Claude Code Plugin

if there's a problem,
say it's serious.

Permanent critical mindset injected into every Claude Code session. Real bugs. Questionable decisions. Ordered by impact.

Same code. Different lens.

Without critique, problems get buried in reassurance.

Four rules, no exceptions

Active on every response. Code, review, plan, architecture, decisions.

01

Real problems

Bugs, security flaws, unexpected behaviors, unhandled edge cases. Only what actually breaks or causes damage.

02

Questionable decisions

Architecture choices that will cause pain later — explained with why and a better alternative.

03

What's good

Mentioned only if non-obvious and worth reinforcing. No praising the obvious.

04

Priority

Findings ordered by real impact, not ease of fix. Highest consequence-if-ignored first.

Two modes

Namespaced under critique:

/critique:critique PERSISTENT

Activates the critical mindset explicitly. A SessionStart hook injects it automatically — this is the manual trigger and confirmation. Once active, applies to all work until explicitly disabled.

critique off disable critique stop critique desativa critica
/critique:rigorous DEEP ANALYSIS

Five-phase protocol before any implementation: pre-flight → security audit → implementation audit → structured output → STOP. Blocks ambiguous scope. Never assumes — always asks.

/rigorous /rigorous plan <task> /rigorous sec /rigorous impl /rigorous code

Get started

Two options. Both take under a minute.

Option 1 — extraKnownMarketplaces

~/.claude/settings.json
{
  "extraKnownMarketplaces": {
    "critique": {
      "source": {
        "source": "github",
        "repo":   "Alfafis/critique"
      }
    }
  }
}
Claude Code
/plugin install critique@critique

Option 2 — community marketplace

Claude Code
/plugin install critique@claude-community

Pending community marketplace review — available soon.