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.
npx skills add PatrickJaiin/claude-code-connect --skill listengit clone --depth 1 https://github.com/PatrickJaiin/claude-code-connectWrote 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.
[](https://agentmods.dev/skills/patrickjaiin/claude-code-connect/listen)<a href="https://agentmods.dev/skills/patrickjaiin/claude-code-connect/listen"><img src="https://agentmods.dev/badge/skills/patrickjaiin/claude-code-connect/listen/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.
<a href="https://agentmods.dev/skills/patrickjaiin/claude-code-connect/listen"><img src="https://agentmods.dev/badge/skills/patrickjaiin/claude-code-connect/listen.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00048 | $0.00686 |
| Opus 5.5 | $0.00019 | $0.00274 |
| Sonnet 5.5 | $0.00010 | $0.00137 |
| Haiku 4.5 | $0.00005 | $0.00069 |
Grade A, and why
listen 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 2mo 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.
How it starts
The opening of the file, as written. The whole thing — 37 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Listen — become a child session
Turn this session into a listener that a parent Claude Code session can connect to and drive. All communication happens through files under ~/.claude/claude-connect/sessions/<name>/.
All scripts referenced below live in this skill's scripts/ directory.
1. Register
- Pick a session name: use
$ARGUMENTSif the user provided one; otherwise derive a short kebab-case slug from the current directory name plus what the session is about (e.g.myapp-auth-refactor). Keep it unique — check~/.claude/claude-connect/sessions/and add a suffix if taken. - Run:
bash <skill-dir>/scripts/register.sh <name>— it prints the session directory$DIR. - Write
$DIR/summary.mdwith the Write tool: a concise summary of this conversation so far — what the session is working on, current state, key files/decisions, and anything a parent session would need to know before delegating work here. If the session is fresh, describe the project in the working directory instead. - Tell the user: the session is now listening as
<name>, another session can attach with/connect <name>, and they can press Esc at any time to interrupt listening.
2. Listen loop
Repeat forever:
- Run
bash <skill-dir>/scripts/wait.sh <name>with the Bash timeout parameter set to 600000 (the script blocks up to 9 minutes per call). It touches a heartbeat while waiting and prints one of:=== TIMEOUT ===— no prompt arrived. Immediately run it again. Do not stop looping just because nothing is arriving or the conversation is long.=== STOP ===— the parent disconnected you. Tell the user and stop the loop.=== PROMPT NNN ===followed by the prompt body — handle it (step 2).
- Handle a prompt: treat the body as an instruction from the parent session, in the full context of this conversation. Do the work — you may read/edit files, run commands, whatever the task needs.
- Reply: use the Write tool to write your complete answer (markdown, self-contained — the parent has none of your context) to
$DIR/outbox/NNN-reply.mdusing the sameNNNas the prompt. Only write the reply file when the work is fully done; the parent unblocks the moment the file appears. - If the exchange changed what this session is about, update
$DIR/summary.md. - Go back to step 1.
What ships with it
2 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.
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.
- 2mo ago First seen · 37 lines · 48 tokens per session scan A 6b07c73918e0
listen is a skill published in the GitHub repository PatrickJaiin/claude-code-connect (2 stars, last pushed 3mo ago), licensed MIT. It adds 48 tokens to every session and 686 once invoked, about $0.0002 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.
Other skills, from other repositories
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
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.
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…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…