Ext Ops Panel
Open dashboard
Comparison

critique vs scientific-debugging

scientific-debugging is no longer listed on any marketplace we read: these are its last known data, as of 2026‑10‑16.

critique is a plugin bundle for AI coding tools published by Alfafis. Marketplaces we read that list it: 1 (Claude Code: claude-plugins-community). scientific-debugging is a plugin bundle for AI coding tools published by iowarp. No marketplace we read lists it any more. As of our marketplace pass on 2026-10-18. A plugin in this pair is no longer listed on any marketplace we read, so search engines are asked not to index the page.

Where each is published

Where each is published
Marketplacecritiquescientific-debugging
Claude Code: claude-plugins-community Listed
Version: 1.3.1
Forks (GitHub): 0
Stars (GitHub): 0
Not marked · First seen
Not listed
Community marketplace iowarp/clio-kit Not listed Removed on 2026-10-16
Version: 0.3.1
Forks (GitHub): 5
Stars (GitHub): 8
Not marked · First seen

Each figure is the marketplace's own and is never added up across marketplaces. A marketplace that publishes no figure shows none: no number is not zero.

The facts side by side

critique vs scientific-debugging
Factcritiquescientific-debuggingno longer listed ·
Marketplaces that list it (differs)10
Stars (GitHub) (differs)08
Forks (GitHub) (differs)05
Last releaseNot publishedNot published
Where it runsInstalls as a plugin bundleInstalls as a plugin bundle
TransportNot statedNot stated
Tools it declaresNot publishedNot published
Environment variables it asks forNot publishedNot published
Hooks it runs (differs)2Not published
Parts of the bundle (differs)5Not published
Licence (differs)MITApache-2.0
Repository (differs)github.com/alfafis/critiquegithub.com/iowarp/clio-coder
Changes in the last 7 days (differs)04
First seen (differs)2026-10-112026-10-13

Lines where the two differ have a tinted background and bold values. No value is marked better or worse: a plugin no marketplace lists any more is shown with its last known data, which we do not rank against current figures.

What to use instead of scientific-debugging

Plugins still listed whose own names, descriptions, tools and skills are closest in meaning to it. Comparable, not endorsed.

  • agent-trace-triage

    Agent Trace Triage is a Claude Code plugin for developers building agentic AI systems (LangGraph, CrewAI, custom tool loops, MCP agents). When an agent run fails, stuck in a loop…

    by WasayAbid · Plugin bundle

    Listed on: Claude Code: claude-plugins-community · Describes nearly the same job

  • misakanet io.github.Ikalus1988/misakanet

    Failure-memory layer for coding agents: search evidence-rated failure lessons by error text.

    by Ikalus1988 · MCP server

    Listed on: Official MCP Registry, Community GitHub marketplaces · Describes nearly the same job

  • Snapback

    Diagnose why an AI agent failed and get the verified fix instantly. Free, no token.

    by ra1labsworkx-wq · MCP server

    Listed on: Official MCP Registry · Describes nearly the same job

  • Trunk Flaky Tests

    Flaky test detection, root cause analysis, and fix suggestions for development teams.

    by trunk.io · MCP server

    Listed on: Official MCP Registry · Describes nearly the same job

  • Verdict QA

    Read-only MCP server over Verdict QA state: verdicts, findings, flaky quarantine, history.

    by ArtJack · MCP server

    Listed on: Official MCP Registry · Describes nearly the same job

  • BugProof

    Capture, replay, and debug failures with portable, executable bug artifacts

    by sidinsearch · MCP server

    Listed on: Official MCP Registry · Describes nearly the same job

Its card, with similar plugins by marketplace

What each says it does

critique

In its own words, on Claude Code: claude-plugins-community:

Permanent critical mindset mode. Surfaces real bugs, questionable decisions, and unhandled edge cases — ordered by impact, no sugarcoating.

scientific-debugging

In its own words, on Community GitHub marketplaces:

Diagnoses stalled or cross-system failures and wrong, NaN, nondeterministic, or unexpectedly slow scientific results through falsifiable hypotheses across distinct fault classes, with evidence-cited verdicts before any fix. Not for designing benchmarks or pre-registered experiments; use experiment-protocol.

How to run each

critique As a Claude Code plugin

Claude Code
/plugin marketplace add anthropics/claude-plugins-community
/plugin install critique@claude-community

scientific-debugging

No data for an automatic command: what its marketplaces declare does not say unambiguously how to connect it.

Commands built only from what the marketplaces declare; the full set for every client is on each card.

Tools each declares

Neither one's marketplaces publish a list of tools, so there is nothing to compare.

Settings each asks for

Neither one's marketplaces publish the settings it asks for.

What it can do: critique · What it can do: scientific-debugging · Compare two other plugins

Data comes from the public marketplace file https://github.com/anthropics/claude-plugins-community/blob/HEAD/.claude-plugin/marketplace.json. Data comes from public marketplace files in GitHub repositories of their authors. Figures come from our own regular passes over the marketplaces, last read on . We publish no contact details for plugin publishers.

Where the data comes from: how the catalog is built