claude

rule-audit

On-demand static analysis of AI system prompts for contradictions, coverage gaps, priority ambiguities, and meta-paradoxes.

0 on GitHubby Hermes Labsv0.4.0Apache-2.0updated 1 month agodeveloper-tools
/

Plugin rule-audit from marketplace hermes-labs-copilot in hermes-labs-ai/copilot-plugins. Commands read from the repo's manifest — 1 month ago.

What it installs

Skills (1)

  • rule-audit

    Audit a named AI system-prompt file for contradictions, coverage gaps, priority ambiguities, meta-paradoxes and absoluteness issues, using the local rule-audit static analyzer (offline, deterministic, no model call). Use when the user asks to audit, lint, review or check a system prompt, agent instr

View source on GitHub

More from hermes-labs-ai/copilot-plugins

All 12 plugins →

Guided, project-local first experience that helps beginners start making something real.

2 commands · hooks

0

Maps markdown acceptance items to explicit implementation evidence for advisory spec-drift checks.

1 skill · 2 commands

0

lintlang

claude

Runs the released LintLang CLI on demand as a portable audit skill, with a separate automatic post-edit hook for Claude Code.

1 skill · hooks

0

Runs the released quick-gate JavaScript and TypeScript quality gate and reads its gate-result/v1 verdict.

2 skills

0

Reports actionable git-state facts before file operations when a checkout is behind its upstream.

hooks

0

Blocks permanent-delete shell commands and redirects the agent to a recoverable trash workflow.

hooks

0

Similar plugins

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

gitnexus

claudecodex

Code intelligence powered by a knowledge graph. Provides execution flow tracing, blast radius analysis, and augmented search across your codebase.

12 skills · 1 MCP server · hooks

abhigyanpatwari/GitNexus 48,482

Convert a rambling description of a desired outcome into one polished, autonomous /goal prompt ready to paste into a fresh session. Extracts deliverable/quantity/stakes/tools/destination, asks at most one question batch, verifies every named resource against the live environment, writes a 150-350 word prose prompt with the seven-part anatomy, and self-checks six binary criteria before delivering. The output is a single copy-paste prompt, never the build itself.

1 skill · 1 command

alirezarezvani/claude-skills 29,725

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

Maintain rule-audit?

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 plugins12 plugins