ghostclaw: Skill for Claude Code

.claude/skills/add-heartbeat/SKILL.md

add-heartbeat is a skill for Claude Code from b1rdmania/ghostclaw. It costs 36 tokens per session (1,004 once invoked), scanned A, original, MIT.

A scheduled checklist that periodically checks logs and system conditions, then alerts you only when it finds something needing attention.

In plain words
What is it for?
It helps monitor recent errors, running processes, and other checks you define in a HEARTBEAT.md file.
Why use it?
It reduces the need to repeatedly inspect routine system information and avoids messages when everything is fine.

Skill for Claude Code

Written for Claude Code: installed under .claude/. Also seen: names the AskUserQuestion tool; built for openclaw.

This is b1rdmania/ghostclaw's own configuration. It tells Claude Code how to work on ghostclaw itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything ghostclaw configures →

Reuse

Borrowing it

Nothing to install: this file belongs to b1rdmania/ghostclaw. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/b1rdmania/ghostclaw/main/.claude/skills/add-heartbeat/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/b1rdmania/ghostclaw

Made for: Claude Code.

Wrote 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.

agentmods badge for add-heartbeat

README.md
[![agentmods](https://agentmods.dev/badge/skills/b1rdmania/ghostclaw/add-heartbeat/github.svg)](https://agentmods.dev/skills/b1rdmania/ghostclaw/add-heartbeat)
Your own site
<a href="https://agentmods.dev/skills/b1rdmania/ghostclaw/add-heartbeat"><img src="https://agentmods.dev/badge/skills/b1rdmania/ghostclaw/add-heartbeat/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.

agentmods 80×15 button for add-heartbeat

Your own site · 80×15
<a href="https://agentmods.dev/skills/b1rdmania/ghostclaw/add-heartbeat"><img src="https://agentmods.dev/badge/skills/b1rdmania/ghostclaw/add-heartbeat.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 36 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,004 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00036 $0.01004
Opus 5 $0.00018 $0.00502
Sonnet 5 $0.00007 $0.00201
Haiku 4.5 $0.00004 $0.00100

Measured 9d ago against content hash 30c546d8daed, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

add-heartbeat 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 9d 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.

- `curl -s https://yoursite.com -o /dev/null -w '%{http_code}'` — website uptime
.claude/skills/add-heartbeat/SKILL.md · 117 lines

How it starts

The opening of the file, as written. The whole thing — 117 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Add Heartbeat

Adds a periodic heartbeat that wakes the agent on a cron schedule, runs through a checklist of cheap checks, and only messages the user if something needs attention.

What it does

  1. Creates groups/main/HEARTBEAT.md with a template checklist
  2. Registers a scheduled task that runs the heartbeat on a cron (default: every 30 minutes)
  3. The agent reads the checklist, runs each check, and stays silent if everything is fine

Setup

1. Create HEARTBEAT.md (if not exists)

Check if groups/main/HEARTBEAT.md exists. If not, create it with this template:

# Heartbeat Checks

Run these checks silently. Only message the user if something actually needs their attention.

## Checks

### 1. Error Log

\`\`\`bash
tail -20 ~/nanoclaw/logs/errors.log
\`\`\`

- Each line is JSON with a `"time"` field (Unix ms).
- Calculate cutoff: `Date.now() - (35 * 60 * 1000)`.
- **Ignore** any entry where `time < cutoff`. Don't mention ignored entries at all.
- If the file is empty or all entries are old, this check passes silently.
- If recent errors exist, summarise the actual problem in one line.

### 2. Runaway Processes

\`\`\`bash
ps aux -r | head -5
\`\`\`

- Check if any process is using >90% CPU.
- Chrome/agent-browser processes that have been running for hours are zombies — kill them:
  \`\`\`bash
  pkill -9 -f "agent-browser-chrome"
  \`\`\`
- Alert the user: "Killed zombie Chrome process (was using X% CPU)."
- Also check load average (`uptime`). If load >4, mention it.

### 3. Disk Space

\`\`\`bash
df -h /
\`\`\`

- Alert if usage >80%. State the percentage and partition.

## Rules

- **Silent by default.** If everything is fine: `<internal>All checks passed</internal>` — nothing else.
- **Never explain your reasoning.** Just do the checks and report problems.
- **Never report old/filtered entries.** If an entry is too old, pretend it doesn't exist.
- When alerting, state the problem in plain English, one or two lines max.
- Don't repeat alerts already visible in recent conversation history.

Read the full file on GitHub · 117 lines

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. 9d ago First seen · 117 lines · 36 tokens per session scan A 30c546d8daed

Subscribe to this mod's changes

add-heartbeat is a skill published in the GitHub repository b1rdmania/ghostclaw (92 stars, last pushed 4mo ago), licensed MIT. It adds 36 tokens to every session and 1,004 once invoked, about $0.0002 per session on Opus 5. 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 2026-08-30.

Related

Other skills, from other repositories

lobu-operator

Contribute safely to the Lobu monorepo: worktrees, package rules, red-to-green fixes, validation gates, SDK-first operations, PRs, and rollout checks.

lobu-ai/lobu · 0 tokens

company-agent-infrastructure

Use when designing or building internal/company AI agents that need shared context across company systems, durable organizational memory across sessions or agents, user-scoped permissions, approvals, audit, or governed actions. Also use when deciding whether ordinary MCP tools, RAG, or local agent memory are enough…

lobu-ai/lobu · 70 tokens

lobu-builder

Use when working inside a Lobu project generated by @lobu/cli or any repository centered on lobu.config.ts, AGENTS.md, agent prompt files, local skills, and evals. This skill helps a coding agent inspect the right files, make Lobu-native changes, keep the stack runnable, and validate semantics with chat tests and…

lobu-ai/lobu · 76 tokens

crm-ops

How to operate the Lobu funnel CRM — create and enrich leads, log interactions, advance funnel stages, open and update pilots, and produce the weekly digest. Use whenever the task touches the pipeline.

lobu-ai/lobu · 44 tokens

deliveroo-order

Turn collected lunch orders into a clean per-person order list for a human to place on Deliveroo. Use in step 2 of the lunch run, after orders are collected. The live menu is fetched automatically by the lobu-team-lunch-finalize reaction (via the Owletto Chrome extension) — this skill never places an order or touches…

lobu-ai/lobu · 75 tokens

lobu

Use Lobu MCP for shared, permission-aware company context, durable organizational memory, and governed actions. Trigger when the user asks what the organization knows, needs context from connected company systems, wants to preserve a durable fact or decision, or needs to discover and use Lobu SDK capabilities.

lobu-ai/lobu · 60 tokens