github-etiquette

Guidelines for AI agents that work with GitHub issues, pull requests, and comments. They explain safe use of @ mentions, how to refer to agents without notifying unrelated users, and how automated comments should identify the agent.

In plain words
What is it for?
Use it when an AI agent writes or reviews GitHub issues, pull requests, or comments, especially when mentioning contributors or describing another agent's work.
Why use it?
It helps prevent accidental notifications, confusing references, and unclear automated messages on GitHub. It keeps agent activity understandable to human contributors.

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/andrewaltimit/template-repo/github-etiquette
Clone the repo
git clone --depth 1 https://github.com/AndrewAltimit/template-repo
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 760 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 $0.00760
Opus 5 $0.00000 $0.00380
Sonnet 5 $0.00000 $0.00152
Haiku 4.5 $0.00000 $0.00076

Measured 3d ago against content hash ec4a599b807a, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

github-etiquette 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.

docs/agents/github-etiquette.md · 123 lines

How it starts

The opening of the file, as written. The whole thing — 123 lines — stays where its author put it; the contents beside it link to each section on GitHub.

GitHub Etiquette for AI Agents

This document provides essential guidelines for AI agents interacting with GitHub issues, pull requests, and comments.

Critical Rules

1. @ Mentions - Use with Extreme Caution

NEVER use @ mentions for:

  • AI agent names (Gemini, Claude, OpenAI, etc.)
  • Generic role names (reviewer, developer, tester)
  • Any name you're not 100% certain is a real contributor

ONLY use @ mentions for:

  • Repository owner: @AndrewAltimit
  • Contributors explicitly listed in the repository
  • Users who have specifically requested to be mentioned

Why this matters: Using @Gemini or @Claude will ping random GitHub users who happen to have those usernames, causing unnecessary notifications and confusion.

2. Referencing AI Agents

Correct ways to reference AI agents:

  • "Gemini's review indicates..."
  • "As Claude suggested..."
  • "The OpenAI agent found..."
  • "Per the agent's analysis..."

Incorrect ways (DO NOT USE):

  • "@Gemini's review indicates..." [WRONG]
  • "As @Claude suggested..." [WRONG]
  • "CC @OpenAI for visibility..." [WRONG]

3. Comment Formatting

When posting automated comments:

  • Clearly identify yourself as an AI agent
  • Use professional, concise language
  • Include relevant context without being verbose
  • End with a signature line indicating automated generation

Example:

## Automated Code Review

I've analyzed the changes and found the following...

[Review content]

---
*This review was automatically generated by [Agent Name] AI.*

4. Issue and PR Interactions

When creating issues:

  • Use clear, descriptive titles
  • Label appropriately
  • Include all necessary context
  • Never assign to users without permission

When commenting on PRs:

  • Focus on constructive feedback
  • Acknowledge good practices, not just issues
  • Provide actionable suggestions
  • Respect the author's time and effort

5. Error Handling

If you make a mistake (like incorrect @ mention):

  • Acknowledge it promptly in a follow-up comment
  • Update documentation to prevent recurrence
  • Learn from the feedback

Read the full file on GitHub · 123 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 · 123 lines · 0 tokens per session scan A ec4a599b807a

Subscribe to this mod's changes

github-etiquette is an agent published in the GitHub repository AndrewAltimit/template-repo (131 stars, last pushed 1mo ago), licensed Unlicense. It costs nothing until one of its globs matches a file; then it loads 760 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.