ClaudeClaw is a lightweight personal assistant built into Claude Code that runs tasks in the background on schedules and responds through messaging services. It is for people who want Claude Code to handle recurring work, voice commands, and integrations while a daemon remains active. Its catalogue commands, skills, instructions, and plugin provide the assistant’s setup and operating workflows.
Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add moazbuilds/claudeclaw/plugin install claudeclawWrote 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/commands/moazbuilds/claudeclaw/jobs)<a href="https://agentmods.dev/commands/moazbuilds/claudeclaw/jobs"><img src="https://agentmods.dev/badge/commands/moazbuilds/claudeclaw/jobs/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/commands/moazbuilds/claudeclaw/jobs"><img src="https://agentmods.dev/badge/commands/moazbuilds/claudeclaw/jobs.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 | $0.00087 | $0.01704 |
| Opus 5 | $0.00044 | $0.00852 |
| Sonnet 5 | $0.00017 | $0.00341 |
| Haiku 4.5 | $0.00009 | $0.00170 |
Grade A, and why
jobs 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 10d 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 — 133 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Manage cron jobs for the heartbeat daemon. Use $ARGUMENTS to determine the action.
Resolving the jobs directory
Read .claude/claudeclaw/settings.json. If the jobsDir field is set, use that path (resolve relative paths against the project root). Otherwise use the default: .claude/claudeclaw/jobs/.
CRITICAL: Job files MUST live under the project-relative jobs directory, NOT under ~/.claude/claudeclaw/jobs/. The daemon only watches the project directory. Using the home directory path will silently fail — the job will never fire.
Parse $ARGUMENTS to identify the sub-command. If no arguments are given, list all jobs.
Sub-commands
list (default when no arguments)
- List all
.mdfiles in the jobs directory. - For each file, read it and display:
- Job name (filename without
.md) - Schedule (cron expression from frontmatter)
- Notify (
true,false, orerror— from frontmatter, defaulttrue) - Prompt (body text, truncated to 100 chars if long)
- Job name (filename without
- If no jobs exist, tell the user and show how to create one.
create or add
Create a new cron job interactively.
-
Use AskUserQuestion to ask:
- "What should this job be called?" (header: "Job name", options: suggest 2 contextual names based on the project, e.g. "git-summary", "test-runner")
- "When should it run?" (header: "Schedule", options: "Every hour (0 * * * *)", "Every 6 hours (0 */6 * * *)", "Daily at 9am (0 9 * * *)", "Daily at midnight (0 0 * * *)")
-
Then ask:
- "What prompt should Claude execute?" (header: "Prompt", options: suggest 2-3 prompts relevant to the project context)
- "Should this job send notifications?" (header: "Notify", options: "Always (default)", "Errors only", "Never")
-
Create the job file at
<jobs-directory>/<name>.mdwith this exact format:--- schedule: "<cron expression>" notify: <true|error|false> --- <prompt>Map the notify answer: "Always" →
true, "Errors only" →error, "Never" →false. Omit thenotifyline if the user chose "Always" (it's the default).
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.
- 10d ago First seen · 133 lines · 87 tokens per session scan A 7e9d8f503aca
jobs is a command published in the GitHub repository moazbuilds/claudeclaw (1,317 stars, last pushed 1mo ago), licensed MIT. It adds 87 tokens to every session and 1,704 once invoked, about $0.0004 per session on Opus 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 2026-08-30.
Other commands, from other repositories
cancel-ralph
Cancel active Ralph Loop.
obsidian-recap
Summarize a time period from the vault - today, week, or month.
setup-pm-skills
Onboard a new user — find out what they do, recommend the right bundles & top skills, and set up a project CONTEXT.md so every skill is tailored to them.
statusbar-style
Switch the status-bar style (classic / capsule / hairline).
engage.actions
Execute Phase 7 - Actions on Objectives and Goal Achievement.
superpowers-execute
Execute the current GSD phase plan with Superpowers instead of gsd-execute-phase.