agents copilot-instructions.md

A set of coding rules for a Python project, covering code style, tests, errors, templates, configuration, and command-line interfaces. Pytest is a Python testing tool, while type annotations describe the kinds of values code expects.

In plain words
What is it for?
Use it when adding or changing Python code, writing pytest tests, creating command-line commands, formatting templates, or updating configuration-related code.
Why use it?
It gives coding agents consistent project-specific decisions instead of making them guess. The rules also help keep changes short and tests focused on real failure points.

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/benchflow-ai/agents/copilot-instructions
Clone the repo
git clone --depth 1 https://github.com/benchflow-ai/agents

Made for: GitHub Copilot.

Per session 378 This file is loaded in full into every session.
When invoked 378 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
Origin 100% 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 $0.00378 $0.00378
Opus 5 $0.00189 $0.00189
Sonnet 5 $0.00076 $0.00076
Haiku 4.5 $0.00038 $0.00038

Measured 2d ago against content hash 6a868fc1a4fd, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

agents 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

100% identical to mini-swe-agent copilot-instructions.md — 0 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 · 37 lines

What it actually says

Style guide

  1. Target python 3.10 or higher
  2. Use python with type annotations. Use list instead of List.
  3. Use pathlib instead of os.path. Use Path.read_text() over with ...open() constructs.
  4. Use typer to add interfaces
  5. Keep code comments to a minimum and only highlight particularly logically challenging things
  6. Do not append to the README unless specifically requested
  7. Use jinja for formatting templates
  8. Use dataclass for keeping track config
  9. Do not catch exceptions unless explicitly told to.
  10. Write concise, short, minimal code.
  11. Not every exception has to be caught. Exceptions are a good way to show problems to a user.
  12. This repository rewards minimal code. Try to be as concise as possible.
  13. Do NOT warn about print messages in tests, print statements in tests are OK!

Test style

  1. Use pytest, not unittest.
  2. Do not mock/patch anything that you're not explicitly asked to do
  3. Avoid writing trivial tests. Every test should test for at least one, preferably multiple points of failure
  4. Avoid splitting up code in multiple lines like this: a=func()\n assert a=b. Instead, just do assert func() == b
  5. The first argument to pytest.mark.parametrize should be a tuple (not a string! not a list!), the second argument must be a list (not a tuple!).
  6. Do NOT warn about print messages in tests, print statements in tests are OK!

Here's an example for rule 4:

# bad
result = func()
assert result == b

# good
assert func() == b
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 · 37 lines · 378 tokens per session scan A 6a868fc1a4fd

Subscribe to this mod's changes

agents copilot-instructions.md is an instructions file published in the GitHub repository benchflow-ai/agents (10 stars, last pushed 3d ago), licensed Apache-2.0. It adds 378 tokens to every session, about $0.0019 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to mini-swe-agent copilot-instructions.md, differing in 0 lines, and is treated as a copy.