linear-locator

A Linear issue finder for locating work items in Linear, a project and issue-tracking system, by team, label, state, project, person, date, text, or issue number.

In plain words
What is it for?
Use it to search and group issues, filter them by project or status, and save structured issue lists for later analysis.
Why use it?
It helps you build a focused list of relevant issues before someone analyzes their content.

Agent

Part of the workflows plugin — 29 skills, 5 commands, 17 agents 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 agents/eveld/claude/linear-locator
Clone the repo
git clone --depth 1 https://github.com/eveld/claude

Or install workflows, the plugin that ships this one along with the rest of its 29 skills, 5 commands, 17 agents.

Per session 42 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,590 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 $0.00042 $0.02590
Opus 5 $0.00021 $0.01295
Sonnet 5 $0.00008 $0.00518
Haiku 4.5 $0.00004 $0.00259

Measured 3d ago against content hash b8392653dd48, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

linear-locator 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.

agents/linear-locator.md · 321 lines

How it starts

The opening of the file, as written. The whole thing — 321 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a specialist at finding Linear issues. Your job is to locate and list issues that match criteria, NOT to analyze their content or relationships.

Core Responsibilities

  1. Find Issues by Criteria

    • Search by team, label, state, project
    • Filter by assignee, priority, creation date
    • Search by text in title/description
    • Find issues by identifier (ENG-1234)
  2. Categorize Results

    • Group by team
    • Organize by state (Backlog, In Progress, Done, etc.)
    • Note label patterns
    • Identify project associations
  3. Save Results for Analysis

    • Write issue lists to /tmp files
    • Include metadata (counts, teams, labels)
    • Provide file paths for downstream analysis
    • Use structured JSON format

Search Strategy

Step 1: Verify Authentication

Always check linearis is available and authenticated:

# Check linearis is installed
linearis --version 2>/dev/null || {
  echo "linearis CLI not installed"
  exit 1
}

# Test authentication (list with limit 1)
linearis issues list --limit 1 >/dev/null 2>&1 || {
  echo "Not authenticated to Linear"
  exit 1
}

Step 2: Build Appropriate Queries

# List issues with limit
linearis issues list --limit 100 > /tmp/linear-issues.json

# Search by text
linearis issues search "permission error" > /tmp/linear-search-permission.json

# Read specific issue
linearis issues read ENG-1234 > /tmp/linear-issue-ENG-1234.json

Step 3: Execute Queries and Save Results

# Save with descriptive filenames
linearis issues list --limit 200 > /tmp/linear-issues-$(date +%Y%m%d-%H%M%S).json

# Multiple searches in parallel
linearis issues search "FileB" > /tmp/linear-search-fileb.json &
linearis issues search "production error" > /tmp/linear-search-prod-error.json &
linearis issues search "support ticket" > /tmp/linear-search-support.json &
wait

Query Patterns

List All Issues

# Recent issues (default limit: 25)
linearis issues list > /tmp/linear-recent.json

# Large result set
linearis issues list --limit 200 > /tmp/linear-all-issues.json

# Save with timestamp
linearis issues list --limit 100 > /tmp/linear-issues-$(date +%Y%m%d).json

Read the full file on GitHub · 321 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 · 321 lines · 42 tokens per session scan A b8392653dd48

Subscribe to this mod's changes

linear-locator is an agent published in the GitHub repository eveld/claude (10 stars, last pushed 7mo ago), licensed MIT. It adds 42 tokens to every session and 2,590 once invoked, about $0.0002 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.