Listen — Development skill for Claude Code
Show what a given agent should read before coding, plus briefs/approvals mentioning it.
How to install Listen
Installs to ~/.claude/skills/anshulixyz-multi-agent-loop-kit-listen/SKILL.md
mkdir -p ~/.claude/skills/anshulixyz-multi-agent-loop-kit-listen && curl -fsSL https://raw.githubusercontent.com/anshulixyz/multi-agent-loop-kit/HEAD/commands/listen.md -o ~/.claude/skills/anshulixyz-multi-agent-loop-kit-listen/SKILL.md Restart Claude Code, or start a new session, for it to be picked up.
What Listen does
description: Show what a given agent should read before coding, plus briefs/approvals mentioning it. argument-hint: ""
Show the pre-coding listening checklist for an agent.
Run, passing the codename in `$ARGUMENTS`:
bash "${CLAUDE_PLUGIN_ROOT}/bin/loop-listen" $ARGUMENTS
If `$ARGUMENTS` is empty, ask the user which agent codename. This lists the files the agent should read before coding and any task briefs / pending approvals that mention it. Relay it, and reinforce
Alternatives in Development
- Benjamin Plus Skill — Benjamin-Plus: a measured token-efficiency skill for coding agents (−17.9% cost median, quality unchanged) 272 ★
- Q Begin — Start a new investigation session 50 ★
- Builder Self Review — Builder step 5 — re-read your own diff before publishing 27 ★
Full documentation available on GitHub
View Source RepositoryRelated Skills
Ste Rewrite
Rewrite the given text or file into Simplified Technical English, then show a before/after comparison.
English Retell Coach
A Codex skill for English listen-read-retell coaching with expression-gap analysis
Everywhy
Content x relation for coding agents: a phrase in, a budgeted read plan out -- pointers, never prose -- so a s
Black Box
A local ledger coding agents write their reasoning into and read back before they act. Codex and Claude Code s
Paperclip Status
Show a Paperclip status report (agents, tasks, spend, approvals)
Instruct
Perform an instruction, given as an instruction file, a file plus its argument, or a description typed in the
Related Agents
Dr Line By Line
Deep-review finder angle. Reads every hunk of a diff line by line plus the enclosing function, hunting for the
Recommend Open Question
Read-only recommendation subagent for a single open question — the non-interactive twin of discuss-open-questi
Profile Differ
Read-only classifier for LinkedIn vs CV vs website differences. Given the mechanical diff output and the accep