finesse-linear

finesse-linear is a command for coding agents from jonathanung/finesse. It costs 18 tokens per session (1,153 once invoked), scanned A, original, MIT.

A command that fetches a Linear issue—a work item from the Linear project-management service—and sends it to Finesse for planning.

In plain words
What is it for?
Use it to turn a Linear issue into a structured Finesse or Finesse Mini planning task, with an optional refinement limit.
Why use it?
It removes the need to copy issue details into a planning request and accepts either an issue ID or URL.

Command

Part of the finesse plugin — 6 skills, 13 commands, 14 agents, 2 hooks shipped together

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 commands/jonathanung/finesse/finesse-linear
Clone the repo
git clone --depth 1 https://github.com/jonathanung/finesse

Or install finesse, the plugin that ships this one along with the rest of its 6 skills, 13 commands, 14 agents, 2 hooks.

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.

agentmods badge for finesse-linear

README.md
[![agentmods](https://agentmods.dev/badge/commands/jonathanung/finesse/finesse-linear.svg)](https://agentmods.dev/commands/jonathanung/finesse/finesse-linear)
Your own site
<a href="https://agentmods.dev/commands/jonathanung/finesse/finesse-linear"><img src="https://agentmods.dev/badge/commands/jonathanung/finesse/finesse-linear.svg" alt="Measured on agentmods" height="20"></a>
Per session 18 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,153 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 $0.00018 $0.01153
Opus 5 $0.00009 $0.00576
Sonnet 5 $0.00004 $0.00231
Haiku 4.5 $0.00002 $0.00115

Measured 3d ago against content hash 7f345bc09a75, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

finesse-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 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.

plugins/finesse/commands/finesse-linear.md · 131 lines

How it starts

The opening of the file, as written. The whole thing — 131 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Finesse Linear — Issue-Driven Planning

Fetch a Linear issue via MCP and delegate to /finesse or /finesse-mini with a structured task description. This is a lightweight wrapper — all planning logic lives in the delegated command.

Argument Parsing

Parse $ARGUMENTS:

  1. Extract flags first:

    • --max-refinements N — store N, remove from arguments. Passed through to /finesse.
    • --mini — store as boolean, remove from arguments. Delegates to /finesse-mini instead of /finesse.
  2. Extract issue identifier from remaining arguments:

    • If the argument is a URL containing issue/([A-Z]+-[0-9]+), extract the issue ID from the match.
    • If the argument matches [A-Z]+-[0-9]+ directly, use it as the issue ID.
    • If neither pattern matches, say: "Could not parse a Linear issue ID. Provide a URL (e.g., https://linear.app/team/issue/PF-254/...) or a raw ID (e.g., PF-254)." and STOP.
  3. If $ARGUMENTS is empty or blank: Ask the user for the Linear issue URL or ID using AskUserQuestion. Then parse the response as in step 2.

  4. If multiple issue-like arguments are present: Use the first one. Say: "Multiple issues detected — using [ID]. Run /finesse-linear separately for each issue."

Step 1: Fetch Issue Data

Call the MCP tool mcp__linear-server__get_issue with the extracted issue ID.

If the MCP tool is unavailable

If the tool call fails because the MCP server is not configured or the tool is not found, display:


Linear MCP Server Not Available

/finesse-linear requires the Linear MCP server. To set it up:

  1. Get a Linear API key from https://linear.app/settings/api

  2. Add to your MCP configuration (.mcp.json in project root or ~/.claude/mcp.json globally):

{
  "mcpServers": {
    "linear-server": {
      "command": "npx",
      "args": ["-y", "@anthropic/linear-mcp-server"],
      "env": {
        "LINEAR_API_KEY": "your-api-key-here"
      }
    }
  }
}
  1. Restart Claude Code to load the server.

Read the full file on GitHub · 131 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. 3d ago First seen · 131 lines · 18 tokens per session scan A 7f345bc09a75

Subscribe to this mod's changes

finesse-linear is a command published in the GitHub repository jonathanung/finesse (4 stars, last pushed 6mo ago), licensed MIT. It adds 18 tokens to every session and 1,153 once invoked, about $0.0001 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.