agentmods.dev

linejs-cli

linejs-cli is a skill for Claude Code, Codex from evex-dev/linejs. It costs 145 tokens per session (3,751 once invoked), scanned A, original, MIT.

A command-line tool for operating a LINE Messenger account from a terminal. It can authenticate, read and send messages and media, manage contacts and groups, and expose the same operations to coding agents.

In plain words
What is it for?
Use it to inspect chats, contacts, groups, OpenChat, media, Timeline, and events, or to send messages and manage account data from automated workflows.
Why use it?
It lets scripts and agents work with LINE without using the graphical app. JSON output makes command results easier for software to read, while account-changing actions still require care.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

not rated 458repo +36 changed today A scan 145 tokens original MIT

Good fit Use it to inspect chats, contacts, groups, OpenChat, media, Timeline, and events, or to send messages and manage account data from automated workflows.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/evex-dev/linejs/linejs-cli
View source ↗ evex-dev/linejs linejs.evex.land
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.

Any agent
npx skills add evex-dev/linejs --skill linejs-cli
Clone the repo
git clone --depth 1 https://github.com/evex-dev/linejs

Made for: Claude Code, Codex.

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 linejs-cli

README.md
[![agentmods](https://agentmods.dev/badge/skills/evex-dev/linejs/linejs-cli/github.svg)](https://agentmods.dev/skills/evex-dev/linejs/linejs-cli)
Your own site
<a href="https://agentmods.dev/skills/evex-dev/linejs/linejs-cli"><img src="https://agentmods.dev/badge/skills/evex-dev/linejs/linejs-cli/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 linejs-cli

Your own site · 80×15
<a href="https://agentmods.dev/skills/evex-dev/linejs/linejs-cli"><img src="https://agentmods.dev/badge/skills/evex-dev/linejs/linejs-cli.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 145 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,751 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 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 $0.00145 $0.03751
Opus 5.5 $0.00058 $0.01500
Sonnet 5.5 $0.00029 $0.00750
Haiku 4.5 $0.00015 $0.00375

Measured today against content hash c6aa609c8b42, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

linejs-cli 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 today.

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.

agent-plugins/linejs-cli/skills/linejs-cli/SKILL.md · 279 lines

How it starts

The opening of the file, as written. The whole thing — 279 lines — stays where its author put it; the contents beside it link to each section on GitHub.

linejs-cli

line is the command-line client for LINEJS. It talks to LINE directly, reuses the same E2EE/session machinery as the library, and exposes contacts, chats, OpenChat, media, Timeline/Note, calls, and raw LINE Thrift/REST methods. Result-producing commands have a --json mode, and the same surface is available to agents through a two-tool MCP server.

This skill is a map, not a frozen manual. The command set is large and still evolving; discover exact arguments with line help <command> or line commands --json instead of guessing.

Ground rules

  1. Check the session before re-authenticating. Run line auth status --json first. Repeated logins can trigger LINE account restrictions.
  2. Use --json for anything you parse. Human output is a table and is not a stable interface.
  3. Confirm before observable or destructive actions. Sending, replying, uploading, unsending, leaving/kicking, blocking, profile edits, deletes, and logout affect a real account. Restate the target MID, chat name, and payload to the user first.
  4. Resolve MIDs; never guess them. Look up the contact or chat and use the returned mid (u… user, c… group, r… room, s… OpenChat square, m… OpenChat chat).
  5. Treat credentials as secrets. ~/.linejs/*.json, line auth token, line storage list --values, and --no-save output contain auth tokens or E2EE keys. Do not print, log, or commit them.
  6. Ask before automating a personal account. Using LINEJS may violate LINE's terms of service and can lead to account restrictions.
  7. Get explicit consent about the BAN risk before setup. Before starting setup (login, etc.), always tell the user that there is an account BAN risk and proceed only after their consent.
  8. Send sparingly — LINE may BAN accounts under heavy request volume. Never hammer on failure or fire rapid retries. Space out requests, keep batches small, and keep total counts low. Do not send more than necessary.
  9. Report errors to evex-dev/linejs Issues. Include the command, error message/code, and version (line --version), excluding tokens, MIDs, and personal info. Check for duplicates first with gh issue list -R evex-dev/linejs, then file with gh issue create -R evex-dev/linejs or another channel.

Read the full file on GitHub · 279 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. today Changed · +3 lines c6aa609c8b42
  2. yesterday First seen · 276 lines · 145 tokens per session scan A 0dbc87f12ec9

Subscribe to this mod's changes

linejs-cli is a skill published in the GitHub repository evex-dev/linejs (458 stars, last pushed yesterday), licensed MIT. It adds 145 tokens to every session and 3,751 once invoked, about $0.0006 per session on Opus 5.5. 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 2026-11-05.

Productivityjavascriptlinelinejsselfbot-line
Related

linejs-cli compared with skills from other repositories

linejs-cli next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
linejs-clievex-dev/linejsSkill458yesterdayMITA145Claude Code, Codex
notion-to-blogwasp-lang/waspSkill19kyesterdayMITA37Claude Code
hero-keymap-pressUnclecheng-li/AI_AnimationSkill1.7k11d agoMITA0Claude Code, Codex
output-meta-project-contextgrowthxai/outputSkill4444d agoApache-2.0A54Claude Code
output-dev-eval-testinggrowthxai/outputSkill4444d agoApache-2.0A47Claude Code
output-eval-error-analysisgrowthxai/outputSkill4444d agoApache-2.0A38Claude Code
output-build-workflowgrowthxai/outputSkill4444d agoApache-2.0A52Claude Code