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 atman-33/workhub --skill manage-desktop-routinesgit clone --depth 1 https://github.com/atman-33/workhubWrote 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/atman-33/workhub/manage-desktop-routines)<a href="https://agentmods.dev/skills/atman-33/workhub/manage-desktop-routines"><img src="https://agentmods.dev/badge/skills/atman-33/workhub/manage-desktop-routines/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/atman-33/workhub/manage-desktop-routines"><img src="https://agentmods.dev/badge/skills/atman-33/workhub/manage-desktop-routines.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 | $0.00058 | $0.02375 |
| Opus 5 | $0.00029 | $0.01188 |
| Sonnet 5 | $0.00012 | $0.00475 |
| Haiku 4.5 | $0.00006 | $0.00237 |
Grade A, and why
manage-desktop-routines 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 8d 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 — 101 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Manage Claude Code Desktop routines: create a local routine, and keep a portable backup so it isn't lost when you move to a new machine.
Local vs remote
Desktop's Routines page creates two different things:
- Local — a scheduled task stored at
~/.claude/scheduled-tasks/<taskId>/SKILL.md(or underCLAUDE_CONFIG_DIR) on this machine only. It runs only while Desktop is open. Nothing about it is synced to the cloud, so it is lost on a fresh machine unless backed up. This skill manages local routines only. - Remote — a saved configuration in the user's claude.ai account, run on Anthropic-managed cloud infrastructure. It already survives a machine change on its own and needs no backup. If the task needs to run with the machine off, or fire on an API call or GitHub event, tell the user to create a Remote routine instead, from Desktop's Routines → New routine → Remote or claude.ai/code/routines — this skill does not create those.
Ask the user which they need only if it isn't obvious from the request; local file/tool access implies Local, "even when my laptop is off" or API/GitHub triggers imply Remote.
Backup scope
list_scheduled_tasks and create_scheduled_task expose taskId, description, prompt, cronExpression/fireAt, and enabled. They do not expose the working folder or model shown in Desktop's own routine form — those live outside this tool surface. A backup/restore cycle through this skill preserves the schedule and prompt exactly, but after a restore the user must reopen each routine in Desktop and re-pick its folder and model, and re-approve any "always allow" tool permissions (these reset to Ask mode by default).
Backup directory config
The backup location is stored in config.json, next to this file (same folder as SKILL.md). It is generated from the checked-in config.example.json template and is itself git-ignored, so each installer of this skill can point it at their own directory without touching the shared marketplace repo.
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.
- 8d ago First seen · 101 lines · 58 tokens per session scan A cb745cc75b4a
manage-desktop-routines is a skill published in the GitHub repository atman-33/workhub (2 stars, last pushed today), licensed MIT. It adds 58 tokens to every session and 2,375 once invoked, about $0.0003 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 2026-09-03.
Other skills, from other repositories
tasks
A task-breakdown tool that turns a plan, specification, feature brief, bug report, technical-debt item, or chore into small TASK-NNN work items. Technical debt means postponed cleanup or design work in a codebase.
prd
A Product Requirements Document (PRD) writer for large software initiatives. A PRD records the problem, goals, requirements, assumptions, and evidence before implementation begins.
roadmap
An implementation plan made from a technical specification, organized into phases, milestones, and dependencies.
pr
A command for managing pull requests on GitHub or Bitbucket Server. A pull request is a request for other developers to review and merge changes into a project branch.
sync
Rebuild PROJECTSTATE derived fields from artifact files.
chore
A shortcut for recording a small, routine coding task that needs little or no planning. It can register the work alone or also create a ready-to-do task.