decision-log

Lets Claude drive the Preflight CLI: audit your AI setup (doctor, context cost), install resources and loadouts with a dry run first, and share or import a setup.

3 skills · 3 commands

One line: what this plugin adds.

1 skill · 1 command · 1 agent

Live plan progress bars above the Claude Code prompt: stages, steps, foldable agent strips and soft sounds

1 skill

Lists the small guesses Claude made without asking; mark each right or wrong, and a wrong one gets fixed on its own

Holds destructive commands (rm -r, force pushes, git resets and cleans, branch deletes, migrations, SQL drops) and shows what they would destroy

Le Bureau des agents in a side pane: its pixel-art office and engine, playing your session

Interactive learning mode that requests meaningful code contributions at decision points (mimics the unshipped Learning output style)

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

Skill: add headroom-ai compress() to a Python or TypeScript app to cut LLM input tokens (tool outputs, logs, JSON, chat history). No API key.

1 skill

DuckDB-powered skills for Claude Code: read any data file, attach and query DuckDB databases, search DuckDB/DuckLake docs, search past session logs, and install/update DuckDB extensions.

9 skills

Metrics collection, logging infrastructure, distributed tracing, SLO implementation, and monitoring dashboards

4 skills · 2 commands · 4 agents

Streamline engineering workflows — standups, code review, architecture decisions, incident response, and technical documentation. Works with your existing tools or standalone.

10 skills · 10 MCP servers