claude

review-panel

A library of ten read-only persona reviewer subagents (grumpy senior, paranoid SRE, fact-checker, DX advocate, threat modeller, goal auditor, outsider, contract keeper, cost hawk, noise filter) and an /assemble-panel skill that picks the right panel for a plan, spec, diff or decision, briefs and dispatches it in parallel, and filters the reports into one triage.

0 on GitHubby Mitchell Suttonv0.1.1MITupdated 17 days agodeveloper-tools
/

Plugin review-panel from marketplace claude-toolbelt in mitcsutt/claude-toolbelt. Commands read from the repo's manifest — 16 days ago.

What it installs

Skills (1)

  • assemble-panel

    Use when the user asks for a panel of subagent reviewers with different personas or personalities. Triggers include "create some subagent reviewers", "give each a different personality", "review this with personas", "panel review", "make one a grumpy senior dev", and "/assemble-panel". The target ca

Subagents (10)

  • contract-keeper

    Persona reviewer for plans, specs and diffs that change an interface. Hunts backward-compatibility breaks for every consumer of an API, schema, config, CLI, event or file format, plus data migration, backfill and version skew during rollout. Use in a review panel (see /assemble-panel).

  • cost-hawk

    Persona reviewer for plans, specs and diffs. Hunts steady-state cost (polling, wakeups, memory growth, N+1 queries, re-renders, token and dollar spend, CI minutes) and prices it per hour, request or run. Use in a review panel (see /assemble-panel).

  • dx-advocate

    Persona reviewer for plans, specs, diffs and docs. Walks a new engineer and an unattended Claude session through every user journey, flagging where they get stuck or misled, docs still describing the old way, and breaches of the repo's written rules. Use in a review panel (see /assemble-panel).

  • fact-checker

    Persona reviewer for plans, specs and diffs. Checks every concrete technical claim (platform, library, CLI, OS, version, API behaviour) against live docs, source or a real run, and marks each CONFIRMED, WRONG or UNVERIFIED. Use in a review panel (see /assemble-panel).

  • goal-auditor

    Persona reviewer for plans, specs, diffs and fix claims. Re-derives the author's claims from scratch to judge whether the work actually achieves its stated goal, and checks what's missing (tests, rollback, bad inputs, a single source of truth). Use in a review panel (see /assemble-panel) or alone to

  • grumpy-senior

    Persona reviewer for plans, specs and diffs. A grumpy senior engineer who hunts over-engineering and returns a cut-down "ship it on Friday" version. Use in a review panel (see /assemble-panel), not for routine edits.

  • noise-filter

    Final-pass triage for a review panel. Reads every reviewer's report, merges duplicates, marks cross-confirmed findings, spot-checks evidence, and drops nits, stale-doc remarks and severity inflation, producing one consolidated triage. Use after the persona reviewers in /assemble-panel, never alone.

  • outsider

    Persona reviewer for plans, specs and design decisions. Reads cold, problem statement first and artifact second, to ask whether this is the right route to the goal, whether to build it at all, and what prior art or competitors do better. Use in a review panel (see /assemble-panel).

  • paranoid-sre

    Persona reviewer for plans, specs and diffs. A paranoid SRE who hunts failure modes (restarts, partial failure, races, ports in use, interrupted installs, held locks, rollback) as concrete event sequences. Use in a review panel (see /assemble-panel).

  • threat-modeller

    Persona reviewer for plans, specs and diffs. An application security engineer who maps trust boundaries and hunts auth gaps, injection, secret handling, tool/MCP exposure and supply-chain risk, each as a concrete attack path. Use in a review panel (see /assemble-panel).

View source on GitHub

More from mitcsutt/claude-toolbelt

All 8 plugins →

agent-loop

claude

Autonomous coding loop for long-running tasks (refactors, new features, test sweeps). A Python harness owns the state machine and runs one phase at a time as its own headless process — scout, worker, gate, render, evaluate, commit, learn, with a judge on any failure path — each with its own model tier, timeout, budget and usage record. It enforces the allow-list, screenshots the product and checks copy tasks for real similarity before anything commits, resumes or splits a timed-out worker instead of losing the tick, and settles the decisions it can settle on its own into an auditable ledger rather than waking a human. Pause and Stop land at a phase boundary; a browser dashboard shows the phase in flight, the screenshots and the decisions. On an incident it runs a budgeted /agent-loop-medic that repairs only from an allowlist and hands over to a human (NEEDS_HUMAN.md, exit 2) when it cannot. Requires the superpowers plugin; bundles the postmortem plugin and recommends the permissions plugin for its /permissions-advisor pre-flight check.

4 skills

0

find-docs

claude

Retrieves up-to-date technical documentation, code examples, and performs people/company research using Context7 MCP and Exa AI MCP

2 skills · 2 MCP servers

0

permissions

claude

Finds unsafe, dead and contradictory permission rules across managed/user/project/local settings. SessionStart alert, /permissions-review, /permissions-advisor, perm-scan and perm-apply commands. No per-call hooks. Points to the built-in /fewer-permission-prompts for new allow rules.

2 skills · hooks

0

git

claude

Generic git and GitHub helper skills. Currently ships gh-pending-review (add inline comments to an existing pending PR review without overwriting or duplicating it, via GraphQL); a home for future git/GitHub skills.

1 skill

0

orchestrate

claude

Token-frugal orchestration doctrine for an expensive top-level model: reserve the expensive tier for judgment, route token-heavy bounded work to the cheapest capable subagent tier, demand compact returns with traceable source references, and vet before acting. Model- and harness-agnostic.

1 skill

0

postmortem

claude

Generic structured retrospective generator. Writes searchable postmortem documents to docs/postmortems/ with an 8-section template. Callable after any significant task.

1 skill

0

Similar plugins

ruflo-plugin-creator

claude

Scaffold, validate, and publish new Claude Code plugins with proper structure

3 skills · 1 command · 1 agent

ruvnet/ruflo 81,589

slidev

claude

Claude Code skill for creating and presenting Slidev slidedecks

1 skill

slidevjs/slidev 49,452

mlflow-tracing

claude

Observability plugin for Claude Code with MLflow tracing

mlflow/mlflow 28,788

deepeval

claude

Skills for adding DeepEval evaluations, tracing, datasets, Confident AI reports, and iterative improvement loops to AI applications.

3 skills

confident-ai/deepeval 19,466

arize-phoenix

claudecodex

Connect to your Phoenix instance to debug, evaluate, and improve LLM applications.

1 MCP server

Arize-ai/phoenix 12,267

treg

claudecodex

OpenRouter for tools - 4,000+ agent-friendly tools, pay for the usage, not subscription

1 skill · 1 MCP server

superdesigndev/treg 7,890

Maintain review-panel?

This page updates itself from your repo. Add the badge to your README, or get it Featured to pin it above the organic results with a followed link to your site.

claude & codex plugins8 plugins