hash CLAUDE.md

Repository guidance for Hash, a Go-based command-line shell with built-in AI features and support for connecting to different agents. It covers the project layout, build and test commands, and fuzz testing, which checks how code handles many unexpected inputs.

In plain words
What is it for?
Use it when working on Hash, especially its parser, learning system, agent connections, configuration, or command-line interface.
Why use it?
It gives a coding agent the project context and the commands needed to build, test, inspect, and safely change the code.

Instructions file

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/tfcace/hash/claude-md
Clone the repo
git clone --depth 1 https://github.com/tfcace/hash
Per session 1,137 This file is loaded in full into every session.
When invoked 1,137 The same file — it is already loaded in full.
Security scan B 1 finding. 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 $0.01137 $0.01137
Opus 5 $0.00568 $0.00568
Sonnet 5 $0.00227 $0.00227
Haiku 4.5 $0.00114 $0.00114

Measured 2d ago against content hash 28e41d41308a, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade B, and why

hash CLAUDE.md scanned grade B with 1 finding 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.

Asks for rootmediumPrivilege escalation

A mod that escalates privileges can change anything on the machine, not only the project.

│ ├── history/ # SQLite history, sudo tracking
CLAUDE.md · 104 lines

How it starts

The opening of the file, as written. The whole thing — 104 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

Hash (Harness Assisted SHell) is an AI-powered shell written in Go with ACP (Agent Client Protocol) integration. It provides a Warp-like intelligent experience while being agent-agnostic, local-first, and protocol-based.

Build Commands

go build -o hash ./cmd/hash      # Build binary
go test ./...                     # Run all tests
go test ./internal/parser/...     # Run tests for a specific package
go test -run TestName ./...       # Run a single test
go vet ./...                      # Lint

# Fuzz testing (parser and learning system)
go test -fuzz=FuzzParse -fuzztime=30s ./internal/parser/...
go test -fuzz=FuzzNormalizeError -fuzztime=30s ./internal/learning/...

Architecture

hash/
├── cmd/hash/          # Main entry point
├── internal/
│   ├── agent/         # ACP client, StdioTransport, HTTPTransport
│   ├── clipboard/     # Copy command/output buffer
│   ├── completion/    # Three-tier completion router
│   ├── config/        # TOML configuration parsing
│   ├── context/       # Context picker TUI
│   ├── executor/      # POSIX interpreter (mvdan/sh), PTY-on-demand
│   ├── history/       # SQLite history, sudo tracking
│   ├── learning/      # Error pattern learning, fix suggestions
│   ├── parser/        # ?? detection and command parsing
│   ├── progress/      # OSC 9;4 progress bar support
│   ├── prompt/        # Starship + built-in prompt engines
│   ├── readline/      # Input, Emacs/Vim/Helix keybindings
│   └── shell/         # REPL, builtins, agent integration
└── go.mod

Agent Invocation

Use ?? to invoke the agent:

  • ?? find large files - Full agent request
  • cmd | ?? filter output - Pipe command output to agent
  • cmd --flag=?? description - Inline completion

Key Design Decisions

Agent invocation: ?? prefix (not #). Supports ?? <prompt> at line start, cmd | ?? <prompt> for pipe completion, and cmd ?? <prompt> for inline completion.

Read the full file on GitHub · 104 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. 2d ago First seen · 104 lines · 1,137 tokens per session scan B 28e41d41308a

Subscribe to this mod's changes

hash CLAUDE.md is an instructions file published in the GitHub repository tfcace/hash (27 stars, last pushed 3d ago), licensed MIT. It adds 1,137 tokens to every session, about $0.0057 per session on Opus 5. A static security scan graded it B with 1 finding (asks for root). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other instructions, from other repositories