Human In The Loop — Development skill for Claude Code
A Claude Code mod: Claude assigns you the tasks only you can do.
How to install Human In The Loop
This entry records only its repository, not the path inside it, so there is no
exact command to give. Open tzafrir/human-in-the-loop and copy the folder into
~/.claude/skills/, or the file into ~/.claude/agents/.
What Human In The Loop does
A Claude Code mod: Claude assigns you the tasks only you can do. They wait in a pane until you answer, and your answer goes back to Claude.
Alternatives in Development
- Ralph Loop — Autonomous coding loop — works through tasks, commits, repeats 14k ★
- Ralphy — My Ralph Wiggum setup, an autonomous bash script that runs Claude Code, Codex, OpenCode, Cursor agent, Qwen & 2.8k ★
- Herdr Reviewr — Review your coding agent's diff in a terminal pane and send line comments back to Claude Code, Codex, OpenCode 823 ★
README

Human in the loop
**Claude hands you the tasks only you can do. They wait until you act, and your answer goes back to Claude.**
Why
Claude often needs something only you can do: a key in `.env`, an approval on staging, a command on your own machine, a decision. Today it says so in the middle of a reply. You're busy steering the next fix, and the ask scrolls away. At best Claude keeps repeating "I still need you to…"; at worst the ask is lost.
With this mod, Claude assigns the ask as a task instead. It waits in the **My tasks** pane, counted under the prompt, until you do it, answer it or reject it.
An example
Get our Stripe webhooks library ready to open-source.
Claude works through it, and three times hits something only you can do: the integration tests need your Stripe key, making the repo public is your call, and the package needs a name. Each becomes a task, and Claude keeps working:
╭─ My tasks ──────────────────────────────────────────────────────────╮
│ ☐ 3 tasks for you │
│ │
│ ☐ #1 Add STRIPE_SECRET_KEY to .env 2m │
│ The integration tests run against Stripe's test mode and need it. │
│ Done when: It's in .env. Don't paste it here. │
│ d: Done r: Answer… x: Reject… │
│ ☐ #2 Decide whether to make the repo public 1m │
│ ☐ #3 Choose the package's name on npm now │
│ │
│ Esc: back to the prompt Hide │
╰─────────────────────────────────────────────────────────────────────╯
☐ 3 tasks for you · /my-tasks
- #1 y
Related Skills
Clear Rewrite
Rewrite text to pass CLEAR-100. Plain words, human voice, real structure, no filler. Runs the checker in a loo
Spaces
Agent-driven SDLC orchestrator: specify → plan → tasks → implement → verify, backed by AIDLC workflows + the P
Buzz
Profile Lean declarations, find the slow ones, trace-diagnose the root cause, and fix them until each elaborat
Verinoda Symbiosis
Verinoda + Claude Code, together: Verinoda with verinoda-live, a Claude Code mod that keeps the code index fre
Herdr Kibitzr
👀 Asks your coding agent to review the comments it just wrote, so what explains something stays and the noise
Await Mailbox
Wait for incoming messages from other agents.This command blocks until a message is received. - Usage: /await-
Related Agents
Adrian
Blocks until a tmux pane is done (pattern match, shell idle, or output idle). Use for any wait that takes more
Automated Reviewer Loop
Run the automated reviewer loop (and CI loop) for a PR. Use when the user wants to run the reviewer loop on a
Approval Gate
HumanLayer-inspired approval gate. Enforces human-in-the-loop for HIGH-stakes operations. Classifies actions b