prompt-audit
73Command Claude Code
Audit a prompt file or pasted prompt as a contract.
5,134 tagged ai-agents, measured the same way as everything else here.
Browse within: agentic-ai 281LLM 194agents 184claude-code-plugin 156cli 156ai-coding 138agentic-coding 127agents-md 117devops-tools 117ai-governance 102agent-orchestration 89agent-framework 86obsidian 85second-brain 67
Command Claude Code
Audit a prompt file or pasted prompt as a contract.
Command Claude Code needs its repo
Orchestrate complex software releases using AI swarms that handle everything from changelog generation to multi-platform deployment.
Command Claude Code
Propagate GDD changes to architecture and ADRs.
sysnet4admin/_Book_Claude-Code
Command Claude Code
Perform a comprehensive PR review with code analysis, best practices check, and suggestions.
Command Claude Code
A command for choosing or defining the visual style of a PowerPoint presentation, including its colors, fonts, and page layouts. It offers preset styles, custom brand settings, and recommendations based on the presentation topic.
Command Claude Code
create a release PR (auto-detects previous tag).
Command Claude Code
Run an ATT&CK-based threat hunt with a specific hypothesis.
Command Claude Code
Route explicit Pensyve memory requests through the bundled MCP server; supports recall, remember, observe, inspect, status, review, forget, and mention-style guidance.
Command Claude Code
Audit merged pull requests over a user-specified number of days.
Command Claude Code
Create a Callee agent or deterministic workflow.
Command Claude Code
Read .claude/skills/handoff/SKILL.md completely and dispatch its export workflow. Use any supplied command arguments only as the requested bundle path; preserve the skill's sourceagent, direct checks, optional verification, and safety boundaries.
Command Claude Code
Generate a new Drupal module with best-practice structure.
Heuresis/Growth-Operator-Agency
Command Claude Code
Refresh PROJECT-STATE.md + memory index from current workspace state + tasks. Run at end of each working session OR whenever significant progress has been made so the next session boots without cold-read overhead.
Command Claude Code needs its repo
Complete checklist for generating a full CRUD command package.
nota-america/forgecat-agent-profiles
Command Claude Code
You need to execute the following bash commands to clean up stale local branches that have been deleted from the remote repository.
Command Claude Code
TDD workflow for MCP Hub implementation. Types → Tests (red) → Implementation (green) with git gates.
Command Claude Code
Scaffold and start the combined topic-swarm plus deep-research workflow with a clean parameter template.
intellegix/intellegix-code-agent-toolkit
Command Claude Code
Perform a thorough live E2E test of a frontend web application using browser-bridge MCP tools. Tests every page, interactive element, form, navigation flow, responsive breakpoint, and accessibility rule through real browser interaction.
Command Claude Code
Generate comprehensive tests for a KMP feature.
SteadfastAsArt/geoscience-skills
Command Claude Code
Guide geophysical inversion from data loading through mesh building and inversion to visualization.
Command Claude Code
A structured way to plan complex features before implementing. Works through: Problem → Options → Solution → Stories → Finalize.
Command Claude Code
Command "final-review" from adriannoes/awesome-agentic-ai, covering final review - comprehensive pr review & testing, step 0: determine review pass, step 1: create or update the pr, step 2: launch three review agents in parallel and agent 1: codebase consistency reviewer.
Command Claude Code
Evaluate and improve one healthcare agent's system prompt. Run up to 5 iterations of: prepare fixed questions -> answer -> judge -> improve -> re-score -> commit if better.
Command Claude Code
Scan a package, repo, MCP server, domain, web page, or skill for security threats using the brin API.
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: