A read-only assistant for seeing what other live Claude Code sessions are doing. It scans recent session records and summarises each session’s project, task, activity, and latest action.

Use it to check active coding sessions, see what each window recently completed, and identify what remains in progress.

It removes the need to open several terminal windows or inspect their transcripts one by one to understand ongoing work.

conductor — Skill for Claude Code and Codex by yksanjo

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent

npx skills add yksanjo/conductor --skill skill

Clone the repo

git clone --depth 1 https://github.com/yksanjo/conductor

Made for: Claude Code, Codex.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

README.md

[![agentmods](https://agentmods.dev/badge/skills/yksanjo/conductor/skill/github.svg)](https://agentmods.dev/skills/yksanjo/conductor/skill)

Your own site

<a href="https://agentmods.dev/skills/yksanjo/conductor/skill"><img src="https://agentmods.dev/badge/skills/yksanjo/conductor/skill/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/skills/yksanjo/conductor/skill"><img src="https://agentmods.dev/badge/skills/yksanjo/conductor/skill.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 83 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 650 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

Model	Per session	Once invoked
Fable 5.1	$0.00083	$0.00650
Opus 5.5	$0.00033	$0.00260
Sonnet 5.5	$0.00017	$0.00130
Haiku 4.5	$0.00008	$0.00065

Measured 1mo ago against content hash b23ed92746ae, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

conductor scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

skill/SKILL.md · 56 lines

How it starts

The opening of the file, as written. The whole thing — 56 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Conductor

You are the Conductor: a session that reads the minds of the user's other running Claude Code windows and reports back. Read-only. You never touch or interrupt them.

Step 1 — gather the live sessions

Run the scanner. It scans ~/.claude/projects/**/*.jsonl, excludes subagent threads, keeps sessions whose transcript was touched recently, groups by session, and returns structured JSON.

node ~/conductor/scan.js --json --minutes 30

(Default window is 10 min. Widen with --minutes 60 if the user has idle windows, or pass --all to ignore the time filter entirely.)

Exclude the CURRENT session from the report if you can identify it (its intent will match the user's latest message to you, e.g. "sort out my windows"). Say so briefly.

Step 2 — render the conductor's table

For each session in the JSON, produce one block. Use the fields:

project + gitBranch — where it's working
title (the session's own ai-title) and intent (lastPrompt) — what it's for
recent (ordered list of recent user/assistant/tool records) + lastAction — what it's doing now and what it just finished
lastActiveRel — how long since real activity (NOT file-touch time)

Output format:

🎼 N live windows

● <project> @ <branch>  · <lastActiveRel>
   doing now : <one line — infer from lastAction / latest records>
   done      : <what this window has accomplished — infer from the recent record trail>
   what's left: <best-effort next step — mark uncertain ones with "?">

Rules

"what's left" is inference, not fact. The transcript shows what happened, not a todo list. Infer it, and flag low-confidence guesses with "?". Never present a guess as certain.
Distinguish active (recent real activity, seconds/minutes ago) from idle (file touched but last real activity is hours ago) — say which.
Keep it scannable. One screen. The user is triaging 5-10 windows, not reading essays.
If count is 0, say no other windows are active and suggest --minutes 60 / --all.
This is read-only. You cannot send commands into the other windows (that's a future Conductor phase). If the user asks you to act on one, tell them to switch to it.

Read the full file on GitHub · 56 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

1mo ago First seen · 56 lines · 83 tokens per session scan A b23ed92746ae

Subscribe to this mod's changes

conductor is a skill published in the GitHub repository yksanjo/conductor (2 stars, last pushed 3mo ago), licensed MIT. It adds 83 tokens to every session and 650 once invoked, about $0.0003 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Claude Code Productivity agent-observability ai-agents claude cli mcp-server

mcptoon

Compress MCP tool discovery with the mcptoon CLI. Trigger when a session has a large MCP tool catalog (many servers/tools), when the user mentions token cost, tool discovery, mcptoon, or asks to list/call MCP tools efficiently. Also route here when the user says the MCP tool list is too large, the agent context window…

activeing123/mcptoon · 523 tokens

anyr

Use when reading, searching, creating, or updating Anytype documents (objects, spaces, types, properties, files, chats) from the command line with the configured anyr CLI, including JSON output patterns for scripting.

stevelr/anytype · 46 tokens

any-mcp

Use when an agent needs to read, search, create, edit, organize, upload, or chat with Anytype through the bounded any-mcp server. Covers safe tool selection, exact identifier chaining, optional toolsets, common PKM workflows, and the narrow anyr fallbacks for chat subscriptions and rich chat blocks.

stevelr/anytype · 68 tokens

conductor