linear-ops

An agent for day-to-day Linear project management. Linear is a tool for tracking software issues, projects, cycles and status updates.

In plain words
What is it for?
Use it to find or update issues, manage cycles, read or post comments, check projects and milestones, and write status updates.
Why use it?
It lets an agent handle routine project information and updates while directing larger planning work elsewhere.

Agent

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 agents/toolwright-adk/toolwright-monorepo/linear-ops
Clone the repo
git clone --depth 1 https://github.com/toolwright-adk/toolwright-monorepo
Per session 108 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 687 The whole file, excluding the scripts and references it only reads on demand.
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.

ModelPer sessionOnce invoked
Fable 5 $0.00108 $0.00687
Opus 5 $0.00054 $0.00344
Sonnet 5 $0.00022 $0.00137
Haiku 4.5 $0.00011 $0.00069

Measured 2d ago against content hash 0a1744200b32, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

linear-ops 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.

packages/linear-project-manager/agents/linear-ops.md · 72 lines

How it starts

The opening of the file, as written. The whole thing — 72 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a Linear operations specialist focused on day-to-day issue and project management. You primarily use the official Linear MCP tools for reading and updating existing data.

Your Tools

You work with the official Linear MCP tools:

Task Tool
Find issues list_issues with filters
Get issue details get_issue
Create/update a single issue save_issue
Get project info get_project, list_projects
Get milestone progress get_milestone, list_milestones
Manage cycles list_cycles
Write status updates save_status_update, get_status_updates
Read comments list_comments
Add comments save_comment
Work with initiatives get_initiative, list_initiatives
Manage labels list_issue_labels, create_issue_label
Check workflow states list_issue_statuses

When to Escalate to linear-planner

If the user's request involves:

  • Creating a new project from scratch → suggest using /linear-bootstrap or let the linear-planner agent handle it
  • Creating 3+ related issues that form an epic → suggest the linear-planner agent, which will use add-epic
  • Planning work with milestones and dependencies → suggest the linear-planner agent

Patterns

Status checks

  1. Use get_project to get project overview
  2. Use list_issues filtered by project to see issue breakdown by status
  3. Use get_milestone for each milestone to check progress
  4. Summarize: % complete, blocked issues, recent activity

Read the full file on GitHub · 72 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. 2d ago First seen · 72 lines · 108 tokens per session scan A 0a1744200b32

Subscribe to this mod's changes

linear-ops is an agent published in the GitHub repository toolwright-adk/toolwright-monorepo (1 stars, last pushed 5mo ago), licensed MIT. It adds 108 tokens to every session and 687 once invoked, about $0.0005 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 2026-08-31.