claude

metacognitive-guard

Cognitive amplification stack: epistemic hooks, competitive review, commit integrity checks, and deep-thinking agents.

6 on GitHubby ANcpLuav0.7.5MITupdated 9 days ago
/

Plugin metacognitive-guard from marketplace ancplua-claude-plugins in ANcpLua/ancplua-claude-plugins. Commands read from the repo's manifest — 8 days ago.

This plugin runs code on your machine — its hooks fire automatically on events like tool use. The exact commands are listed below; read them before installing.

What it installs

Slash commands (5)

  • /metacognitive-guard:competitive-review

    Dispatch two competing reviewers (arch-reviewer and impl-reviewer) before deep analysis. Competition produces more thorough results. Use before creating code, modifying architecture, or making technical decisions.

  • /metacognitive-guard:deep-analysis

    Structured 4-phase analysis with transparent reasoning and adversarial self-review. Use for complex decisions, architecture choices, debugging dead-ends, or any problem where jumping straight to implementation would be premature.

  • /metacognitive-guard:epistemic-checkpoint

    Force verification before answering questions involving versions, dates, status, or "current" state. Prevents hallucinations at the REASONING level by checking assertions.yaml and WebSearch before forming beliefs.

  • /metacognitive-guard:metacognitive-guard

    Monitors Claude's responses for struggle signals and suggests escalation to deep-thinking agents when complexity exceeds comfortable reasoning capacity.

  • /metacognitive-guard:verification-before-completion

    Force verification before claiming success or completion. Prevents false "it works" claims. Triggers when about to say "done", "complete", "works", "fixed", or "the implementation is ready".

Subagents (3)

  • arch-reviewer

    Architecture-focused competitive reviewer. Finds structural problems like dependency violations, SSOT violations, layer boundary issues, coupling problems, and SOLID principle violations. Competes with impl-reviewer - whoever finds more valid issues gets promoted. - Read - Grep - Glob - WebSearch

  • deep-think-partner

    Asynchronous reasoning amplifier for complex problems requiring deep analysis. Use when facing multi-step logical challenges, architectural trade-offs, strategic decisions, or when you need a second brain to validate reasoning chains. Runs in background to multiply thinking capacity. Examples: <exam

  • impl-reviewer

    Implementation-focused competitive reviewer. Finds code-level issues like banned API usage, version mismatches, wrong assumptions, and fact-checks claims using WebSearch. Competes with arch-reviewer - whoever finds more valid issues gets promoted. - Read - Grep - Glob - WebSearch

Hooks (5)

  • PreToolUse

    ${CLAUDE_PLUGIN_ROOT}/bin/epistemic-guard

  • PreToolUse

    ${CLAUDE_PLUGIN_ROOT}/bin/commit-integrity-hook

  • PostToolUse

    ${CLAUDE_PLUGIN_ROOT}/bin/objective-watch

  • PostToolUse

    ${CLAUDE_PLUGIN_ROOT}/bin/ralph-loop

  • UserPromptSubmit

    ${CLAUDE_PLUGIN_ROOT}/bin/objective-watch

View source on GitHub

More from ANcpLua/ancplua-claude-plugins

All 23 plugins →

dotnet-dnceng

claude

Vendored (MIT) from dotnet/arcade-skills: .NET engineering-infrastructure CI/CD investigation. A ci-investigator orchestrator agent routes across 10 skills (Helix log analysis, Azure DevOps pipeline triage, binlog/crash-dump inspection, codeflow + dependency tracing, Maestro, known-issue history) and 4 MCP servers. Forked only to fix the manifest agents path for Claude Code's ./-prefixed component-path schema; upstream is unchanged otherwise.

10 skills · 1 agent · 4 MCP servers

6

nihil

claude

Evidence-gated maintainability discipline in two layers. (1) A native plugin: four modes — /nihil:raze (root-authority, write-capable transformation of a repo you own; only secret-leak and catastrophic, unrecoverable commands are blocked) plus /nihil:review, /nihil:implement, /nihil:release with confidence scoring, scope control, and release gating — backed by five read-only review agents and PreToolUse/Stop hooks (a discipline aid, not a security boundary: heuristic command matching, fail-open; a secret / API-key brake is active in every mode). (2) A summonable pantheon of five first-principles dynamic workflows (/nihil orchestrator + /nihil-maat review, /nihil-odin research, /nihil-shiva deletion, /nihil-athena restructure), installed into .claude/workflows/ via /nihil:summon.

6 skills · 1 command · 5 agents · hooks

6

elegance-pipeline

claude

Code-elegance pipeline: 4 scouts, 2 judges, planner, verifier, and a gated implementer, plus a standalone code-simplifier for single-pass diff cleanups. Persistent state with stage gates.

1 skill · 3 commands · 6 agents

6

exodia

claude

Multi-agent workflow orchestration (7 commands + 2 skills: eight-gates, hades): fix, tournament, mega-swarm, deep-think, batch-implement, red-blue-review, baryon-mode. Hades, eight-gates, and red-blue-review use Teams API for reactive collaboration.

2 skills · 7 commands · hooks

6

mutation-minded-testing

claude

Mutation-minded, behavior-first test quality. 4 agents (architecture reviewer, senior tester judge, expressive verifier improver, branch coverage implementer) + 4 skills. Coverage is a floor; kill power is the signal.

4 skills · 1 command · 4 agents

6

derot

claude

Dependency lifecycle: /derot audits comment/doc/CI/version/dependency rot and proposes fixes; /depmigrate migrates packages to their new APIs from upstream releases/tags — refutation-gated.

1 skill · 2 commands · 3 agents

6

Similar plugins

collaboration-modes

claude

Define collaboration style between Claude Code and user: step-by-step, deep-think, or pair programming

1 command

NTCoding/claude-skillz 364

Atelier

claudecodex

Spec-driven development, deep thinking, and code quality workflows

16 skills · 4 agents

martinffx/atelier 51

anamnesis

claude

Log predictions before acting; get scored when reality answers; see your standing over/under-confidence injected into every project at session start.

1 skill · 5 commands · 1 MCP server · hooks

Anbu-00001/Anamnesis 36

self-message

claude

Give Claude Code agents the ability to send themselves continuation messages mid-session — metacognition, not repetition

1 skill · hooks

alberduris/skills 25

meta-cc

claudecodex

Meta-Cognition tool for Claude Code with 16 MCP tools for session history analysis, error tracking, quality scanning, work patterns, timelines, and bug detection. Focused, fast, and data-driven.

3 skills · 3 commands · 1 MCP server

yaleh/meta-cc 22

roast

claude

Thought Roasting Engine — turns AI into a relentless Socratic questioner. Progressive 5-level interrogation (D1 Surface → D5 Core) with 7 questioning flavors (Socratic, First Principles, Devil's Advocate, VC Mode, CBT, Mirror, Feynman). Includes anti-deflection system, cognitive bias detection, and structured depth reports.

3 skills · 1 command

sumleo/roast 10

Maintain metacognitive-guard?

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 plugins23 plugins