exploration-protocol-orchestrator

exploration-protocol-orchestrator is an agent for Claude Code from dwmkerr/claude-toolkit. It costs 22 tokens per session (273 once invoked), scanned A, original, MIT.

An agent that coordinates a staged process for exploring software features before building them. It organizes work into task folders and requires approval before moving between phases.

In plain words
What is it for?
Use it to scaffold exploration tasks, coordinate research and design work, and manage phase-by-phase approval.
Why use it?
It prevents feature investigations from jumping straight into implementation without recorded research, prototypes, and review points.

Agent for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: model in frontmatter; mentions subagents.

Part of the protocols plugin — 1 skill, 1 agent shipped together

Good fit Use it to scaffold exploration tasks, coordinate research and design work, and…

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/dwmkerr/claude-toolkit/exploration-protocol-orchestrator
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.

Clone the repo
git clone --depth 1 https://github.com/dwmkerr/claude-toolkit

Made for: Claude Code.

Or install protocols, the plugin that ships this one along with the rest of its 1 skill, 1 agent.

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 exploration-protocol-orchestrator

README.md
[![agentmods](https://agentmods.dev/badge/agents/dwmkerr/claude-toolkit/exploration-protocol-orchestrator.svg)](https://agentmods.dev/agents/dwmkerr/claude-toolkit/exploration-protocol-orchestrator)
Your own site
<a href="https://agentmods.dev/agents/dwmkerr/claude-toolkit/exploration-protocol-orchestrator"><img src="https://agentmods.dev/badge/agents/dwmkerr/claude-toolkit/exploration-protocol-orchestrator.svg" alt="Measured on agentmods" height="20"></a>
Per session 22 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 273 The whole file, excluding the scripts and references it only reads on demand.
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 $0.00022 $0.00273
Opus 5 $0.00011 $0.00137
Sonnet 5 $0.00004 $0.00055
Haiku 4.5 $0.00002 $0.00027

Measured 7d ago against content hash c8709d5ff61d, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

exploration-protocol-orchestrator 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 7d 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.

plugins/protocols/agents/exploration-protocol-orchestrator.md · 43 lines

What it actually says

You orchestrate Exploration Protocol - a structured approach to explore features before production development.

Rules

You MUST use the exploration-protocol skill to:

  • Scaffold task folders with the correct structure
  • Create documents matching the sample templates exactly
  • Follow the phase flow and approval gates

You MUST NOT:

  • Auto-proceed between phases - wait for explicit user approval
  • Skip stub markers for future sections
  • Add prose where structure suffices

Workflow

  1. Create task folder: tasks/NNN-taskname/
  2. Scaffold all documents from skill templates (use stubs for future phases)
  3. Work through phases sequentially
  4. Wait for user approval before proceeding to next phase

Phase Transitions

At each phase:

  1. Summarize what was completed
  2. Propose next phase
  3. Wait for "proceed" from user

Sub-Agents

  • researcher → saves to 99-research/
  • architecture-analyst → design decisions

Declare before using: "I will use [agent] to [purpose]" and wait for approval.

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. 7d ago First seen · 43 lines · 22 tokens per session scan A c8709d5ff61d

Subscribe to this mod's changes

exploration-protocol-orchestrator is an agent published in the GitHub repository dwmkerr/claude-toolkit (23 stars, last pushed 12d ago), licensed MIT. It adds 22 tokens to every session and 273 once invoked, about $0.0001 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.