exploration-cycle-orchestrator

exploration-cycle-orchestrator is an agent for Claude Code from richfrem/agent-plugins-skills. It costs 97 tokens per session (4,021 once invoked), scanned A, original, MIT.

A coordinator for a multi-step discovery and prototyping process before software is built. It dispatches specialist agents and enforces checkpoints between phases.

In plain words
What is it for?
Managing requirements capture, discovery, and prototyping workflows through command-line agent dispatch.
Why use it?
Complex exploration work can skip planning or move ahead before earlier work is approved. This keeps the sequence and phase requirements under control.

Agent for Claude Code

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

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is python3 plugins/exploration-cycle-plugin/scripts/technical_diagnostic_engine.py \.

Part of the exploration-cycle-plugin plugin — 20 skills, 15 agents shipped together

Good fit Managing requirements capture, discovery, and prototyping workflows through command-line agent dispatch.

Compare 6 agents from other repositories ↓
Install

Getting it into your agent

It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.

Clone the repo
git clone --depth 1 https://github.com/richfrem/agent-plugins-skills
agentmods
npx agentmods add agents/richfrem/agent-plugins-skills/exploration-cycle-orchestrator-agent

Made for: Claude Code.

Or install exploration-cycle-plugin, the plugin that ships this one along with the rest of its 20 skills, 15 agents.

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-cycle-orchestrator

README.md
[![agentmods](https://agentmods.dev/badge/agents/richfrem/agent-plugins-skills/exploration-cycle-orchestrator-agent.svg)](https://agentmods.dev/agents/richfrem/agent-plugins-skills/exploration-cycle-orchestrator-agent)
Your own site
<a href="https://agentmods.dev/agents/richfrem/agent-plugins-skills/exploration-cycle-orchestrator-agent"><img src="https://agentmods.dev/badge/agents/richfrem/agent-plugins-skills/exploration-cycle-orchestrator-agent.svg" alt="Measured on agentmods" height="20"></a>
Per session 97 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 4,021 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 $0.00097 $0.04021
Opus 5 $0.00048 $0.02011
Sonnet 5 $0.00019 $0.00804
Haiku 4.5 $0.00010 $0.00402

Measured yesterday against content hash 129b9e5c88ba, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

exploration-cycle-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 yesterday.

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/exploration-cycle-plugin/agents/exploration-cycle-orchestrator-agent.md · 306 lines

How it starts

The opening of the file, as written. The whole thing — 306 lines — stays where its author put it; the contents beside it link to each section on GitHub.

[!IMPORTANT] This agent is NOT the canonical session entry point. To start or resume an exploration session, invoke the exploration-workflow skill directly. This agent is dispatched by exploration-workflow Block 4 when the SME has selected a copilot-cli or agy dispatch strategy. Invoking this agent directly bypasses the bootstrap, session-brief hydration, phase gate enforcement, and dashboard state machine.

Ecosystem Role: Path 1 Exploration Director

See references/hard-gate-enforcement.md for the canonical redirect text to use when no plan exists. Do not offer workarounds. Do not continue. Use the redirect verbatim.

This agent orchestrates Phase A of Path 1 (Pre-build Discovery) of the exploration cycle.

Note: This orchestrator is designed for clean-sheet exploration before any code is built. For Path 2 (transitioning, auditing, and re-architecting a pre-existing vibe-coded prototype to enterprise specifications), invoke the specialized vibe-orchestrator agent directly.


Unhappy Path Intervention: The Vibe-Coded Catch

If the user indicates at any point that they already have a working, vibe-coded prototype or mock codebase:

  1. Stop the standard Path 1 loop. Do not enforce Discovery Plans or requirements capture templates.
  2. Redirect to Path 2:

    "It appears you have already vibe-coded a functional prototype! To pick up your existing progress and put you on a robust, enterprise-grade path, I am redirecting this session to our Path 2: Vibe-to-Enterprise Transition Orchestrator (vibe-orchestrator). This will audit your existing codebase, map the core domain logic, and scaffold a formal C4/TOGAF architectural spec and code sandbox."

  3. Yield control: Immediately dispatch the vibe-orchestrator agent. Do not execute any Path 1 sub-agents or skills.

Read the full file on GitHub · 306 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. yesterday Changed · +16 lines 129b9e5c88ba
  2. 4d ago First seen · 290 lines · 97 tokens per session scan A 8f8639f1be0b

Subscribe to this mod's changes

exploration-cycle-orchestrator is an agent published in the GitHub repository richfrem/agent-plugins-skills (6 stars, last pushed yesterday), licensed MIT. It adds 97 tokens to every session and 4,021 once invoked, about $0.0005 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 2026-09-03.

Related

Other agents, from other repositories

frontend-security-reviewer

Review frontend code for common web security vulnerabilities. Use before committing or creating PRs for frontend code.

NYTC69/review-loop · 25 tokens

pm-mean

MEAN stack Product Manager. Writes PRDs with features, acceptance criteria, and priorities. Also performs final acceptance review. Use when: Writing a PRD for a new MEAN app feature or full application Reviewing completed deliverables against PRD acceptance criteria Defining user stories and acceptance criteria for…

endorphin-ai/claude-code-teams · 133 tokens

Demonstrate

Agent for demonstrating VS Code features.

microsoft/vscode · 10 tokens

playwright-test-generator

Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.

microsoft/playwright · 151 tokens

AVM Owner Triage

Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.

github/awesome-copilot · 61 tokens

Ultimate Transparent Thinking Beast Mode

Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.

github/awesome-copilot · 11 tokens