goose copilot-instructions.md

goose copilot-instructions.md is an instructions file for GitHub Copilot from aaif-goose/goose. It costs 1,077 tokens per session, scanned A, original, Apache-2.0.

Code-review instructions for Goose, an AI agent framework, focused on high-confidence feedback about security, safety, correctness, and error handling.

In plain words
What is it for?
They guide reviews of unsafe code, command injection, path traversal, credentials, missing validation, race conditions, resource leaks, boundary errors, and incorrect error propagation.
Why use it?
They help reviewers avoid noisy comments while still looking for bugs that could expose secrets, crash the program, or produce incorrect results.

Instructions file for GitHub Copilot

About the project

Goose is an open-source AI agent that runs on a computer as a desktop app, command-line tool, or API and can perform tasks beyond code completion. Developers and other users employ it for coding, research, writing, automation, and data analysis with different language-model providers and extensions. The catalogue add-ons define parts of its agent workflow and behavior.

aaif-goose/goose · 53,916 stars · on GitHub

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 instructions/aaif-goose/goose/copilot-instructions
Clone the repo
git clone --depth 1 https://github.com/aaif-goose/goose

Made for: GitHub Copilot.

Wrote 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.

agentmods badge for goose copilot-instructions.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/aaif-goose/goose/copilot-instructions.svg)](https://agentmods.dev/instructions/aaif-goose/goose/copilot-instructions)
Your own site
<a href="https://agentmods.dev/instructions/aaif-goose/goose/copilot-instructions"><img src="https://agentmods.dev/badge/instructions/aaif-goose/goose/copilot-instructions.svg" alt="Measured on agentmods" height="20"></a>
Per session 1,077 This file is loaded in full into every session.
When invoked 1,077 The same file — it is already loaded in full.
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 $0.01077 $0.01077
Opus 5 $0.00539 $0.00539
Sonnet 5 $0.00215 $0.00215
Haiku 4.5 $0.00108 $0.00108

Measured 5d ago against content hash dc8ca0a52b54, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

goose copilot-instructions.md 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 5d 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.

.github/copilot-instructions.md · 102 lines

How it starts

The opening of the file, as written. The whole thing — 102 lines — stays where its author put it; the contents beside it link to each section on GitHub.

GitHub Copilot Code Review Instructions

Review Philosophy

  • Only comment when you have HIGH CONFIDENCE (>80%) that an issue exists
  • Be concise: one sentence per comment when possible
  • Focus on actionable feedback, not observations
  • When reviewing text, only comment on clarity issues if the text is genuinely confusing or could lead to errors. "Could be clearer" is not the same as "is confusing" - stay silent unless HIGH confidence it will cause problems

Priority Areas (Review These)

Security & Safety

  • Unsafe code blocks without justification
  • Command injection risks (shell commands, user input)
  • Path traversal vulnerabilities
  • Credential exposure or hardcoded secrets
  • Missing input validation on external data
  • Improper error handling that could leak sensitive info

Correctness Issues

  • Logic errors that could cause panics or incorrect behavior
  • Race conditions in async code
  • Resource leaks (files, connections, memory)
  • Off-by-one errors or boundary conditions
  • Incorrect error propagation (using unwrap() inappropriately)
  • Optional types that don't need to be optional
  • Booleans that should default to false but are set as optional
  • Error context that doesn't add useful information (e.g., .context("Failed to do X") when error already says it failed)
  • Overly defensive code that adds unnecessary checks
  • Unnecessary comments that just restate what the code already shows (remove them)

Architecture & Patterns

  • Code that violates existing patterns in the codebase
  • Missing error handling (should use anyhow::Result)
  • Async/await misuse or blocking operations in async contexts
  • Improper trait implementations

No Doc Updates with Code Changes

  • PRs with code changes shouldn't update /documentation - docs deploy on merge, code on release. Use unlisted: true or remove/hide docs.

Project-Specific Context

  • This is a Rust project using cargo workspaces
  • Core crates: goose (agent logic and ACP server), goose-cli (CLI), goose-mcp (MCP servers)
  • Error handling: Use anyhow::Result, not unwrap() in production code
  • Async runtime: tokio
  • MCP protocol implementations require extra scrutiny
  • Naming convention: In documentation/docs and documentation/blog, always refer to the project as "goose" (lowercase), never "Goose" (even at the start of sentences)

Read the full file on GitHub · 102 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. 5d ago First seen · 102 lines · 1,077 tokens per session scan A dc8ca0a52b54

Subscribe to this mod's changes

goose copilot-instructions.md is an instructions file published in the GitHub repository aaif-goose/goose (53,916 stars, last pushed today), licensed Apache-2.0. It adds 1,077 tokens to every session, about $0.0054 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 2026-08-30.