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/evex-dev/linejs/agents-mdgit clone --depth 1 https://github.com/evex-dev/linejsWhat 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 | $0.00630 | $0.00630 |
| Opus 5 | $0.00315 | $0.00315 |
| Sonnet 5 | $0.00126 | $0.00126 |
| Haiku 4.5 | $0.00063 | $0.00063 |
Grade A, and why
linejs AGENTS.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 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.
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.
How it starts
The opening of the file, as written. The whole thing — 47 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Repository Guidelines
Project Structure & Module Organization
This repository is a Deno-first monorepo.
packages/linejs: main TypeScript library (@evex/linejs) with feature modules underclient,base, andthrift.packages/types: shared LINE type definitions (@evex/linejs-types).docs: VitePress documentation site and content.example: runnable examples for browser, node, talk, square, storage, thrift, etc.scripts: generation/utility scripts, including thrift tooling and service/type helpers.resources: static assets used by the project.
README.md in the root points to packages/linejs/README.md for package-level context.
Build, Test, and Development Commands
deno task dev: run local sandbox (workspace root).deno task docs:dev: run docs dev server fromdocs.deno task docs:build: build docs fromdocs.cd docs && npm run dev|build|serveorbun run dev|build|serve: alternate docs workflows.deno test: run the Deno test suite (CI uses this at repository root).cd packages/linejs && deno test: run package-scoped tests.deno fmt: apply repository formatter (configured indeno.json).
Coding Style & Naming Conventions
- Use Deno formatter settings from repo: tabs for indentation, double quotes in most files.
- Keep TypeScript across all source files and prefer explicit typing for public APIs.
- Use clear, domain-based names:
camelCasefor functions/variables,PascalCasefor classes/types. - File names are typically kebab-case or snake-like and placed under relevant feature folders (
client/features/*,base/*).
Testing Guidelines
- Test framework: Deno’s built-in test runner.
- Test files use
*_test.tsnaming, e.g.packages/linejs/base/core/typed-event-emitter/index.test.ts. - Run tests before PRs:
deno testor package-scoped commands above. - Add/adjust unit coverage when changing logic in touched files; keep existing test conventions.
Commit & Pull Request Guidelines
- Commit history mostly follows Conventional Commit style (
feat:,fix:,chore:,testing:). - Use short, imperative summaries, e.g.
feat(client): add message retry logic. - PR description should explain behavior changes and testing performed.
- Include reproduction notes when behavior depends on credentials, protocol behavior, or network-sensitive paths.
- Optional checklist items in
.github/pull_request_template.md: tests, jsdoc updates, local runtime checks.
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.
- 3d ago First seen · 47 lines · 630 tokens per session scan A e88bba60f580
linejs AGENTS.md is an instructions file published in the GitHub repository evex-dev/linejs (374 stars, last pushed 5d ago), licensed MIT. It adds 630 tokens to every session, about $0.0032 per session on Opus 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 2026-08-30.
Other instructions, from other repositories
deno CLAUDE.md
Claude Code instructions for denoland/deno, covering deno development guide, git workflow, high level overview, key directories and quick start.
appwrite AGENTS.md
AGENTS.md instructions for appwrite/appwrite, covering appwrite, commands, stack, layout and libraries.
conductor CLAUDE.md
Claude Code instructions for conductor-oss/conductor, covering claude.md — conductor (server repo), writing documentation, for each content type, start here, when you can't verify and key source locations.
eve AGENTS.md
Instructions for vercel/eve, covering agents.md, about eve, repository layout, git workflow and commands.
oxc copilot-instructions.md
Instructions for oxc-project/oxc: When reviewing pull requests in this repository.
joint CLAUDE.md
Instructions for clientIO/joint, covering claude.md, project overview, common commands, install dependencies and build distribution files (runs grunt).