subcog copilot-instructions.md

Project instructions for GitHub Copilot, an AI coding assistant, working on a Rust package. They define the project’s Rust version, tools, testing approach, error-handling style, and code expectations.

In plain words
What is it for?
Use them when asking Copilot to add or change Rust code, especially public functions, error types, tests, formatting, linting, and dependency checks.
Why use it?
They give generated code the project context needed to fit its existing quality and safety rules, such as returning errors instead of crashing.

Instructions file for GitHub Copilot

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

Made for: GitHub Copilot.

Per session 1,320 This file is loaded in full into every session.
When invoked 1,320 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
Origin 92% copy Near-identical to another mod 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 $0.01320 $0.01320
Opus 5 $0.00660 $0.00660
Sonnet 5 $0.00264 $0.00264
Haiku 4.5 $0.00132 $0.00132

Measured 2d ago against content hash 3df0c09d0bf1, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

subcog 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 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.

Origin

This is a copy

92% identical to rlm-rs copilot-instructions.md — 6 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

.github/copilot-instructions.md · 270 lines

How it starts

The opening of the file, as written. The whole thing — 270 lines — stays where its author put it; the contents beside it link to each section on GitHub.

GitHub Copilot Instructions

This document provides context for GitHub Copilot when working with this Rust project.

Project Context

This is a Rust crate using modern tooling:

  • Rust: 1.80+ (2024 edition)
  • Build System: Cargo
  • Linting: clippy with pedantic and nursery lints
  • Formatting: rustfmt
  • Testing: Built-in test framework + proptest
  • Supply Chain Security: cargo-deny

Code Generation Guidelines

Error Handling

Use Result types instead of panicking:

// Good - Returns Result
pub fn parse_value(input: &str) -> Result<i64, ParseError> {
    input.parse().map_err(|e| ParseError::InvalidFormat(e))
}

// Avoid - Panics on failure
pub fn parse_value(input: &str) -> i64 {
    input.parse().unwrap() // Never do this
}

Use thiserror for custom error types:

use thiserror::Error;

#[derive(Error, Debug)]
pub enum AppError {
    #[error("invalid input: {0}")]
    InvalidInput(String),

    #[error("operation failed: {operation}")]
    OperationFailed { operation: String },

    #[error(transparent)]
    Io(#[from] std::io::Error),
}

Type Annotations

Provide explicit return types for public functions:

// Good - explicit return type
pub fn process_data(items: &[String]) -> Vec<ProcessedItem> {
    // implementation
}

// Avoid for public APIs
pub fn process_data(items: &[String]) -> impl Iterator<Item = ProcessedItem> {
    // implementation
}

Documentation

Use doc comments with examples:

/// Processes a list of items according to the given configuration.
///
/// # Arguments
///
/// * `items` - The items to process.
/// * `config` - Configuration options for processing.
///
/// # Returns
///
/// A vector of processed items.
///
/// # Errors
///
/// Returns [`Error::InvalidInput`] if any item is invalid.
///
/// # Examples
///
/// ```rust
/// use {{crate_name}}::{process, Config};
///
/// let items = vec!["a", "b", "c"];
/// let config = Config::default();
/// let result = process(&items, &config)?;
/// # Ok::<(), {{crate_name}}::Error>(())
/// ```
pub fn process(items: &[&str], config: &Config) -> Result<Vec<Item>> {
    // implementation
}

Read the full file on GitHub · 270 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 · 270 lines · 1,320 tokens per session scan A 3df0c09d0bf1

Subscribe to this mod's changes

subcog copilot-instructions.md is an instructions file published in the GitHub repository zircote/subcog (28 stars, last pushed 29d ago), licensed MIT. It adds 1,320 tokens to every session, about $0.0066 per session on Opus 5. A static security scan graded it A with 0 findings. It is 92% identical to rlm-rs copilot-instructions.md, differing in 6 lines, and is treated as a copy.