Guards

Denies a Bash command that stops processes by name or by port, because it can also stop another checkout's dev server; a kill of a named PID passes

A pane, opened with /catalog, that lists every skill, command, agent, mod, plugin, settings hook, MCP server and tool by category: descriptions, usage over 7 and 30 days, token cost, what each mod hooks, updates, GitHub stars, a model-written note on what each is for, and buttons to insert, run, update, disable or uninstall.

Pane drawing the session's running subagents: a left-to-right card graph in the desktop app, an indented tree in the terminal

Deckhand — the multi-AI toolbar for Claude Code. A band above the prompt with usage gauges, one-click model buttons, Sub5 parallel sub agents in git worktrees, read-only delegation to Codex, Cursor agent and agy, a plain-words recap, and a tabbed ⚙ settings pane; plus opt-in translation and web search by a delegate, background deploy/PR/CI watch, Claude↔Codex handoff, and attribution and...

Shows what the conversation's context holds in a side pane: files, skills, MCP servers and memory files

Every subagent Claude starts waits for your approval: approve, refuse, approve all for the turn, change its model (suggested by the task's complexity) or add a note to its task. A pane lists the agents waiting, the full task and recent decisions, the same in the terminal and the desktop app.

Pattern-based checks that deny .env reads, git force pushes and rm -rf on / or your home folder before Claude Code runs them.

Hands a long session over, to a fresh one or by compacting, before the context gets too big

Development standards: look before building, test what changed, pass the repo's checks, keep the rules in view.

Keeps AI coding agents inside your project's rules, from idea to merged code: spec design, lanes, layer rules, protected paths with an approval log, spec-check and design gates, proof-before-finish checks, dispatch, review, build status and CI verification, configured per project from its docs

Harness opinionado de Claude Code para construir aplicaciones serverless en Azure con Event Driven Architecture, Event Sourcing (Marten + Wolverine), Postgres y .NET 10. Incluye pipelines TDD, IaC, tooling, scaffolding y agentes/skills especializados.

Session dashboard: a /tether pane for a working-on note, context, the assumptions Claude is making, the work it puts off, decisions, needs-you tasks, subagents and cost. Every section folds.

Live GitHub PR pane: checks, reviews, threads, comments; polls gh and redraws on change

A brief view of the repo's BACKLOG.md: what's next, and how many items are to-do, new, parked or blocked

dima's command center above the prompt, one row: orbit 🪐 (the session's asks, ticked in the board instead of pasted, and its 🌔 phases), the 5h and ctx meters, afk (one switch every session obeys), keep-hot 🔥, the ⏰ waker, and the /board fleet board

A pane on the right listing the decisions Claude needs from you, each with its recommendation and Approve / Chat buttons

Claude says the tests pass. Receipts checks. Flags success claims that no check backs up.

After each response, a panel above the prompt with what needs you, errors, the next action (with its task id), open to-dos and heads-ups.

Stops Claude from re-reading the same large, unchanged file in full again and again in one session: past a limit it is pointed to Grep or a ranged Read instead.

A live pane for a workstreams round: each stack layer's place in the review loop, its CI, threads, agents and collisions

Ather Automata: what needs you and what is next in every S2 session and web app repository (Plan, Build, Prove, Ship), a newcomer tour, autonomy windows, and guards that catch false build passes and lost merge edits.

Git only when you asked: commits, pushes, pull requests, merges and destructive git commands run only when your latest message (or /ship, /kickoff (also as /progress-pane:kickoff), or your answer to Claude's question) allowed them; everything else is refused with a note telling Claude to ask. No UI.

Mission control for Claude sessions, in a Notebook look: a band and /progress pane in every session (model, effort, tokens, context, agents, gate, git), and with a worklog a validated worklog tool Claude updates at every step (done only after a green gate), facts the mod sees for itself (gate runs, commits, branch, agents, context and cost), drift hints where the two disagree, a band above the...

A live HUD for Claude Code: context, spend, usage limits and repo status in RPG gauges, and your subagents as a fantasy party around a campfire.