pre-commit-hooks copilot-instructions.md

Project instructions for Duolingo’s pre-commit-hooks repository, covering development rules, architecture, deployment workflows, and testing. The instructions point to additional rule files that apply only to particular file types or tasks.

In plain words
What is it for?
Use them when working in that repository to decide which architecture, deployment, root, or testing rules must be read for the files being changed.
Why use it?
They help an agent apply the repository’s own conventions instead of guessing how Swift code, GitHub Actions workflows, general files, or tests should be changed.

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/duolingo/pre-commit-hooks/copilot-instructions
Clone the repo
git clone --depth 1 https://github.com/duolingo/pre-commit-hooks

Made for: GitHub Copilot.

Per session 336 This file is loaded in full into every session.
When invoked 336 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 $0.00336 $0.00336
Opus 5 $0.00168 $0.00168
Sonnet 5 $0.00067 $0.00067
Haiku 4.5 $0.00034 $0.00034

Measured 2d ago against content hash 0bdacb5b88c1, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

pre-commit-hooks 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.

test/after/.github/copilot-instructions.md · 48 lines

What it actually says

Development Rules

Each rule below has the following properties:

  • Description: Tells you exactly when to read and apply this rule to your current task
  • File scope: Defines which files/directories this rule applies to
  • Always apply: false = apply only when relevant; true = always apply this rule

Read the properties of each rule and apply those that match your current task. When you decide to apply a rule, you MUST read the entire contents of the actual rule file using the file path shown

Architecture

Architecture Rule@.cursor/rules/architecture/architecture-rule.mdc

  • Description: Architecture rule description
  • File scope: **/*.swift
  • Always apply: false

Build Deploy

Github Actions@.cursor/rules/build-deploy/github-actions.mdc

  • Description: GitHub Actions workflow guidelines
  • File scope: **/.github/workflows/.yml, /.github/actions//.yml
  • Always apply: false

Root

Rule@.cursor/rules/rule.mdc

  • Description: Rule description
  • File scope: All files
  • Always apply: false

Testing

Testing Rule@.cursor/rules/testing/testing-rule.mdc

  • Description: Testing rule description
  • File scope: **/*Test.swift
  • Always apply: true
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 · 48 lines · 336 tokens per session scan A 0bdacb5b88c1

Subscribe to this mod's changes

pre-commit-hooks copilot-instructions.md is an instructions file published in the GitHub repository duolingo/pre-commit-hooks (68 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 336 tokens to every session, about $0.0017 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.