Snapshot every tmux pane with links to its agent and transcript (tmux-archive), and rename and regroup windows from their contents through a reviewed plan (tmux-organize)
Plugin tmux from marketplace dx in coletebou/dx. Commands read from the repo's manifest — 2 days ago.
tmux-archiveSnapshot every pane in every window in every tmux session to disk, organized by session/window with auto-detected filenames and a cross-referenced manifest. Use when the user says "capture all tmux panes", "archive my tmux state", "snapshot sessions", "back up my panes", "dump tmux to disk", "tmux s
tmux-organizeInspect every tmux pane, infer what it's about, then rename + reorder windows/sessions accordingly. Use when the user says "organize my tmux", "rename my windows based on what's in them", "clean up tmux", "auto-name tmux", "tidy tmux sessions", or invokes `/tmux-organize`. Builds on the tmux-archive
Code review by Codex, Claude and other engines with a pre-send secret scan (autoreview), multi-lens review with three refuters per finding (adversarial-review), a canary harness for MCP servers that touch secrets (mcp-agent-safety), and a tmux-side second-opinion advisor (fable-second-opinion)
4 skills
Run N Claude Code or Codex sessions in parallel git worktrees with a merged log (parallel-worktrees), contract-first fan-outs (contract-fanout), and branch stacking (stack-branches, stack-claude)
4 skills
End-of-session retrospectives that capture learnings and open follow-ups (reflect), nightly memory consolidation (dreaming), and transcript analysis (session-analyzer)
3 skills
Fan out Codex CLI subagents through tmux (codex-subagents) and read a Codex agent's real transcript instead of its truncated pane (codex-transcripts)
2 skills
Park idle Claude Code sessions in tmux to free memory and resume them with one keypress (cc-park), and hand a long session off to a fresh one through a written brief (fresh-session-handoff)
2 skills
Free disk space on a Mac or Linux dev host without touching active work, from a bounded read-only survey (disk-reclaim), and find open GitLab issues whose work already merged (shipped-but-open)
2 skills
AGENTS.md as project instructions, by one option. Under claude-md-or-agents-md a project with no instruction files of its own gets its AGENTS.md files instead: a prompt.context hook asks $.fs.ancestors for every AGENTS.md and .claude/AGENTS.md from the filesystem root down to the working directory and hands them to the engine as project instruction files, which it renders, announces and withholds from agents exactly as it does CLAUDE.md, skipping any file the engine already loaded by import or link; a tool.call hook on Read attaches the ones under the project root as the engine attaches a nested CLAUDE.md. Under claude-md-and-agents-md every AGENTS.md is loaded beside CLAUDE.md. Under managed-only the project's and the person's instruction files are dropped and the organization's managed ones kept. Under claude-md the engine's walk stands alone. claude-md-or-agents-md is the default.
Persistent memory for Claude Code: the next session starts where the last one left off.
29 skills · 1 MCP server · hooks
Open-source AI job search that runs locally in your AI coding CLI: scan job portals, evaluate listings into a structured A-H report with a 1-5 score, tailor your CV, track applications
5 skills · 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
Headroom startup hooks for Claude Code and GitHub Copilot CLI.
hooks
Expose the plugin-safe Claude Code subset of Agentic Awesome Skills through a single marketplace entry.
200 skills
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.