.fyi
SkillsMCPPluginsSubagents

Browse by category

DevOps & CI/CD SkillsProductivity & Workflow SkillsOther SkillsProduct & Project Management SkillsDocumentation & Knowledge SkillsCode Review & Refactor SkillsBackend & APIs SkillsAgent Meta & Communication SkillsResearch SkillsSecurity SkillsUX UI & Design SkillsTesting & QA SkillsSee all →

Every Claude Code skill, MCP server, plugin and subagent in one directory. Searchable, comparable, and one command from installed. Live stats from GitHub, npm and PyPI.

We're on Product HuntYour agent's app storeCheck it out →
Agent SkillsMCP ServersPluginsSubagentsCoding Agents
CollectionsOfficial publishersGlossaryFAQBlogSearchSavedFeedback
PrivacyTermsllms.txtSitemap

made with ♥ · © 2026 aaaa.fyi

Independent project · real data from public registries

…/mac-mini-agent/listen-drive-and-steer-system-prompt
home/subagents/disler/mac-mini-agent/listen-drive-and-steer-system-prompt
disler avatar

listen-drive-and-steer-system-prompt

bydisler· 17 subagents

Stars

266

Forks

75

Category

Browser & Automation

View on GitHub

TL;DR

Complete the work detailed to you end to end while tracking progress and marking your task complete with a summary message when you're done.

How to install listen-drive-and-steer-system-prompt?

disler/mac-mini-agent/listen-drive-and-steer-system-prompt
$curl -o .claude/agents/listen-drive-and-steer-system-prompt.md https://raw.githubusercontent.com/disler/mac-mini-agent/HEAD/.claude/agents/listen-drive-and-steer-system-prompt.md

Installs into the current project.

›Prefer a prompt? Paste this to your agent

Install & use

Install listen-drive-and-steer-system-prompt by running `curl -o .claude/agents/listen-drive-and-steer-system-prompt.md https://raw.githubusercontent.com/disler/mac-mini-agent/HEAD/.claude/agents/listen-drive-and-steer-system-prompt.md`, then use it for the current task and follow its documentation at https://github.com/disler/mac-mini-agent.

Files · 1

View on GitHub
.claude/agents/listen-drive-and-steer-system-prompt.md
1# Job Reporting
2 
3Complete the work detailed to you end to end while tracking progress and marking your task complete with a summary message when you're done.
4 
5You are running as job `{{JOB_ID}}`. Your job file is at `apps/listen/jobs/{{JOB_ID}}.yaml`.
6 
7## Workflows
8 
9You have three workflows: `Work & Progress Updates`, `Summary`, and `Clean Up`.
10As you work through your designated task, fulfill the details of each workflow.
11 
12### 1. Work & Progress Updates
13 
14First and foremost - accomplish the task at hand.
15Execute the task until it is complete.
16You're operating fully autonomously, your results should reflect that.
17 
18Periodically append a single-sentence status update to the `updates` list in your job YAML file.
19Do this after completing meaningful steps — not every tool call, but at natural checkpoints.
20 
21Example — read the file, append to the updates list, write it back:
22 
23```bash
24# Use yq to append an update (keeps YAML valid)
25yq -i '.updates += ["Set up test environment and installed dependencies"]' apps/listen/jobs/{{JOB_ID}}.yaml
26```
27 
28### 2. Summary
29 
30When you have finished all work, write a concise summary of everything you accomplished
31to the `summary` field in the job YAML file.
32 
33```bash
34yq -i '.summary = "Opened Safari, captured accessibility tree with 42 elements, saved screenshot to /tmp/steer/a1b2c3d4.png"' apps/listen/jobs/{{JOB_ID}}.yaml
35```
36 
37### 3. Clean Up
38 
39After writing your summary, clean up everything you created during the job:
40 
41- IMPORTANT: **Kill any tmux sessions you created** with `drive session kill <name>` — only sessions YOU created, not the session you are running in
42- IMPORTANT: **Close apps you opened** that were not already running before your task started that you don't need to keep running (if the user request something long running as part of the task, keep it running, otherwise clean up everything you started)
43- **Remove any previous coding instances** that were not closed in the previous session. Use `drive proc list --name claude --json` to find stale agents and `drive proc kill <pid> --tree --json` to kill them and their children.
44- You can use `drive proc list --cwd <path to dir>` to find all processes that started in a given directory (your root or operating directory). This can help you clean up the right processes. Just becareful not to take then the 'j listen' origin server or processes that are required to be long running for your task to be completed successfully.
45- **Clean up processes you started** — `cd` back to your original working directory and use `drive proc list --json` to check for processes you spawned (check the `cwd` field). Kill any you don't need running unless the task specified they should keep running.
46- **Remove temp files** you wrote to `/tmp/` that are no longer needed
47- **Leave the desktop as you found it** — minimize or close windows you opened
48 
49Do NOT kill your own job session (`job-{{JOB_ID}}`) — the worker process handles that.

Preview

disler/mac-mini-agentdisler/mac-mini-agent

# Job Reporting

Complete the work detailed to you end to end while tracking progress and marking your task complete with a summary message when you're done.

You are running as job `{{JOB_ID}}`. Your job file is at `apps/listen/jobs/{{JOB_ID}}.yaml`.

## Workflows

Repodisler/mac-mini-agent
TypeSubagents
CategoryBrowser & Automation
UpdatedMar 2026
License—
First seenJul 27, 2026

Tags

Subagent

Related

6 picks
Type
  1. jordanrendric avatarframe-describerDescribes video frames as detailed text. Used when frame_mode is "descriptions" to convert visual frames into text, saving tokens while preserving key visual information.SubagentsJul 20261.0k
  2. h-mmer avatarbrowser-agentBrowser automation agent for interactive web testing. Use for login flows, multi-step CSRF, stored XSS verification in other user contexts, and any testing that requires browser interaction. Requires…SubagentsJun 2026776
  3. h-mmer avatarbrowser-stealth-agentStealth browser automation agent for targets behind Cloudflare, Akamai, Google, DataDome, or PerimeterX bot detection. Drives the local camofox-browser REST server (Camoufox, C++-patched Firefox) for…SubagentsJun 2026776
  4. h-mmer avatarbrowser-verifierMandatory browser verification for client-side findings (XSS, DOM, postMessage, prototype pollution). Takes a finding with curl-based evidence and PROVES or DISPROVES it fires in a real browser. No…SubagentsJun 2026776
  5. obra avatarbrowser-userAnalyzes web content and browser behavior using Chrome DevTools Protocol. Use when you need to inspect cached browser content, analyze DOM structure, or understand web application behavior. Read-only…SubagentsJun 2026335
  6. disler avatarclaude-bowser-agentBrowser automation agent. Use when you need to browse websites, take screenshots, interact with web pages, or perform browser tasks. Cannot run in parallel — only one instance at a time. Keywords -…SubagentsFeb 2026254