28 tagged agent-trace, measured the same way as everything else here.
Instructions file CodexOpenCode
Instructions for Siddhant-K-code/agent-trace, covering agents.md — agent-strace development guide, project layout, constraints, development workflow and install in editable mode.
Agent
Investigates agent-strace sessions to explain behavior, failures, cost, and tool usage.
Skill Claude CodeCodex
Trace and investigate GitHub Copilot CLI sessions with agent-strace. Use when the user wants to capture a Copilot session, replay agent activity, explain a decision, diagnose repeated tool calls or failures, inspect cost, or audit a recorded session.
Plugin Claude Code
Decision provenance for AI-coded codebases: the why, and what was already tried and rejected.
MCP server Claude CodeCodexCursor +2
MCP server "selvedge" as configured in masondelan/selvedge. Launched with ${CLAUDE_PLUGIN_ROOT}/bin/selvedge-plugin-server.
Instructions file
Instructions for masondelan/selvedge, covering claude.md — selvedge agent instructions, sources of truth, code conventions, test suite and version bump checklist.
Command
Run selvedge-cli blame "$ARGUMENTS" and report the entity's change history. Read-only.
Command
Recent Selvedge change events, optionally filtered (e.g. --since 7d, --entity users, --changeset add-billing).
Command
Was this change tried and reverted before? Check an entity's prior attempts, and why they were rejected, before editing it.
Hook
Runs before the agent uses a tool for Edit, Write, MultiEdit, NotebookEdit and Bash tool calls, running an inline shell check. From masondelan/selvedge.
Hook
Runs when a session starts, running an inline shell check. From masondelan/selvedge.
Hook
Runs before the context is compacted, running an inline shell check. From masondelan/selvedge.
Skill Claude CodeCodex
Use before editing a tracked entity (a DB column, table, function, API endpoint, dependency, or env var) and after any substantive change. Call priorattempts first to learn whether the change was tried and reverted before, then logchange to record what changed and why. Selvedge is this project's change memory — a…
Plugin Claude Code
Security analysis plugins for AI agents by Cylestio.
Instructions file
Claude Code instructions for cylestio/agent-inspector, covering claude.md, project overview, architecture, core components and cli workflow.
Plugin Claude Code
AI Agent Security Analysis - scan, fix, analyze, and report on AI agent vulnerabilities using OWASP LLM Top 10.
Command
Debug AI agent workflows by exploring agents, sessions, and events. Investigate behavioral issues and unexpected patterns. Use when user asks to debug, explore sessions, investigate issues, or examine agent behavior at runtime.
Command
Apply intelligent, contextual security fixes to AI agent vulnerabilities. Fix prompt injection, output handling, tool security, data leaks, memory issues, supply chain, and behavioral risks. Use when user says fix, asks to remediate a recommendation (REC-XXX), apply security patches, or resolve vulnerabilities.
Command
Install, configure, and ensure Agent Inspector is running for AI agent security analysis. Handles installation, server startup, provider detection, MCP tools, and IDE connection. Use when user asks to install, setup, configure agent-inspector, ensure it's running, or when starting a new security analysis project.
Cursor rule Cursor
Agent Inspector MCP endpoint at http://localhost:7100/mcp provides security analysis tools.
Cursor rule
Agent Inspector - AI Agent Security Analysis (scan, correlate static ↔ dynamic).
At most 3 mods per repository are shown here — the rest are on their repository pages: