investigate-github-issue

A command for examining a GitHub issue in depth, including its discussion and related code, to find the likely root cause and define next steps.

In plain words
What is it for?
Use it after initial issue triage to analyze unclear bugs, estimate impact and scope, and prepare a fix plan.
Why use it?
It helps when a bug or request is too complex to understand from the issue description alone. It also checks whether investigation has already been done, reducing duplicate work.

Command for Cursor

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/pinecone-io/pinecone-mcp/investigate-github-issue
Clone the repo
git clone --depth 1 https://github.com/pinecone-io/pinecone-mcp

Made for: Cursor.

Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,413 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 $0.00000 $0.01413
Opus 5 $0.00000 $0.00707
Sonnet 5 $0.00000 $0.00283
Haiku 4.5 $0.00000 $0.00141

Measured 3d ago against content hash 615d6e12df57, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

investigate-github-issue 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.

.cursor/commands/investigate-github-issue.md · 159 lines

How it starts

The opening of the file, as written. The whole thing — 159 lines — stays where its author put it; the contents beside it link to each section on GitHub.

investigate-github-issue

Conduct a thorough, deep investigation of a GitHub issue to understand root causes, verify behavior, and produce actionable next steps.

When to use this command:

  • After github-triage has determined the issue needs investigation (has needs-investigation label)
  • When you need to understand root causes before creating a fix plan
  • When an issue is complex or unclear and needs code analysis
  • When you need to assess impact and scope before prioritizing

When NOT to use this command:

  • For initial triage (use github-triage instead)
  • For simple, clear-cut bugs with obvious fixes
  • For straightforward feature requests that don't need technical analysis

IMPORTANT: This command must be idempotent. Before starting, check:

  • If a Linear investigation issue already exists for this GitHub issue
  • If an investigation has already been completed and documented
  • The current state of the GitHub issue (open/closed, labels, comments)
  • If github-triage has already been run (if not, run it first for proper labeling)

Investigation Process

1. Understand the Issue

  • Read the GitHub issue title, description, and all comments thoroughly
  • Extract key information:
    • Problem description and expected vs actual behavior
    • Code examples, error messages, stack traces
    • Environment details (Node.js version, TypeScript version, SDK version, OS, dependencies)
    • Steps to reproduce (if provided)
    • Related issues or PRs mentioned
  • Identify what type of issue this is (bug, feature request, question, etc.)
  • Note any ambiguity or missing information

2. Codebase Analysis

  • Search for relevant code using semantic search:
    • Identify components/modules mentioned in the issue
    • Find code paths that handle the described functionality
    • Locate error handling or validation logic related to the issue
    • Find tests that might be relevant
  • Read and analyze the relevant source code:
    • Understand the current implementation
    • Identify potential root causes
    • Check for similar patterns or related code
    • Review error handling and edge cases
  • Check test coverage:
    • Find existing tests for the affected functionality
    • Identify gaps in test coverage
    • Review test cases that might be related

Read the full file on GitHub · 159 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 · 159 lines · 0 tokens per session scan A 615d6e12df57

Subscribe to this mod's changes

investigate-github-issue is a command published in the GitHub repository pinecone-io/pinecone-mcp (71 stars, last pushed 7d ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 1,413 tokens. 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.