A set of tools for Linear, a task-management system used to track issues, projects, teams, and backlogs. It supports common issue and project work through the available connector or command-line tools.

Use it to create, update, view, list, and comment on issues, and to manage Linear projects and teams.

It avoids switching between an agent and Linear to manage development tasks. It also provides rules for choosing tools and handling issue references.

linear — Skill for Claude Code by bendrucker/claude

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 bendrucker/claude --skill linear

Clone the repo

git clone --depth 1 https://github.com/bendrucker/claude

Made for: Claude Code.

Or install linear, the plugin that ships this one along with the rest of its 1 skill.

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/bendrucker/claude/linear/github.svg)](https://agentmods.dev/skills/bendrucker/claude/linear)

Your own site

<a href="https://agentmods.dev/skills/bendrucker/claude/linear"><img src="https://agentmods.dev/badge/skills/bendrucker/claude/linear/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/bendrucker/claude/linear"><img src="https://agentmods.dev/badge/skills/bendrucker/claude/linear.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 72 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 845 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. Third-party audits

NVIDIA SkillSpector pass 7 Sept 2026

How audits are shown

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 5.1	$0.00072	$0.00845
Opus 5.5	$0.00029	$0.00338
Sonnet 5.5	$0.00014	$0.00169
Haiku 4.5	$0.00007	$0.00085

Measured 10d ago against content hash 8b7e0ff16173, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

linear 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 10d 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.

plugins/linear/skills/linear/SKILL.md · 51 lines

How it starts

The opening of the file, as written. The whole thing — 51 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Linear

Environment

The connector and MCP paths need no CLI. Before a CLI-only operation (relations without the connector, bulk work), run linear --version, and stay on the connector when it fails. Check CLI subcommands and flags with linear <cmd> --help or the linear-cli:linear-cli skill.

Arguments

$0 is an optional verb (create, update, list, view, comment) and the rest are its params. With no verb, infer the operation from the request.

Tool Selection

Claude.ai connector (mcp__claude_ai_Linear__*) is the primary path. save_issue creates or updates, and takes relations (blocks, blockedBy, relatedTo, duplicateOf), parentId, project, milestone, cycle, estimate, dueDate, and links as params.
Local or plugin MCP splits save_issue into create_issue and update_issue with the same flat fields. Use it when the connector is unavailable.
linear CLI and GraphQL covers bulk work, complex queries, and relations without the connector. Defer to the linear-cli:linear-cli skill for the CLI surface and api.md for raw GraphQL.

Saving an Issue

save_issue creates when id is absent and updates when it is present. An update sends only the fields that change. Relation params are append-only, so a save never removes a relation you did not name. Pass duplicateOf, parentId, project, or cycle as null to clear one. milestone and dueDate have no null clear.

The description body is GFM and renders Linear's first-class constructs directly. Author them inline instead of using a workaround:

Fence code and traces, and put a repro command in a sh block even when it is one line. Fold a pasted log or trace over about 15 lines into a collapsible titled for its source, and keep shorter ones inline.
Draw a mermaid sequence diagram when the report describes several actors interleaving, such as a race or a handoff. A bug in one component doesn't need one.
Turn criteria or tasks the request supplies into a check list (- [ ]). Leave next steps, fix plans, and verification tasks to whoever picks the issue up unless the request lists them.

Read the full file on GitHub · 51 lines

Files

What ships with it

3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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.

10d ago Changed · -2 lines 8b7e0ff16173
18d ago Changed · -67 lines · +31 tokens per session d981bfbfd74c
2mo ago First seen · 120 lines · 41 tokens per session scan A 7636db15611b

Subscribe to this mod's changes

linear is a skill published in the GitHub repository bendrucker/claude (18 stars, last pushed today), licensed MIT. It adds 72 tokens to every session and 845 once invoked, about $0.0003 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 2026-08-30.

Claude Code Project management claude-code-plugin

linear next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
linearbendrucker/claude	Skill	18	today	MIT	A	72	Claude Code
reviewSethGammon/Citadel	Skill	928	4d ago	MIT	A	17	Claude Code
system-upgradealivecontext/alive	Skill	132	yesterday	MIT	A	55	Claude Code
wenlan-handoffwenlan-app/wenlan	Skill	94	today	Apache-2.0	A	43	Claude Code, Codex
extract-resumesuxrobGM/jobpilot	Skill	111	today	MIT	A	32	Claude Code
pr-reviewnitinjain999/platform-skills	Skill	71	yesterday	Apache-2.0	A	81	Claude Code
read-literaturefirecrawl/firecrawl-claude-plugin	Skill	258	3d ago	MIT	A	101	Claude Code