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 humanerd-drew/opencode-drewgent --skill launchd-process-health-checkgit clone --depth 1 https://github.com/humanerd-drew/opencode-drewgentWrote 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/humanerd-drew/opencode-drewgent/launchd-process-health-check)<a href="https://agentmods.dev/skills/humanerd-drew/opencode-drewgent/launchd-process-health-check"><img src="https://agentmods.dev/badge/skills/humanerd-drew/opencode-drewgent/launchd-process-health-check.svg" alt="Measured on agentmods" 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 | $0.00000 | $0.10056 |
| Opus 5 | $0.00000 | $0.05028 |
| Sonnet 5 | $0.00000 | $0.02011 |
| Haiku 4.5 | $0.00000 | $0.01006 |
Grade A, and why
launchd-process-health-check scanned grade A 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 7d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
- **Port mismatch (F2)**: "kanban-dashboard port 5555 HTTP 000" turned out to be testing the wrong port — kanban-dashboard listens on **8765** (`ultraseek-http`). `curl http://localhost:8765/kanban` returned 200. Lesson: How it starts
The opening of the file, as written. The whole thing — 530 lines — stays where its author put it; the contents beside it link to each section on GitHub.
title: Launchd Process Health Check name: launchd-process-health-check type: skill space: outcome description: Diagnose launchd service state when launchctl list shows stale exit codes but process is actually running tags: [skill, launchd, troubleshooting, diagnostics] created: 2026-05-31 updated: 2026-06-12 links:
- "[[@action/skills/SKILL-INDEX]]"
- "[[@memory/growth/harness-autonomous-behaviors]]"
- "[[@identity/brain/rules]]"---
Launchd Process Health Check
Problem
When checking launchctl list | grep <name>, the Exit code and PID columns can be misleading. A process can:
- Show "Exit -15" but actually be running (someone else restarted it)
- Show old PID but have been replaced by a new process
- Be managed by launchd but running under a different binary
Always Verify With These 3 Commands
# 1. launchd's view (may be stale)
launchctl list | grep <service-name>
# 2. Is it actually listening? (ground truth)
lsof -i :<port> 2>/dev/null
# 3. Is there a process? (ground truth)
ps aux | grep -i <process-name> | grep -v grep
Common Exit Codes Explained
| Exit Code | Meaning |
|---|---|
| 0 | Clean exit (normal) |
| -15 | SIGTERM received (killed) |
| -64 | Exit with signal 64 (often network/socket issue) |
| 87299 | Large number — usually a PID shown as "last exit status", not an exit code |
Important: The PID column shows the LAST process that exited, not the current one. A "running" service can show an old PID with a non-zero exit code.
Reverse Pattern: Process Died and launchd Didn't Restart
The opposite case is more dangerous and is the one that actually broke {{AGENT_NAME}} infra on 2026-06-10 (cron / n8n / quartz-fswatch all dead, never restarted, undetected for 6+ days):
Symptoms:
launchctl list | grep <name>→ row is present but PID is-and Exit is non-zero (e.g. -15 for SIGTERM, 1 for crash)lsof -i :<port>→ empty (nothing listening)ps aux | grep <name>→ empty (no process)cron-runner.log/n8n.log/quartz-fswatch.log→ last entry is hours/days old, often a graceful shutdown ("Received SIGTERM. Shutting down...")
What ships with it
8 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.
- references/2026-06-10-customize-layer-recipe.md 14 KB
- references/2026-06-10-harmony-check-recipe.md 13 KB
- references/2026-06-10-incident-fix-recipe.md 10 KB
- references/2026-06-10-launchd-mass-failure.md 6.1 KB
- references/2026-06-10-log-rotation-recipe.md 8.5 KB
- references/2026-06-10-smoke-test-recipe.md 4.9 KB
- references/2026-06-10-vault-graph-recipe.md 8.5 KB
- references/gateway-watchdog-2026-06-11.md 1.8 KB
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.
- 7d ago First seen · 530 lines · 0 tokens per session scan A a24c747b9329
launchd-process-health-check is a skill published in the GitHub repository humanerd-drew/opencode-drewgent (2 stars, last pushed 1mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 10,056 tokens. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
debug-optimize-lcp
Guides debugging and optimizing Largest Contentful Paint (LCP) using Chrome DevTools MCP tools. Use this skill whenever the user asks about LCP performance, slow page loads, Core Web Vitals optimization, or wants to understand why their page's main content takes too long to appear. Also use when the user mentions…
systematic-debugging
Use when debugging a failing test, build error, or runtime issue that isn't immediately obvious. Guides a 4-phase root cause analysis instead of random fix attempts.
diagnose
Trace from a reproduced symptom to the source code that causes it. Pin the specific file and approximate line, rate confidence in the cause and clarity of the fix independently, and always propose a concrete fix.
repro-admin
Reproduce an EmDash admin UI bug. Attach a container, start the demo dev server, drive the admin with agent-browser using the dev-bypass session, and capture the reproduction as screenshots plus a replayable transcript.
log-error-digest
Analyze log files to troubleshoot errors, identify peak error periods, and produce error clustering, frequency statistics, and time distribution reports. Supports JSON, syslog, and Nginx formats with automatic detection. Use when a user uploads a .log file and asks to analyze errors, find patterns, debug issues, or…
byted-util-volcengine-detect-retry
An orchestration workflow for Volcengine Cloud Detect, a service that checks websites or network endpoints from test locations.