cli: Instructions file for GitHub Copilot

.github/copilot-instructions.md

cli copilot-instructions.md is an instructions file for GitHub Copilot from entireio/cli. It costs 1,352 tokens per session, scanned A, original, MIT.

Development instructions for Entire CLI, a Go command-line tool that records AI coding-agent sessions as searchable metadata separate from Git commits. Git commits are saved snapshots of code changes.

In plain words
What is it for?
Developing the CLI, session and checkpoint handling, error reporting, formatting, linting, unit tests, and race-detection checks.
Why use it?
They explain the project’s purpose and required formatting, linting, and test checks so changes can be validated consistently.

Instructions file for GitHub Copilot

Written for GitHub Copilot: a Copilot instructions file. Also seen: mentions CLAUDE.md; mentions Claude Code; mentions Codex.

This is entireio/cli's own configuration. It tells GitHub Copilot how to work on cli itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything cli configures →

About the project

Entire CLI connects AI coding-agent sessions to Git so prompts, responses, files, tool calls, and checkpoints become a searchable record alongside commits. Developers and teams use it to understand why code changed, resume earlier sessions, keep agent context out of Git history, and support traceability. The catalogue includes commands, hooks, skills, agents, and plugins for the Entire workflow.

entireio/cli · 5,253 stars · on GitHub · entire.io

Reuse

Borrowing it

Nothing to install: this file belongs to entireio/cli. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/entireio/cli/main/.github/copilot-instructions.md
Clone the repo
git clone --depth 1 https://github.com/entireio/cli

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 cli copilot-instructions.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/entireio/cli/copilot-instructions/github.svg)](https://agentmods.dev/instructions/entireio/cli/copilot-instructions)
Your own site
<a href="https://agentmods.dev/instructions/entireio/cli/copilot-instructions"><img src="https://agentmods.dev/badge/instructions/entireio/cli/copilot-instructions/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for cli copilot-instructions.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/entireio/cli/copilot-instructions"><img src="https://agentmods.dev/badge/instructions/entireio/cli/copilot-instructions.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 1,352 This file is loaded in full into every session.
When invoked 1,352 The same file — it is already loaded in full.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.01352 $0.01352
Opus 5.5 $0.00541 $0.00541
Sonnet 5.5 $0.00270 $0.00270
Haiku 4.5 $0.00135 $0.00135

Measured 1mo ago against content hash e55d2e0b614e, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

cli 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 1mo 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 · 151 lines

How it starts

The opening of the file, as written. The whole thing — 151 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Copilot Instructions for Entire CLI

Repository Overview

Entire CLI is a Go CLI tool that captures AI coding agent sessions (Claude Code, Codex, Antigravity, OpenCode, Cursor, Factory AI Droid, Copilot CLI, etc.) as searchable metadata stored separately from code commits. It uses a strategy pattern for session/checkpoint management with minimal impact on commit history.

Tech Stack: Go (version in mise.toml), Cobra (CLI), charmbracelet/huh (interactive prompts), go-git/v5 (with caveats)

Build & Validation Commands

All commands use mise as the task runner. Always run these in order before committing:

mise run fmt           # Format with gofmt (required - CI will fail otherwise)
mise run lint          # Lint with golangci-lint (only new issues)
mise run test          # Unit tests
mise run test:ci       # Full tests with race detection (same as CI)

CI runs these checks on every PR (see .github/workflows/):

  1. gofmt formatting check (must pass - no unformatted files)
  2. golangci-lint
  3. go.mod tidy check
  4. All tests with race detection (mise run test:ci)

Critical Code Patterns

Error Handling

The CLI uses SilentError to avoid duplicate error output (see errors.go):

// When you print a custom error message, return SilentError
fmt.Fprintln(cmd.ErrOrStderr(), "User-friendly error message")
return NewSilentError(errors.New("internal error"))

// For normal errors, just return them - main.go will print
return fmt.Errorf("failed to do X: %w", err)

Forbidden go-git Operations

NEVER use go-git v5's Reset or Checkout directly - they delete .gitignored directories.

// WRONG - deletes .entire/ and .worktrees/
worktree.Reset(&git.ResetOptions{Mode: git.HardReset, Commit: hash})
worktree.Checkout(&git.CheckoutOptions{Branch: ref})

// CORRECT - use CLI wrappers from strategy/common.go and git_operations.go
HardResetWithProtection(hash)
CheckoutBranch(branch)

Path Handling

NEVER use os.Getwd() for git-relative paths - breaks when running from subdirectories.

Read the full file on GitHub · 151 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. 1mo ago Changed · +4 tokens per session e55d2e0b614e
  2. 1mo ago Changed · +38 tokens per session 6864b8e1780c
  3. 1mo ago First seen · 151 lines · 1,310 tokens per session scan A 2179e52ce51a

Subscribe to this mod's changes

cli copilot-instructions.md is an instructions file published in the GitHub repository entireio/cli (5,253 stars, last pushed today), licensed MIT. It adds 1,352 tokens to every session, about $0.0054 per session on Opus 5.5. 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.

Related

Other instructions, from other repositories