shell-guard

Cuts 'You're absolutely right!' and other tics: a tone rule, opener stripping and a tic counter.

Keeps the goal, your prompts, pinned notes and touched files across compaction, and archives the history before it.

Locks existing tests against edits and runs your checks before Claude may say it is done.

Fingerprints what the model is given (version, model, effort, system prompt sections, tools) and tells you what changed.

Keeps a permanent copy of every session as JSONL and markdown, adds timestamps and /history search.

Turns project rules into hard blocks: protected paths, no report .md files, banned commands, pinned reminders.

Harness-native ECC operator layer - 71 agents, 314 skills, 98 legacy command shims, reusable hooks, rules, selective install profiles, and production-ready workflows for Claude Code, Codex, OpenCode, Cursor, and related agent harnesses

200 skills · 98 commands · 71 agents · 1 MCP server · hooks

Security review for Claude-generated code. Pattern-based warnings on edits, LLM-powered diff review on Stop, and an agentic commit reviewer that catches injection, XSS, SSRF, hardcoded secrets, and 25+ other vulnerability classes.

hooks

Agentic QE (external: maintained in proffesor-for-testing/agentic-qe, pinned to v3.15.17): a quality-engineering fleet with 11 QE agents, 9 skills, 9 commands, the agentic-qe MCP server pinned to the plugin version, and the aqe-mod guard that refuses destructive operations on AQE learning data

9 skills · 9 commands · 11 agents · 1 MCP server

Claude Code mod: watch Headroom snip tokens off every request, with an animated band, a /headroom log and a running total.

Install the "AAS Security Engineer" editorial skill bundle for Claude Code.

12 skills

Independent auditing for AI agents, open source. Claude discovers your setup, confirms the cost, and audits your agent against the one question other tools skip: is it doing the job it's supposed to do, given your business rules and org structure? Test any model (Anthropic, OpenAI, Gemini, Azure, Bedrock, …) graded by self, one independent judge, or a cross-vendor panel; each provider is billed to its own account via a key in your settings, never the command line. Results render as an interactive artifact (with a static-report fallback).

1 skill · hooks