spice-edit CLAUDE.md

Project instructions for SpiceEdit, a small terminal code editor written in Go for working through SSH and tmux. They describe its interface, file actions, menus and shortcut conventions.

In plain words
What is it for?
They help modify or review SpiceEdit's editor actions, menus, file tree, tabs, mouse interactions and terminal-friendly controls while preserving its single-binary design.
Why use it?
Editors used inside terminals can conflict with tmux and terminal keyboard handling, and important actions may be missed if they are available only through right-click. These rules document the intended behavior.

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/cloudmanic/spice-edit/claude-md
Clone the repo
git clone --depth 1 https://github.com/cloudmanic/spice-edit
Per session 2,009 This file is loaded in full into every session.
When invoked 2,009 The same file — it is already loaded in full.
Security scan C 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 $0.02009 $0.02009
Opus 5 $0.01005 $0.01005
Sonnet 5 $0.00402 $0.00402
Haiku 4.5 $0.00201 $0.00201

Measured 3d ago against content hash 581246c8fb79, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade C, and why

spice-edit CLAUDE.md scanned grade C 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 3d 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.

Recursive force deletehighDestructive command

rm -rf with a variable or a broad path is one typo away from removing the wrong tree.

make clean # rm -rf bin
CLAUDE.md · 191 lines

How it starts

The opening of the file, as written. The whole thing — 191 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md — SpiceEdit

Project-specific guidance for Claude Code. Read this first; it captures conventions and design decisions that aren't obvious from the code alone.

What this project is

SpiceEdit is an opinionated, mouse-first terminal code editor aimed at SSH-into-tmux workflows. It looks and behaves like a tiny VS Code: file tree on the left, tabs across the top, syntax-highlighted editor in the middle, status bar at the bottom. It ships as a single static Go binary with no CGO.

Users open the action menu (Save, Quit, Show/Hide Sidebar, …) by clicking the icon, right-clicking, or double-tapping Esc. There are intentionally no Ctrl+ shortcuts for editor actions — they conflict with tmux and terminal emulators. Don't add them back.

Every file action also lives in the main ≡ menu. macOS Terminal + tmux often swallows Button3 (right-click), so the editor cannot rely on right-click as the only path to anything. Tree right-click is a redundant shortcut, not a primary surface — when adding new file-management features, make sure they're reachable from the main menu first.

Module / repo

  • Module: github.com/cloudmanic/spice-edit
  • Binary name: spiceedit (one word, lowercase — Makefile, goreleaser, brew formula all assume this)
  • Brew tap: this same repo, Formula/ directory (no separate tap repo)

Architecture map

main.go                       Entry — parses optional rootDir arg
internal/app/app.go           Event loop, layout, menu modal, splitter, all rendering
internal/editor/buffer.go     Position + Buffer ([]string lines), edit primitives
internal/editor/tab.go        Tab: path, buffer, cursor, anchor, scroll, dirty state
internal/editor/highlight.go  Chroma → []tcell.Style per line
internal/filetree/filetree.go Lazy tree, identity-preserving refresh, hit-test, render
internal/clipboard/clipboard.go OSC 52 to /dev/tty with tmux passthrough wrap
internal/spiceconfig/spiceconfig.go ~/.config/spiceedit/config.json loader (icons mode)
internal/icons/icons.go       Nerd Font detection + per-file glyph mapping
internal/theme/theme.go       Tokyo Night palette + syntax color mapping
internal/version/version.go   const Version = "x.y.z" — single line, CI bumps it

Read the full file on GitHub · 191 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. 3d ago First seen · 191 lines · 2,009 tokens per session scan C 581246c8fb79

Subscribe to this mod's changes

spice-edit CLAUDE.md is an instructions file published in the GitHub repository cloudmanic/spice-edit (82 stars, last pushed 1mo ago), licensed MIT. It adds 2,009 tokens to every session, about $0.0100 per session on Opus 5. A static security scan graded it C with 1 finding (recursive force delete). 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

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 6,785 tokens

spec-kit AGENTS.md

AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.

github/spec-kit · 7,104 tokens

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,182 tokens

langchain AGENTS.md

AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.

langchain-ai/langchain · 4,345 tokens

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).

microsoft/vscode · 5,001 tokens

next.js AGENTS.md

Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens