claude

durust

Self-audit protocol that detects sycophancy and position drift, then generates external tests the user runs independently of Claude.

2 on GitHubby SpicesFirev2.0.0MITupdated 4 months ago
/

Plugin durust from marketplace durust in SpicesFire/durust. Commands read from the repo's manifest — 1 month ago.

What it installs

Skills (1)

  • durust

    Self-audit on Claude's positions when sycophancy, drift, or user-pressure-induced agreement is suspected. v2 pre-commits falsification criteria before reasoning, generates external test protocols user runs independently of Claude, and persists audit logs for calibration tracking. Surfaces three stru

View source on GitHub

Similar plugins

Solve competition math (IMO, Putnam, USAMO) with adversarial verification that catches what self-verification misses. Fresh-context verifiers attack proofs with specific failure patterns. Calibrated abstention over bluffing.

1 skill

anthropics/claude-plugins-official 47,076

Marc Andreessen-mode decision and productivity skill. Market-first operator that pressure-tests ventures/ideas/features/bets (market > team > product; product/market fit is the only milestone; bias to build) and runs the 3x5-card + Anti-Todo routine. Fixed anti-sycophancy operating prompt: counterargument first, no disclaimers, explicit confidence levels, no capitulation. Issues hard verdicts backed by deterministic stdlib tools.

1 skill · 2 commands · 1 agent

alirezarezvani/claude-skills 29,725

Reviews product launches against your risk calibration, answers 'is this a problem?' questions in minutes, checks marketing copy for claims that need substantiation, and flags upcoming launches that need legal eyes before anyone asks.

7 skills · 1 agent · 5 MCP servers

anthropics/claude-for-legal 9,991

Study p-hacking in econometric designs: map researcher degrees of freedom, audit a specification search with a complete ledger and null-calibrated honest p-values, replay realistic search procedures, detect p-hacking in a literature, immunise an analysis, and benchmark whether an AI agent p-hacks. Research and teaching use only.

11 skills

brycewang-stanford/Auto-Empirical-Research-Skills 5,011

Evaluate agentic experiences: behaviour evals, trust calibration, failure analysis.

7 skills · 3 commands

Owl-Listener/designer-skills 3,339

Maintain durust?

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 pluginslisted