agentmods.dev

prompt-line: Instructions file for Claude Code

CLAUDE.md

prompt-line CLAUDE.md is an instructions file for Claude Code from nkmr-jp/prompt-line. It costs 4,023 tokens per session, scanned A, original, MIT.

Project instructions for Prompt Line, a macOS app for entering and sending prompts, including its development commands and isolated test setup.

In plain words
What is it for?
Use them to start the app, reset accessibility permissions, inspect logs, or run isolated verification actions such as typing and clearing input.
Why use it?
They help agents test changes without disturbing the user's normally running app and explain where logs and setup tasks are located.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: mentions CLAUDE.md; mentions Claude Code; mentions Codex.

This is nkmr-jp/prompt-line's own configuration. It tells Claude Code how to work on prompt-line itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything prompt-line configures →

Not installable: its command points at a path on the author’s own machine, so it runs nowhere else. The line is /Users/me/ghq/github.com/me/project.

not rated 148repo 4d ago A scan 4,023 tokens original MIT
View source ↗ nkmr-jp/prompt-line
Reuse

Borrowing it

Nothing to install: this file belongs to nkmr-jp/prompt-line. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/nkmr-jp/prompt-line/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/nkmr-jp/prompt-line

Made for: Claude Code.

Wrote 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.

agentmods badge for prompt-line CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/nkmr-jp/prompt-line/claude-md/github.svg)](https://agentmods.dev/instructions/nkmr-jp/prompt-line/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/nkmr-jp/prompt-line/claude-md"><img src="https://agentmods.dev/badge/instructions/nkmr-jp/prompt-line/claude-md/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for prompt-line CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/nkmr-jp/prompt-line/claude-md"><img src="https://agentmods.dev/badge/instructions/nkmr-jp/prompt-line/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 4,023 This file is loaded in full into every session.
When invoked 4,023 The same file — it is already loaded in full.
Security scan A 2 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.04023 $0.04023
Opus 5 $0.02011 $0.02011
Sonnet 5 $0.00805 $0.00805
Haiku 4.5 $0.00402 $0.00402

Measured 12d ago against content hash 3b57216aa8c7, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

prompt-line CLAUDE.md scanned grade A with 2 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 12d 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

- `curl http://localhost:9222/json/list` to get WebSocket URL for the renderer page

Runs shell commandslowCapability

Expected in a hook, worth knowing in a rule or an instructions file.

- **Mocks**: Comprehensive mocks in `tests/setup.ts` (Electron APIs, fs, child_process, IPC)
CLAUDE.md · 285 lines

How it starts

The opening of the file, as written. The whole thing — 285 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.

Essential Commands

Development

pnpm start          # Run app in development mode (with DEBUG logging enabled)
pnpm run reset-accessibility      # Reset accessibility permissions for Prompt Line
  • pnpm run setup-codesign creates a "Prompt Line" self-signed certificate in the login Keychain. Automatically run by install-app, so manual execution is not needed.
  • pnpm start sets LOG_LEVEL=debug automatically. Packaged apps always use INFO level.
  • Logs: ~/.prompt-line/app.log (use tail -f ~/.prompt-line/app.log for real-time monitoring)

Isolated Verification Instance (per worktree)

Verify the checkout you are working in without disturbing the Prompt Line the user keeps running.

pnpm run isolated start              # Compile if needed, then launch headless in the background
pnpm run isolated show               # Run the real show flow (renderer gets history/draft/settings)
pnpm run isolated type "@"           # Type into the input, as a user would
pnpm run isolated clear              # Empty the input
pnpm run isolated eval "<js>"        # Evaluate JavaScript in the renderer
pnpm run isolated screenshot out.png # Capture the offscreen window
pnpm run isolated logs -n 40         # Tail this instance's app.log
pnpm run isolated status
pnpm run isolated stop               # `clean` also deletes the instance's data directory

How the isolation works (scripts/isolated-instance.js):

  • PROMPT_LINE_DATA_DIR=~/.prompt-line-isolated/<worktree>/data — its own history, drafts, settings, log, plugins and cache. On first start, settings.yaml, plugins/ and custom-search/ are copied (never symlinked) from ~/.prompt-line so verification runs against a realistic config; pass --no-seed for a pristine one.
  • Its own Electron --user-data-dir, so it gets its own single-instance lock and runs alongside the installed app.
  • PROMPT_LINE_ISOLATED=1 — no global shortcut (no fight over Cmd+Shift+Space), no tray icon, no native warmup, and the window is never shown or focused. The renderer still paints offscreen, so CDP screenshots show the real UI.
  • CDP port derived from the worktree directory name (9300–9399), so parallel worktrees never collide. Two checkouts whose directories share a name are rejected (the state file records repoRoot) — set PROMPT_LINE_INSTANCE_ID to give one of them a distinct id.
  • The CDP-driven commands (type, clear, eval, screenshot) need Node 22+ (global WebSocket); start/stop/status/show/logs run on the version in engines.

Read the full file on GitHub · 285 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. 12d ago First seen · 285 lines · 4,023 tokens per session scan A 3b57216aa8c7

Subscribe to this mod's changes

prompt-line CLAUDE.md is an instructions file published in the GitHub repository nkmr-jp/prompt-line (148 stars, last pushed 4d ago), licensed MIT. It adds 4,023 tokens to every session, about $0.0201 per session on Opus 5. A static security scan graded it A with 2 findings (makes network calls, runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Claude Codecodex-cligemini-cli
Related

Other instructions, from other repositories

next.js AGENTS.md

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

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 · 5,153 tokens

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

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 · 4,469 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