What is linearis AGENTS.md?

A contributor guide for Linearis, a Node.js command-line tool that connects to Linear and returns structured JSON for people and AI agents.

Running tests and builds, regenerating GraphQL types, checking code with Biome, updating usage documentation, and creating compliant commits.

It records the project's runtime, build, test, formatting, code-generation, and commit rules so changes match the repository's expectations.

linearis AGENTS.md — Instructions file by linearis-oss

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/linearis-oss/linearis/agents-md

Clone the repo

git clone --depth 1 https://github.com/linearis-oss/linearis

Made for: Codex, OpenCode.

Per session 2,381 This file is loaded in full into every session.

When invoked 2,381 The same file — it is already loaded in full.

Security scan A 0 findings. 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.

Model	Per session	Once invoked
Fable 5	$0.02381	$0.02381
Opus 5	$0.01190	$0.01190
Sonnet 5	$0.00476	$0.00476
Haiku 4.5	$0.00238	$0.00238

Measured 2d ago against content hash f967bf420dbf, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

linearis 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 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.

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.

AGENTS.md · 243 lines

How it starts

The opening of the file, as written. The whole thing — 243 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md

Identity

Linearis is a CLI tool for Linear.app that outputs JSON only (except help/usage text). It is designed for both human users and LLM agents, optimized for minimal token usage and maximum structure.

Runtime: Node.js ≥ 22, ES Modules, TypeScript strict mode
Package manager: npm
Formatter/Linter: Biome (npm run check)
Tests: Vitest (npm test)
GraphQL codegen: npm run generate (never edit src/gql/)

Audience

This file is for AI coding agents working on the Linearis codebase. For user documentation, see README.md. For human contributor guidelines, see CONTRIBUTING.md.

Quick Commands

npm install          # install deps, codegen, and lefthook (via prepare hook)
npm test             # unit tests (vitest)
npm run build        # compile to dist/
npm run generate     # regenerate GraphQL types from .graphql files
npm run check        # biome format + lint (auto-fix)
npm run check:ci     # biome format + lint (CI, no fix)
npm run generate:usage  # regenerate USAGE.md

Commit Rules

Conventional Commits required (enforced by commitlint via lefthook).
Issue/PR refs in commit body when applicable: Closes #n, Refs #n, Part of #n.
No AI co-author trailers. Do not add Co-authored-by for AI assistants.

See CONTRIBUTING.md for the full commit types table and examples.

Architecture (5 Layers)

CLI Input → Command → Resolver → Service → JSON Output
               │         │          │
           createContext GraphQL  GraphQL
                        (UUID)   (data)

Layer	Directory	Client	Responsibility
Client	`src/client/`	—	Thin API wrappers, no logic
Resolver	`src/resolvers/`	`GraphQLClient`	Human ID → UUID conversion
Service	`src/services/`	`GraphQLClient`	Business logic, CRUD via GraphQL
Command	`src/commands/`	`GraphQLClient` via `createContext()`	CLI orchestration only
Common	`src/common/`	—	Shared types, errors, output, auth

Read the full file on GitHub · 243 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.

2d ago First seen · 243 lines · 2,381 tokens per session scan A f967bf420dbf

Subscribe to this mod's changes

linearis AGENTS.md is an instructions file published in the GitHub repository linearis-oss/linearis (248 stars, last pushed 3d ago), licensed MIT. It adds 2,381 tokens to every session, about $0.0119 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.

Backend and APIs Git and workflow LLM Testing agent cli command-line-tool linear linearapp

linearis AGENTS.md

Getting it into your agent

What it costs to keep this loaded

Grade A, and why

Nothing flagged

How it starts

AGENTS.md

Identity

Audience

Quick Commands

Commit Rules

Architecture (5 Layers)

What this file has done since we first saw it

Other instructions, from other repositories

linear-cli AGENTS.md

linctl CLAUDE.md

linear-cli CLAUDE.md

intelligent-terminal rust.instructions.md

InvestSkill GEMINI.md

she-love-me CLAUDE.md