What is linear-cli CLAUDE.md?

Project instructions for linear-cli, a Go command-line tool for managing Linear, a service for tracking issues and projects.

Building, testing, and extending the CLI, including its commands, Linear connection, login flow, and project settings.

They explain how agents should authenticate, choose a team, use commands, and follow the repository structure.

linear-cli CLAUDE.md — Instructions file by joa23

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/joa23/linear-cli/claude-md

Clone the repo

git clone --depth 1 https://github.com/joa23/linear-cli

Per session 2,551 This file is loaded in full into every session.

When invoked 2,551 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	$0.02551	$0.02551
Opus 5	$0.01275	$0.01275
Sonnet 5	$0.00510	$0.00510
Haiku 4.5	$0.00255	$0.00255

Measured 2d ago against content hash 576d307d8f52, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

linear-cli CLAUDE.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.

CLAUDE.md · 341 lines

How it starts

The opening of the file, as written. The whole thing — 341 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

Linear CLI - A token-efficient CLI for Linear, written in Go.

Commands

make build    # Build binary (bin/linear)
make test     # Run unit tests
make clean    # Clean build artifacts

Project Structure

cmd/linear/          # CLI entry point
internal/cli/        # CLI commands (Cobra)
internal/format/     # ASCII formatters for token-efficient output
pkg/linear/          # Linear GraphQL client (public library)
internal/service/    # Service layer
internal/skills/     # Embedded Claude Code skills
internal/oauth/      # OAuth2 flow
internal/token/      # Secure token storage

For AI Agents (Claude Code)

Essential Setup

Step 1: Authenticate and set mode

linear auth login    # Choose "Agent" mode for bots/automation
linear auth status   # Verify: should show "Mode: Agent"

Step 2: Set default team

linear init          # Select default team - creates .linear.yaml

Step 3 (optional): Set default project

Edit .linear.yaml to add a default project:

# .linear.yaml
team: CEN
project: my-project  # optional — used when --project flag is omitted

When set, commands with --project (issues list, issues create, issues update, search, deps) will use this default. Explicit --project flags always override it.

Authentication Modes

User mode: --assignee me assigns to the human's Linear account
Agent mode: --assignee me assigns to the OAuth app (delegate), visible as a separate entity in Linear

If linear auth status shows "Auth mode not set", re-run linear auth login.

Output Formats

IMPORTANT: All commands now support JSON output for automation and scripting.

Text Output (default) - Token-efficient ASCII format:

linear issues list
linear issues get CEN-123

JSON Output - Machine-readable for parsing:

linear issues list --output json
linear issues get CEN-123 --output json

Verbosity Levels (--format flag):

minimal - Essential fields only (~50 tokens)
compact - Key metadata (~150 tokens, default)
detailed - Complete details, truncated comments (~500 tokens). Use linear issues comments <id> for full text.
full - Complete details, untruncated comments

Read the full file on GitHub · 341 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 · 341 lines · 2,551 tokens per session scan A 576d307d8f52

Subscribe to this mod's changes

linear-cli CLAUDE.md is an instructions file published in the GitHub repository joa23/linear-cli (141 stars, last pushed 1mo ago), licensed MIT. It adds 2,551 tokens to every session, about $0.0128 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.

Languages Productivity Testing

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

buildNext

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

linear-cli CLAUDE.md