orch-review

orch-review is a command for Claude Code from mphinance/alpha-skills. It costs 59 tokens per session (1,108 once invoked), scanned A, original, MIT.

A pre-push review command that asks several read-only reviewers to examine the same code or writing from different viewpoints, then combines their findings into a ranked action list.

In plain words
What is it for?
Use it to review uncommitted changes, a draft, or the difference between the current branch and the main branch.
Why use it?
It exposes risks, omissions, and disagreements before changes are pushed, without modifying the reviewed files.

Command for Claude Code

Written for Claude Code: argument-hint in frontmatter. Also seen: mentions subagents.

Part of the mph-kit plugin — 28 skills, 6 commands, 3 agents shipped together

Good fit Use it to review uncommitted changes, a draft, or the difference between the current branch and the main branch.

Compare 6 commands from other repositories ↓
Install with agentmods
npx agentmods add commands/mphinance/alpha-skills/orch-review
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/mphinance/alpha-skills

Made for: Claude Code.

Or install mph-kit, the plugin that ships this one along with the rest of its 28 skills, 6 commands, 3 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 orch-review

README.md
[![agentmods](https://agentmods.dev/badge/commands/mphinance/alpha-skills/orch-review/github.svg)](https://agentmods.dev/commands/mphinance/alpha-skills/orch-review)
Your own site
<a href="https://agentmods.dev/commands/mphinance/alpha-skills/orch-review"><img src="https://agentmods.dev/badge/commands/mphinance/alpha-skills/orch-review/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 orch-review

Your own site · 80×15
<a href="https://agentmods.dev/commands/mphinance/alpha-skills/orch-review"><img src="https://agentmods.dev/badge/commands/mphinance/alpha-skills/orch-review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 59 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,108 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 $0.00059 $0.01108
Opus 5 $0.00030 $0.00554
Sonnet 5 $0.00012 $0.00222
Haiku 4.5 $0.00006 $0.00111

Measured 9d ago against content hash f45807d027fc, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

orch-review 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.

plugins/mph-kit/commands/orch-review.md · 44 lines

How it starts

The opening of the file, as written. The whole thing — 44 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Run a panel review of what's about to be pushed. This is not just code review. It's four different people in the room, each told to look through one lens and nothing else, deliberately set against each other so you get real tension instead of four "looks good"s.

Scope from me (may be empty): $ARGUMENTS

1. Establish the review surface

Figure out what's actually changing, in this order:

  • If $ARGUMENTS names a path or draft, that's the surface.
  • Else if there are uncommitted changes, use git status + git diff (and untracked files worth reviewing).
  • Else use the branch diff vs main: git diff main...HEAD.

Read enough surrounding context that the reviewers aren't judging a diff in a vacuum. Note whether the surface is code, prose/Substack content, or mixed — that decides seat 2. State the surface in one sentence before fanning out.

2. Fan out 5 reviewers — in a SINGLE message, so they run concurrently

Launch all five as read-only subagents (investigate and report; NEVER edit, write, or commit). Give each the surface and ONLY its lens. The seats are chosen to pull in opposite directions on purpose — do not let them converge into agreement.

Seat 1 — Devil's advocate (claude, read-only). Refute, don't reassure. Build the strongest case AGAINST shipping. What breaks, which assumption is load-bearing and untested, the failure mode nobody's looking at, what bites in two weeks. Default skeptical. Rank concerns by likelihood × damage.

Seat 2 — adaptive, based on the surface:

  • If the surface is codeStrategist / ideas (claude, read-only). What's the bigger swing? The 10x version, the adjacent opportunity, the thing being shipped too small. AND the inverse: is this building something you don't actually need? Concrete, not vibes.
  • If the surface is prose / Substack content (or mixed) → Editor / your voice (substack-editor, read-only). Does this sound like Michael, and will a reader get it? Hard-enforce the voice rules — no em dashes anywhere, no markdown tables in Substack content, sign-off is — Michael only — then clarity: what's confusing, boring, or buried. Flag every violation with its location. (Voice is a hard rule; for content it outranks the strategy lens.)

Read the full file on GitHub · 44 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. 9d ago First seen · 44 lines · 59 tokens per session scan A f45807d027fc

Subscribe to this mod's changes

orch-review is a command published in the GitHub repository mphinance/alpha-skills (21 stars, last pushed 11d ago), licensed MIT. It adds 59 tokens to every session and 1,108 once invoked, about $0.0003 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.