Borrowing it
Nothing to install: this file belongs to pinecone-io/pinecone-mcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/pinecone-io/pinecone-mcp/main/.cursor/commands/investigate-github-issue.mdgit clone --depth 1 https://github.com/pinecone-io/pinecone-mcpWrote 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.
[](https://agentmods.dev/commands/pinecone-io/pinecone-mcp/investigate-github-issue)<a href="https://agentmods.dev/commands/pinecone-io/pinecone-mcp/investigate-github-issue"><img src="https://agentmods.dev/badge/commands/pinecone-io/pinecone-mcp/investigate-github-issue/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/commands/pinecone-io/pinecone-mcp/investigate-github-issue"><img src="https://agentmods.dev/badge/commands/pinecone-io/pinecone-mcp/investigate-github-issue.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00000 | $0.01413 |
| Opus 5.5 | $0.00000 | $0.00565 |
| Sonnet 5.5 | $0.00000 | $0.00283 |
| Haiku 4.5 | $0.00000 | $0.00141 |
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 1mo 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.
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-triagehas determined the issue needs investigation (hasneeds-investigationlabel) - 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-triageinstead) - 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-triagehas 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
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.
- 1mo ago First seen · 159 lines · 0 tokens per session scan A 615d6e12df57
investigate-github-issue is a command published in the GitHub repository pinecone-io/pinecone-mcp (72 stars, last pushed today), 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.
Other commands, from other repositories
barista-fix
Attempt a small, focused fix for a frappe-ui issue and open a draft PR.
fix-issue
Fixes GitHub issues using parallel analysis agents for root cause investigation, code exploration, and regression detection. Reads issue context from gh CLI, searches codebase and memory for related patterns, generates a fix with tests, and links the resolution back to the issue via PR. Includes prevention analysis to…
unbloat
Remove dead code, duplicate files, and unused dependencies with user approval at each step. Backs up before deleting.
payload-revert
Stage reverts for high-confidence payload candidates identified by payload-analysis.
fix-issue
Analyze and fix a GitHub issue end-to-end.
AGENTS
Run the current binary in a temporary test repository with a real PTY. Use tmux-cli when available, capture terminal output, and inspect -vv logs when behavior depends on timing or shell state. Avoid treating a piped command as proof of interactive behavior.