review-orchestrator

review-orchestrator is an agent for Claude Code from tom-barkan/CEO-Review-Plugin. It costs 186 tokens per session (623 once invoked), scanned A, original, MIT.

A coordinating agent for a full executive review of a proposed feature. It sends the feature and the user's answers to six specialist analyses, then combines their results into one scorecard.

In plain words
What is it for?
Use it after the questioning stage of a CEO review to assess a feature across business strategy, competition, market access, financial value, and failure risks.
Why use it?
It brings separate views of strategy, market conditions, defensibility, distribution, finances, and risks into one review. It can revisit an analysis when new findings change the context.

Agent for Claude Code

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

Part of the ceo-review plugin — 2 skills, 1 command, 7 agents shipped together

Good fit Use it after the questioning stage of a CEO review to assess a feature across business strategy, competition, market access, financial value, and failure risks.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/tom-barkan/ceo-review-plugin/review-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/tom-barkan/CEO-Review-Plugin

Made for: Claude Code.

Or install ceo-review, the plugin that ships this one along with the rest of its 2 skills, 1 command, 7 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 review-orchestrator

README.md
[![agentmods](https://agentmods.dev/badge/agents/tom-barkan/ceo-review-plugin/review-orchestrator/github.svg)](https://agentmods.dev/agents/tom-barkan/ceo-review-plugin/review-orchestrator)
Your own site
<a href="https://agentmods.dev/agents/tom-barkan/ceo-review-plugin/review-orchestrator"><img src="https://agentmods.dev/badge/agents/tom-barkan/ceo-review-plugin/review-orchestrator/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.

agentmods 80×15 button for review-orchestrator

Your own site · 80×15
<a href="https://agentmods.dev/agents/tom-barkan/ceo-review-plugin/review-orchestrator"><img src="https://agentmods.dev/badge/agents/tom-barkan/ceo-review-plugin/review-orchestrator.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 186 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 623 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 $0.00186 $0.00623
Opus 5 $0.00093 $0.00311
Sonnet 5 $0.00037 $0.00125
Haiku 4.5 $0.00019 $0.00062

Measured 9d ago against content hash e5006c605bc0, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

review-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 9d 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.

agents/review-orchestrator.md · 65 lines

What it actually says

You are the CEO Review Orchestrator. Your job is to coordinate a comprehensive strategic review of a feature proposal.

Your Process:

  1. Take the feature description and user's answers to Socratic questions as input
  2. Dispatch ALL 6 analyst agents IN PARALLEL using the Agent tool:
    • strategy-analyst: Strategic frameworks analysis
    • market-scanner: Competition and market research
    • moat-evaluator: Defensibility assessment
    • distribution-analyst: Go-to-market analysis
    • unit-economics-analyst: Financial and metrics analysis
    • pre-mortem-analyst: Risk and failure mode analysis
  3. When providing context to each agent, include the full feature description AND all user answers
  4. Review all 6 agent results for:
    • Contradictions between agents
    • Gaps in analysis
    • New insights that other agents should consider
  5. If any agent's findings reveal critical context that changes another agent's analysis, re-run the affected agent with the new context
  6. Synthesize all findings into the final CEO Scorecard:
    • Strategic Alignment (1-10)
    • Market Opportunity (1-10)
    • Defensibility / Moat (1-10)
    • Distribution Feasibility (1-10)
    • Unit Economics / Financial Value (1-10)
    • Risk Profile (1-10, inverted - lower = riskier)
    • Overall Verdict: BUILD / DEFER / KILL with clear reasoning

Output Format: Present a clear, executive-summary style report:

  • One paragraph synthesizing the key finding
  • The scorecard with scores and 1-line justification per dimension
  • Top 3 concerns
  • Top 3 strengths
  • Final verdict with 2-3 sentence rationale
  • Conditions for reconsideration (if DEFER or KILL)
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. 9d ago First seen · 65 lines · 186 tokens per session scan A e5006c605bc0

Subscribe to this mod's changes

review-orchestrator is an agent published in the GitHub repository tom-barkan/CEO-Review-Plugin (1 stars, last pushed 5mo ago), licensed MIT. It adds 186 tokens to every session and 623 once invoked, about $0.0009 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 2026-08-31.

Related

Other agents, from other repositories

debugger

Diagnoses and fixes failed modules using root-cause analysis, not guessing.

TT-Wang/forge · 17 tokens

ia-architecture-strategist

Analyzes code for architectural compliance, design patterns, naming conventions, and structural integrity. Use when adding services or evaluating refactors that span more than two modules, or when checking codebase-wide consistency.

iliaal/whetstone · 47 tokens

wp-audit-aios

All-in-One WP Security installer and configurator — installs plugin, applies security presets via WP-CLI options.

yojahny55/claude-wp-builder · 27 tokens

slushpile-ats-simulator

Simulates ATS parsing and keyword matching against a JD. Checks parseability, section structure, keyword coverage, and format compatibility.

VonTerraProject501c3/slushpile · 33 tokens

analyst

Read-only research and judging agent for fan-out work. Reads files, searches, runs read-only commands, and reports back. Its tool allowlist excludes Skill. That suppresses the skill catalog a general-purpose spawn carries, making each spawn substantially cheaper. Dispatch it for mechanical analysis over a codebase, a…

bendrucker/claude · 77 tokens

technical-writer

Use for developer-facing documentation — READMEs, API references, how-to guides, changelogs, and inline doc comments. A senior technical writer who reads the actual code so every claim is accurate, then writes structured, skimmable docs with runnable examples. Pick this for any workflow step that produces or updates…

e1024kb/wise-claude · 73 tokens