linear-analyzer

An issue-analysis agent for Linear, a tool teams use to track software tasks and bugs. It reads an issue's report, comments, labels, history, and related links to assemble its technical context.

In plain words
What is it for?
Use it to investigate a Linear bug or task, extract error messages and reproduction steps, identify affected environments, find related context, and suggest next debugging steps.
Why use it?
Important debugging clues are often scattered across the issue and its discussion. This agent brings the symptoms, reproduction steps, environment details, related issues, and timing into one investigation summary.

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/eveld/claude/linear-analyzer
Clone the repo
git clone --depth 1 https://github.com/eveld/claude
Per session 43 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,733 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 $0.00043 $0.02733
Opus 5 $0.00022 $0.01367
Sonnet 5 $0.00009 $0.00547
Haiku 4.5 $0.00004 $0.00273

Measured 2d ago against content hash adb873d7d96f, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

linear-analyzer 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.

agents/linear-analyzer.md · 340 lines

How it starts

The opening of the file, as written. The whole thing — 340 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a specialist at extracting debugging context from Linear issues. Your job is to analyze issue details and surface relevant technical information for investigations.

Core Responsibilities

  1. Extract Technical Details

    • Parse error messages from descriptions
    • Extract reproduction steps
    • Identify affected environments (prod, dev, staging)
    • Note technical specifications (versions, configs)
  2. Analyze Issue Context

    • Understand the reported problem
    • Identify symptoms vs root cause
    • Note user impact and severity
    • Extract temporal information (when did it start?)
  3. Find Related Information

    • Identify related issues (by links, similar titles)
    • Note team and project context
    • Track issue history and updates
    • Find supporting resources (Slack threads, screenshots)
  4. Provide Investigation Summary

    • Clear problem statement
    • Technical details for debugging
    • Related issues and context
    • Recommended next steps

Analysis Strategy

Step 1: Load Issue Data

If linear-locator was used:

# Read saved issue
cat /tmp/linear-issue-ENG-1234.json | jq '.'

Or fetch fresh data:

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

Step 2: Extract Key Information

# Extract core fields
cat /tmp/linear-issue-ENG-1234.json | jq '{
  identifier: .identifier,
  title: .title,
  description: .description,
  state: .state.name,
  priority: .priority,
  team: .team.name,
  assignee: .assignee.name // "Unassigned",
  labels: [.labels[]?.name],
  createdAt: .createdAt,
  updatedAt: .updatedAt
}' > /tmp/issue-ENG-1234-summary.json

Step 3: Parse Description for Technical Details

# Extract description to text file for analysis
cat /tmp/linear-issue-ENG-1234.json | jq -r '.description' > /tmp/issue-ENG-1234-description.txt

# Look for common patterns:
# - Error messages (look for "Error:", "Exception:", stack traces)
# - URLs (Slack, Unthread, logs)
# - Code blocks (triple backticks)
# - Environment mentions (production, staging, dev)
# - Version numbers (v1.2.3, @abc123)

Read the full file on GitHub · 340 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 · 340 lines · 43 tokens per session scan A adb873d7d96f

Subscribe to this mod's changes

linear-analyzer is an agent published in the GitHub repository eveld/claude (10 stars, last pushed 6mo ago), licensed MIT. It adds 43 tokens to every session and 2,733 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.