/azure-sdk-for-rust, a project described as: This repository is for the active development of the Azure SDK for Rust. For consumers of the SDK we recommend visiting Docs.rs and looking up the docs for any of libraries in the SDK.