protocol

protocol is a command for Claude Code from Everyone-Needs-A-Copilot/claude-copilot. It costs 0 tokens per session (10,628 once invoked), scanned A, original, MIT.

A conversation-start command that loads project-specific instructions before applying a shared working protocol. It tells the coding agent which rules take priority for the current project.

In plain words
What is it for?
Use it at the start of agent conversations to check for a project protocol and establish the applicable working rules.
Why use it?
It prevents a machine-wide instruction file from silently overriding rules defined by the project. This helps keep agent behaviour consistent with the project's own instructions.

Command for Claude Code

Written for Claude Code: installed under .claude/. Also seen: reads .claude/ paths; mentions CLAUDE.md; mentions Claude Code.

Part of the claude-copilot plugin — 72 skills, 17 commands, 17 agents, 4 hooks shipped together

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 commands/everyone-needs-a-copilot/claude-copilot/protocol
Clone the repo
git clone --depth 1 https://github.com/Everyone-Needs-A-Copilot/claude-copilot

Made for: Claude Code.

Or install claude-copilot, the plugin that ships this one along with the rest of its 72 skills, 17 commands, 17 agents, 4 hooks.

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 protocol

README.md
[![agentmods](https://agentmods.dev/badge/commands/everyone-needs-a-copilot/claude-copilot/protocol.svg)](https://agentmods.dev/commands/everyone-needs-a-copilot/claude-copilot/protocol)
Your own site
<a href="https://agentmods.dev/commands/everyone-needs-a-copilot/claude-copilot/protocol"><img src="https://agentmods.dev/badge/commands/everyone-needs-a-copilot/claude-copilot/protocol.svg" alt="Measured on agentmods" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 10,628 The whole file, excluding the scripts and references it only reads on demand.
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 5.1 $0.00000 $0.10628
Opus 5 $0.00000 $0.05314
Sonnet 5 $0.00000 $0.02126
Haiku 4.5 $0.00000 $0.01063

Measured today against content hash 5bcf694e8e4f, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

protocol 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 today.

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.

.claude/commands/protocol.md · 1,072 lines

How it starts

The opening of the file, as written. The whole thing — 1,072 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Protocol Enforcement

You are starting a new conversation. The Agent-First Protocol is now active.

Project Protocol Precedence

Before anything else below: check the current project for its own .claude/commands/protocol.md. Claude Code resolves a same-named personal/machine-level command (this file, materialized to ~/.claude/commands/protocol.md) over a project-level one by filename precedence alone -- so without this check, a project's own protocol would silently lose to this machine copy every time, even on a project that intentionally defines its own.

  1. Read .claude/commands/protocol.md relative to the current project's root, if the project has one.
  2. If it exists and its content differs from this file: follow the PROJECT file's instructions in full, in place of everything below this section -- this machine copy is superseded for the rest of this conversation. Declare it: [Protocol: project]. This is expected and correct for a non-software project (documents, presentations, image creation, etc.) whose protocol has nothing to do with the software flows below.
  3. If it is absent, or identical to this file: this file governs, unchanged. Declare it: [Protocol: machine].

Do this check once, before any flow detection or agent routing below -- never mid-flow, and never skipped because a flow already seems obvious from the user's first message.

Command Argument Handling

This command supports an optional task description argument for quick task initiation:

Usage:

  • /protocol - Interactive mode (select task type manually)
  • /protocol [description] - Auto-detect intent and route to appropriate agent chain

Examples:

/protocol add user voice profiles          → Experience Flow (sd → uxd → uids → uid → ta → me)
/protocol fix login authentication bug     → Defect Flow (qa → me → qa)
/protocol refactor auth module             → Technical Flow (ta → me)
/protocol improve the dashboard            → Clarification Flow (ask user)

Read the full file on GitHub · 1,072 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. today First seen · 1,072 lines · 0 tokens per session scan A 5bcf694e8e4f

Subscribe to this mod's changes

protocol is a command published in the GitHub repository Everyone-Needs-A-Copilot/claude-copilot (13 stars, last pushed today), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 10,628 tokens. 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 2026-09-04.