agentmods.dev

base copilot-instructions.md

Repository instructions for Base, a tool that prepares and verifies independent Git repositories for handoff. They make AGENTS.md the main workflow guide and point to other project documentation for details.

In plain words
What is it for?
Use them when preparing a repository, choosing or creating a GitHub issue, creating a branch, linking a pull request, updating project metadata, or changing the repository's product and architecture context.
Why use it?
They keep project setup and handoff work consistent across repositories. The issue, branch, pull-request, metadata, and context rules reduce confusion about how implementation work should be tracked.

Instructions file for GitHub Copilot

119 2d ago A scan 544 tokens original Apache-2.0
View the source file basefoundry/base
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/basefoundry/base/copilot-instructions
Clone the repo
git clone --depth 1 https://github.com/basefoundry/base

Made for: GitHub Copilot.

Per session 544 This file is loaded in full into every session.
When invoked 544 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 $0.00544 $0.00544
Opus 5 $0.00272 $0.00272
Sonnet 5 $0.00109 $0.00109
Haiku 4.5 $0.00054 $0.00054

Measured 2d ago against content hash 343d70576304, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

base 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.

.github/copilot-instructions.md · 49 lines

What it actually says

GitHub Copilot Instructions

Use AGENTS.md as the canonical workflow guidance for Base. These instructions exist to point Copilot at the same repository-owned rules used by other coding agents; they do not replace AGENTS.md, CONTRIBUTING.md, STANDARDS.md, or the .ai-context/ orientation files.

Keep Base focused as the local operating contract for deterministic readiness and handoff across independent Git repositories. Its durable loop is inventory -> prepare -> verify -> trust -> onboard -> hand off. Project application code, project-specific setup, service behavior, and one-off local machine preferences belong in the owning project unless Base is explicitly the right shared layer.

For implementation work, use Base's issue-backed workflow:

  • choose or create the GitHub issue before editing;
  • use the branch shape <category>/<issue>-<YYYYMMDD>-<slug>;
  • do not replace the category with a Copilot-specific or generic agent prefix;
  • link pull requests with Fixes #<issue> or Closes #<issue>;
  • keep Project metadata updated as described in AGENTS.md;
  • update .ai-context/ when a change affects Base's product shape, architecture, command surface, manifest model, release status, or durable workflow guidance.

For a pull request superseded by another pull request, follow the superseded-PR close-and-cleanup rule in AGENTS.md before ending the session.

Follow CONTRIBUTING.md for contribution flow and STANDARDS.md for coding standards. Prefer existing Base helpers, structured parsers, and local command patterns over new one-off conventions.

Use the narrowest relevant validation first:

  • documentation-only changes: git diff --check;
  • Python changes: use the standalone base-cli source checkout and run the focused pytest target with BASE_CLI_SOURCE_DIR=../base-cli/lib/python and PYTHONPATH=../base-cli/lib/python:lib/python:cli/python;
  • Bash command changes: run the focused BATS tests;
  • general Base changes: run basectl test base when practical.

Copilot cloud-agent sessions may run .github/workflows/copilot-setup-steps.yml before work starts. That workflow is only a lightweight environment guardrail; pull requests still need the focused validation above and normal CI review.

Do not require GitHub Copilot for Base development, add personal Copilot or Codex settings, store credentials, or introduce third-party agent methodology as a repo requirement. Translate useful external workflow ideas into smaller Base-native guidance.

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 · 49 lines · 544 tokens per session scan A 343d70576304

Subscribe to this mod's changes

base copilot-instructions.md is an instructions file published in the GitHub repository basefoundry/base (119 stars, last pushed 2d ago), licensed Apache-2.0. It adds 544 tokens to every session, about $0.0027 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.

Code reviewGit and workflowWriting and docsautomationbash-scriptsbootstrapclidev-environmentdeveloper-tools
Related

Other instructions, from other repositories

lazy-starter-kit CLAUDE.md

Instructions for Heoooooon/lazy-starter-kit: Follow the safety rules in AGENTS.md. In particular, never execute recursive rm directly; use lazy-safe-rm for a strict descendant of the current Git workspace.

Heoooooon/lazy-starter-kit · 42 tokens

lazy-starter-kit AGENTS.md

Instructions for Heoooooon/lazy-starter-kit, a project described as: A signed GUI and one safe command to turn macOS, Linux, or Windows into a complete AI development environment — dry-run first, repeatable, and tested.

Heoooooon/lazy-starter-kit · 130 tokens

gentelella CLAUDE.md

Instructions for ColorlibHQ/gentelella, covering claude.md, what this is, commands, architecture and directory layout.

ColorlibHQ/gentelella · 3,768 tokens

gentelella AGENTS.md

Instructions for ColorlibHQ/gentelella, covering agents.md, what this is, setup, architecture and directory layout.

ColorlibHQ/gentelella · 2,591 tokens

gentelella copilot-instructions.md

Instructions for ColorlibHQ/gentelella, covering github copilot instructions — gentelella v4, hard rules, file layout, anti-patterns and commands.

ColorlibHQ/gentelella · 1,726 tokens

maroto AGENTS.md

Instructions for johnfercher/maroto, covering agent instructions, skills, definition of done, contributing commands and tool dependencies.

johnfercher/maroto · 668 tokens