Borrowing it
Nothing to install: this file belongs to Everyone-Needs-A-Copilot/claude-copilot. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/Everyone-Needs-A-Copilot/claude-copilot/main/.claude/commands/protocol.mdgit clone --depth 1 https://github.com/Everyone-Needs-A-Copilot/claude-copilotWrote 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.
[](https://agentmods.dev/commands/everyone-needs-a-copilot/claude-copilot/protocol)<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/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.
<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="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00000 | $0.11810 |
| Opus 5.5 | $0.00000 | $0.04724 |
| Sonnet 5.5 | $0.00000 | $0.02362 |
| Haiku 4.5 | $0.00000 | $0.01181 |
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 6d 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 — 1,145 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.
Work lifecycle
Read .claude/agents/_shared/work-lifecycle.md once per task and apply its proportional start/resume, during-work, handoff, finish and later-use checkpoints, including direct invocation. Use the existing task and maintained narrative; selective memory pointers must not duplicate them. Preserve exact destructive approval and recovery, original authority and required assets. Substantial QA-required work needs an observable WORK-LIFECYCLE criterion before acceptance freezes; cleanup status and product acceptance remain separate.
At start/resume (including a new PRD or initiative) and finish/merge/pause/handoff, proactively inspect relevant worktrees and surface eligible cleanup with exact paths, recovery and dependency checks, then visibly request deletion approval; do not wait for a cleanup command. Merge alone is insufficient. Record owned holds and pending approval in the existing task, continue unrelated work, and reuse unchanged prior approval after drift checks.
Project Protocol Precedence
First check the current project's .claude/commands/protocol.md. Claude Code's filename precedence favors this machine copy at ~/.claude/commands/protocol.md; explicitly check for a project override before routing.
- Read
.claude/commands/protocol.mdrelative to the current project's root, if the project has one. - If its content differs: follow the PROJECT instructions in full instead of everything below for the rest of this conversation. Declare
[Protocol: project]. Non-software projects may legitimately use different flows. - If it is absent, or identical to this file: this file governs, unchanged. Declare it:
[Protocol: machine].
Check once before flow detection/routing, never mid-flow or skipped because intent seems obvious.
Command Argument Handling
This command supports an optional task description argument for quick task initiation:
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.
- 6d ago Changed · -1 lines 2b4f7599f41c
- 7d ago Changed · +1 lines daf334fae4c8
- 1mo ago Changed · -13 lines d90043209c2c
- 1mo ago Changed · +86 lines 03028920f89a
- 1mo ago First seen · 1,072 lines · 0 tokens per session scan A 5bcf694e8e4f
protocol is a command published in the GitHub repository Everyone-Needs-A-Copilot/claude-copilot (14 stars, last pushed yesterday), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 11,810 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.
Other commands, from other repositories
rename
Generate a concise, sentence-case title (3-7 words) that captures the main topic or goal of this coding session. The title should be clear enough that the user recognizes the session in a list. Use sentence case: capitalize only the first word and proper nouns.
follow-up
Review and act on pending reminders. Bare invocation shows all reminders as an indexed list; cron-fired invocation (/follow-up due ) surfaces the specific reminder and waits for a response; /follow-up review lists stale project follow-up entries for per-item disposition (extend/close/promote/skip). Transport-aware…
help
Explain Ralph Wiggum technique and available commands.
orchestrate
Do this task as an orchestrator. The aim is the same result at a fraction of the cost: in a long session, every token in this conversation is re-read on each later request, while a subagent's reading is discarded when it returns. The plugin's subagents run on Haiku 5.5, about 40× cheaper per token than Opus 5.5.
scout-meta-review
Run an interactive Scout meta-review — a system-level audit that sits above the individual session types. Checks whether sessions are running, mistake audit is trending well, proposals are flowing, KB files are healthy, and data-source coverage is consistent across session types. Runs in the current conversation.
graphify
Turn your vault into a clustered knowledge graph with HTML and JSON outputs.