conductor
View what all active Claude Code sessions are doing and optionally send instructions to them via inbox
What this skill does
# Conductor: Cross-Session Awareness
Aggregate state from all active Claude Code sessions
and optionally send instructions to any of them.
## Helper script
A pre-built script collects all session data in one pass.
Run it first to avoid spending tokens on individual calls.
```bash
~/code/seabbs/dotfiles/scripts/claude-conductor-gather.sh
```
If the script is missing or not executable, flag this to
the user and stop.
The script outputs a JSON object with:
- `sessions`: array sorted by priority (permission first,
then running, waiting, idle, stale), each entry has:
- `session_id`: UUID
- `state`: running, waiting, idle, permission, stale
- `icon`: state indicator character
- `project`: project basename
- `name`: session display name (may be empty)
- `cwd`: working directory
- `tmux_session`, `tmux_window`, `tmux_window_name`,
`tmux_pane`: tmux location
- `age`: human-readable age string (e.g. "3m", "2h")
- `recent_prompts`: last 3 user prompts (truncated)
- `last_response`: last assistant text response (truncated
to 200 chars, may be empty if session has no history)
## Present dashboard
Start with a compact summary table. One row per session.
Skip stale sessions unless the user asks for them.
```
| # | ◉ | Session | Window | Age | Last prompt | Last response |
|---|---|------------|--------|-----|-------------------|----------------------|
| 1 | ● | dotfiles | main | 2m | /conductor demo | Working on table... |
| 2 | ◐ | epinowcast | main | 1h | fix failing test | Fixed, now running… |
```
Columns:
- `#` — row number, used for drill-down
- `◉` — state icon only (● running, ◐ waiting, ○ idle, ▲ permission)
- `Session` — tmux session name (or project)
- `Window` — tmux window name
- `Age` — compact age string from gather output
- `Last prompt` — most recent user prompt, ~30 chars
- `Last response` — last assistant text, ~40 chars
Keep the table under 10 rows. If more sessions exist,
note the count and offer to show all.
After the table, ask ONE question:
"Pick a row to see details, send a message, or say
'stale' for old sessions — or skip."
## Drill-down
When the user picks a row number, show the full entry:
```
Session: {name or project} [{state}]
Location: {tmux_session}:{tmux_window} ({cwd})
Age: {age}
Recent prompts:
1. {most recent}
2. {second most recent}
3. {third most recent}
Last response:
{last_response}
```
Then ask again what they want to do.
## Send instructions (optional)
After presenting the dashboard, ask:
"Send instructions to a session? (name/project or skip)"
If the user names a session:
1. Ask what message to send.
2. Write the message to the inbox file using the Write
tool: `~/.claude/inbox/{session-id}.md`
### Inbox file format
```markdown
---
from: conductor
timestamp: {ISO 8601}
---
{user's message text}
```
The delivery hook reads and deletes this file after
injecting it via `tmux send-keys` when the target
session next finishes a turn (Stop hook).
3. Confirm delivery is queued.
Multiple messages can be sent in one conductor session.
## Delivery timing
- If target is `waiting` or `idle`, delivery happens on
the next hook fire (nearly instant).
- If target is `running` or `permission`, delivery is
delayed until the session finishes its current turn.
Warn the user about this.
- New writes overwrite pending undelivered messages.
## Prerequisites
If the gather script reports no sessions or errors,
check these are in place:
1. Session tracking hook in `settings.json` on all
lifecycle events calling
`~/code/seabbs/dotfiles/scripts/claude-session-track.sh`
2. Inbox delivery script at
`~/code/seabbs/dotfiles/scripts/claude-inbox-deliver.sh`
(called by the tracking hook on Stop)
3. Inbox directory: `mkdir -p ~/.claude/inbox`
Related in AI Agents
skill-development
IncludedComprehensive meta-skill for creating, managing, validating, auditing, and distributing Claude Code skills and slash commands (unified in v2.1.3+). Provides skill templates, creation workflows, validation patterns, audit checklists, naming conventions, YAML frontmatter guidance, progressive disclosure examples, and best practices lookup. Use when creating new skills, validating existing skills, auditing skill quality, understanding skill architecture, needing skill templates, learning about YAML frontmatter requirements, progressive disclosure patterns, tool restrictions (allowed-tools), skill composition, skill naming conventions, troubleshooting skill activation issues, creating custom slash commands, configuring command frontmatter, using command arguments ($ARGUMENTS, $1, $2), bash execution in commands, file references in commands, command namespacing, plugin commands, MCP slash commands, Skill tool configuration, or deciding between skills vs slash commands. Delegates to docs-management skill for official documentation.
reprompter
IncludedTransform messy prompts into well-structured, effective prompts — single or multi-agent. Use when: "reprompt", "reprompt this", "clean up this prompt", "structure my prompt", rough text needing XML tags and best practices, "reprompter teams", "repromptception", "run with quality", "smart run", "smart agents", multi-agent tasks, audits, parallel work, anything going to agent teams. Don't use when: simple Q&A, pure chat, immediate execution-only tasks. See "Don't Use When" section for details. Outputs: Structured XML/Markdown prompt, quality score (before/after), optional team brief + per-agent sub-prompts, agent team output files. Success criteria: Single mode quality score ≥ 7/10; Repromptception per-agent prompt quality score 8+/10; all required sections present, actionable and specific.
adaptive-compaction
IncludedAdaptive add-on policy and recovery layer that decides WHEN to compact, prune, snapshot, or fork -- replacing fixed-percent auto-compaction across Claude Code, Codex, and MCP-capable hosts. Trigger on auto-compact timing or damage: "when should I compact", "is it safe to compact now or start a fresh session", "auto-compact fires too early/mid-task", "switching to an unrelated task but the window still has space", "context rot", "answers get worse the longer the session runs", "the agent forgot the plan or my decisions after it summarized", "add a layer on top that manages context without changing the agent", raising autoCompactWindow to give the policy room, or installing/tuning a cross-tool compaction policy or PreCompact hook -- even when "compaction" is never said but the problem is context-window pressure or post-summarization memory loss. Do NOT use to summarize a conversation, build RAG, write a summarization prompt (decides WHEN not HOW), or answer max-context-length trivia.
agent-skill-creator
IncludedCreate cross-platform agent skills from workflow descriptions. Activates when users ask to create an agent, automate a repetitive workflow, create a custom skill, or need advanced agent creation. Triggers on phrases like create agent for, automate workflow, create skill for, every day I have to, daily I need to, turn process into agent, need to automate, create a cross-platform skill, validate this skill, export this skill, migrate this skill. Supports single skills, multi-agent suites, transcript processing, template-based creation, interactive configuration, cross-platform export, and spec validation.
llm-wiki
IncludedUse when building or maintaining a persistent personal knowledge base (second brain) in Obsidian where an LLM incrementally ingests sources, updates entity/concept pages, maintains cross-references, and keeps a synthesis current. Triggers include "second brain", "Obsidian wiki", "personal knowledge management", "ingest this paper/article/book", "build a research wiki", "compound knowledge", "Memex", or whenever the user wants knowledge to accumulate across sessions instead of being re-derived by RAG on every query.
skill-master
IncludedAgent Skills authoring, evaluation, and optimization. Create, edit, validate, benchmark, and improve skills following the agentskills.io specification. Use when designing SKILL.md files, structuring skill folders (references, scripts, assets), ingesting external documentation into skills, running trigger evals, benchmarking skill quality, optimizing descriptions, or performing blind A/B comparisons. Keywords: agentskills.io, SKILL.md, skill authoring, eval, benchmark, trigger optimization.