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.
npx agentmods add instructions/entireio/cli/copilot-instructionsgit clone --depth 1 https://github.com/entireio/cliWhat 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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.01310 | $0.01310 |
| Opus 5 | $0.00655 | $0.00655 |
| Sonnet 5 | $0.00262 | $0.00262 |
| Haiku 4.5 | $0.00131 | $0.00131 |
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 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.
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, Gemini CLI, 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/):
- gofmt formatting check (must pass - no unformatted files)
- golangci-lint
- go.mod tidy check
- 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.
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.
- 2d ago First seen · 151 lines · 1,310 tokens per session scan A 2179e52ce51a
cli copilot-instructions.md is an instructions file published in the GitHub repository entireio/cli (5,038 stars, last pushed 2d ago), licensed MIT. It adds 1,310 tokens to every session, about $0.0066 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.
Other instructions, from other repositories
adk-go AGENTS.md
Instructions for google/adk-go, covering agents.md, project overview, setup & core commands, definition of done and repository layout.
adk-go CLAUDE.md
Instructions for google/adk-go: See AGENTS.md for project context, commands, and contribution guidelines for AI coding agents.
agent-starter-pack GEMINI.md
Instructions for GoogleCloudPlatform/agent-starter-pack, covering agent starter pack - ai coding agent guide, core principles for ai agents, project architecture overview, 4-layer template system and key directory structure.
codedb AGENTS.md
Instructions for justrach/codedb, covering codedb agent guidelines, what codedb is (and isn't), review guidelines, pre-merge verification and security-sensitive areas.
codedb copilot-instructions.md
Instructions for justrach/codedb, covering codedb — agent instructions, project, rules, filing issues and test style.
codedb CLAUDE.md
Instructions for justrach/codedb, covering codedb — agent instructions, project, rules, filing issues and test style.