analyze-github

A command for investigating a GitHub issue that reports a production incident, meaning a problem affecting a live service. It gathers the issue details, related code, and Git history to produce a root-cause report.

In plain words
What is it for?
Use it to examine a GitHub issue number or URL, collect comments and related references, find matching code and errors, and trace relevant changes through Git history.
Why use it?
It brings incident evidence into one investigation instead of requiring you to search the issue, codebase, and commit history separately.

Command

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/evangelosmeklis/thufir/analyze-github
Clone the repo
git clone --depth 1 https://github.com/evangelosmeklis/thufir
Per session 19 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,892 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 $0.00019 $0.01892
Opus 5 $0.00010 $0.00946
Sonnet 5 $0.00004 $0.00378
Haiku 4.5 $0.00002 $0.00189

Measured 2d ago against content hash b28e0c78c1f4, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

analyze-github 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.

commands/analyze-github.md · 276 lines

How it starts

The opening of the file, as written. The whole thing — 276 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Analyze GitHub Issue Command

Purpose

Investigate a GitHub issue reporting a production problem by fetching issue details, extracting error information, searching the codebase for related code, analyzing git history, and generating a root cause analysis report.

Instructions for Claude

When this command is invoked, perform comprehensive root cause analysis for a GitHub issue:

Step 1: Gather Issue Information

If user provided issue number:

  1. Read settings from .claude/thufir.local.md to get default repo
  2. Use github MCP tool to fetch issue details:
    • Tool: github_get_issue
    • Parameters: {issue_number: <number>}

If user provided issue URL:

  1. Parse URL to extract owner, repo, and issue number
  2. Use github MCP tool with parsed values

If no argument provided:

  1. Use AskUserQuestion to ask:
    • "What is the GitHub issue number?"
    • Or "What repository? (leave blank for default from settings)"

Extract from issue:

  • Issue number and title
  • Issue body/description
  • Labels (look for "production", "incident", "p0", "bug")
  • Created/updated timestamps
  • Comments (read comments for additional context)
  • Assignees
  • Related PRs or issues mentioned

Step 2: Parse Error Information

From issue body and comments, extract:

  1. Error messages:

    • Stack traces
    • Error names (e.g., "ConnectionPoolExhausted")
    • Error codes (500, 503, timeout, etc.)
  2. Reproduction details:

    • Steps to reproduce
    • Affected features or endpoints
    • User actions that trigger error
  3. Impact information:

    • When error first occurred (timestamp)
    • How many users affected
    • Frequency (one-time, intermittent, constant)
    • Geographic or segment-specific
  4. System context:

    • Service or component mentioned
    • Environment (production, staging)
    • Browser or client information

Parse patterns like:

  • "Users are getting 500 errors..."
  • "Error: ConnectionPoolExhausted at 14:32 UTC"
  • "Stack trace: ..."
  • "Approximately 15,000 users affected"

Read the full file on GitHub · 276 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 · 276 lines · 19 tokens per session scan A b28e0c78c1f4

Subscribe to this mod's changes

analyze-github is a command published in the GitHub repository evangelosmeklis/thufir (7 stars, last pushed 8mo ago), licensed MIT. It adds 19 tokens to every session and 1,892 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.