connect

A connection tool for attaching one Claude Code session to another session that is waiting in listen mode.

In plain words
What is it for?
Use it to list waiting sessions, read a child session’s summary, send it instructions, and read its replies.
Why use it?
It lets you inspect the other session and communicate with it without switching manually between sessions.

Skill for Claude CodeCodex

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.

agentmods
npx agentmods add skills/patrickjaiin/claude-code-connect/connect
Any agent
npx skills add PatrickJaiin/claude-code-connect --skill connect
Clone the repo
git clone --depth 1 https://github.com/PatrickJaiin/claude-code-connect

Made for: Claude Code, Codex.

Per session 48 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 638 The whole file, excluding the scripts and references it only reads on demand.
Security scan C 1 finding. Scan, not verified.
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.

ModelPer sessionOnce invoked
Fable 5 $0.00048 $0.00638
Opus 5 $0.00024 $0.00319
Sonnet 5 $0.00010 $0.00128
Haiku 4.5 $0.00005 $0.00064

Measured 2d ago against content hash eecca2b8e475, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade C, and why

connect scanned grade C with 1 finding 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 2d ago.

The scan reads SKILL.md. This mod also ships 3 executable files (scripts/await.sh, scripts/list.sh, scripts/send.sh), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

Recursive force deletehighDestructive command

rm -rf with a variable or a broad path is one typo away from removing the wrong tree.

If the user wants to stop the child's listen mode: `touch ~/.claude/claude-connect/sessions/<name>/stop`. To merely detach while leaving the child listening, just stop sending prompts. To clean up a dead session's files:
skills/connect/SKILL.md · 32 lines

How it starts

The opening of the file, as written. The whole thing — 32 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Connect — attach to a listening child session

Drive another Claude Code session that ran /listen. Communication is via files under ~/.claude/claude-connect/sessions/<name>/. All scripts referenced below live in this skill's scripts/ directory.

Finding and attaching

  • /connect with no arguments → run bash <skill-dir>/scripts/list.sh, show the user each session's name, status (LISTENING / WORKING / STALE), working directory, and summary preview, then ask which to attach to. If exactly one is LISTENING, suggest it.
  • /connect <name> (or after the user picks) → read ~/.claude/claude-connect/sessions/<name>/summary.md and meta.json, present the child's summary to the user, and remember <name> as the connected session for the rest of this conversation. Warn (but still attach) if the session looks STALE.
  • /connect <name> <prompt...> → attach as above, then immediately send the rest of the arguments as the first prompt.

Sending a prompt and reading the reply

When the user asks you to send something to the child (e.g. "ask it to run the tests", "tell it to refactor X"):

  1. Write the prompt to a temp file (use the scratchpad dir), phrased as a clear standalone instruction — the child has its own context but none of this conversation's.
  2. NNN=$(bash <skill-dir>/scripts/send.sh <name> <prompt-file>) — prints the sequence number.
  3. bash <skill-dir>/scripts/await.sh <name> $NNN with the Bash timeout parameter set to 600000. It prints one of:
    • === REPLY NNN === + body → show the child's reply to the user (quote it substantially, don't over-compress; make clear it's the child speaking).
    • === TIMEOUT (state: working) === → the child is still working; run await.sh again. Keep re-running while state is working unless the user interrupts.
    • === CHILD NOT LISTENING === → the child session's heartbeat went stale (its user may have interrupted it or closed the session). Tell the user; the prompt file stays queued and the child will pick it up if /listen is resumed there.

Read the full file on GitHub · 32 lines

Files

What ships with it

3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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.

  1. 2d ago First seen · 32 lines · 48 tokens per session scan C eecca2b8e475

Subscribe to this mod's changes

connect is a skill published in the GitHub repository PatrickJaiin/claude-code-connect (2 stars, last pushed 1mo ago), licensed MIT. It adds 48 tokens to every session and 638 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it C with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

brainstorming

You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.

obra/superpowers · 37 tokens

auto-perf-optimize

Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.

microsoft/vscode · 62 tokens

chat-perf

Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.

microsoft/vscode · 51 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens