By mightycogs
Workflow skills and agents: code-walk-thru, log-work, make-issue-spec skills; ui-tester agent for browser-based UI validation
Use this when user wants you to walk through (code or text) files in a EDITOR to either explain how some code works, or to show the user what changes you made, etc. You would typically use this repeatedly to show the user your changes or code files one by one, sometimes with specific line-numbers. This way the user is easily able to follow along in their favorite EDITOR as you point at various files possibly at specific line numbers within those files.
1. create the file WORKLOG/YYYYMMDD.md if it doesn't already exist.
There isn't a lot more to this than what the top level description says. The idea is
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
Productivity tools for Claude Code, Codex-CLI, and similar CLI coding agents: CLI commands, skills, agents, hooks, plugins. Click on a card below to navigate.
Prerequisites: Node.js 16+ (required for action menus)
Step 1: Install the Python package (includes Node.js UI components):
uv tool install claude-code-tools
Step 2: Install the Rust-based search engine (powers both human TUI and agent search). Choose one of these methods:
brew install pchalasani/tap/aichat-searchcargo install aichat-search (compiles from source, ~5 min)rust-v* releases)That's it! No npm install needed — the Python package includes pre-installed Node.js dependencies.
Without aichat-search, search won't work, but other aichat commands (resume, trim, rollover, etc.) still function.
Four commands are installed:
| Command | Description |
|---|---|
aichat | Continue work with session lineage and truncation, avoiding compaction; fast (Rust/Tantivy) full-text session search TUI for humans, CLI for agents |
tmux-cli | Terminal automation for AI agents ("Playwright for terminals") |
vault | Encrypted .env backup and sync |
env-safe | Safe .env inspection without exposing values |
This repo also provides plugins for the Claude Code marketplace:
| Plugin | Description |
|---|---|
aichat | hooks (>resume), commands, skills, agents for continuing session work and fast full-text search of sessions |
tmux-cli | Terminal automation skill for interacting with other tmux panes |
workflow | Work logging, code walk-through, issue specs, UI testing |
safety-hooks | Prevent destructive git/docker/rm commands |
langroid | Design patterns for the Langroid multi-agent LLM framework |
voice | Spoken audio summaries when agent stops; uses pocket-tts |
Install the plugins:
First, add the marketplace (from terminal or within a Claude Code session):
npx claudepluginhub mightycogs/claude-code-tools --plugin workflowProvides an agent, skill, hook, and slash command related to the `aichat` tool-set for searching and resuming CLI-agent sessions
Safety hooks to block or require user approval for dangerous commands (rm, git operations, .env access, file size limits)
Provides tmux-cli skill, to allow Claude-Code to interact with CLI scripts or other code-agents in tmux panes, using the `tmux-cli` command
Design patterns for the Langroid multi-agent LLM framework
Audio feedback when Claude Code agent completes tasks using pocket-tts
Evidence-gated AI coding workflow: scan → analyze → plan → TDD → execute → fix → verify → review, powered by Codebase Memory MCP >= 0.9.0 with optional Serena LSP intelligence. Includes blast-radius planning, test/cycle gates, independent review, and Windows Git Bash hook auto-resolution.
Tools to maintain and improve CLAUDE.md files - audit quality, capture session learnings, and keep project memory current.
A growing collection of Claude-compatible academic workflow bundles. Covers scientific figures, manuscript writing and polishing, reviewer assessment, citation retrieval, data availability, paper reading, literature search, response letters, paper-to-PPTX conversion, and evidence-grounded Chinese invention patent drafting. Rules are organized as reusable skill folders with explicit workflows and quality checks.
Comprehensive feature development workflow with specialized agents for codebase exploration, architecture design, and quality review
Harness-native ECC operator layer - 67 agents, 278 skills, 94 legacy command shims, reusable hooks, rules, selective install profiles, and production-ready workflows for Claude Code, Codex, OpenCode, Cursor, and related agent harnesses
v9.54.0 — Reliability wave: tangle contextual review correction loop with hard round ceiling, progress-supervised review rounds (per-agent stall watch, descendant-tree kills), council diversity and agy pin fixes, marketplace generator source-of-truth fix, provider troubleshooting runbook and cost-expectations docs. Run /octo:setup.