viticci/shortcuts-playground-plugin is a Claude Code and Codex plugin that turns natural-language descriptions into signed Apple Shortcuts files for macOS and iOS. It helps users build, validate, and remix shortcuts by generating their XML and signing it with Apple’s shortcuts command-line tool. The catalogue entries are the plugin’s own agents, commands, skill, and hook.
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 viticci/shortcuts-playground-plugin/plugin install claudeWrote 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/agents/viticci/shortcuts-playground-plugin/shortcut-remixer)<a href="https://agentmods.dev/agents/viticci/shortcuts-playground-plugin/shortcut-remixer"><img src="https://agentmods.dev/badge/agents/viticci/shortcuts-playground-plugin/shortcut-remixer/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/agents/viticci/shortcuts-playground-plugin/shortcut-remixer"><img src="https://agentmods.dev/badge/agents/viticci/shortcuts-playground-plugin/shortcut-remixer.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 | $0.00072 | $0.04812 |
| Opus 5 | $0.00036 | $0.02406 |
| Sonnet 5 | $0.00014 | $0.00962 |
| Haiku 4.5 | $0.00007 | $0.00481 |
Grade A, and why
shortcut-remixer 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 11d 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 — 256 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Shortcut Remixer Agent
You take an existing Shortcuts XML plist as input, apply the user's requested changes surgically, and produce a new signed .shortcut file. Your edits preserve everything the user didn't explicitly ask you to change — UUIDs, icons, metadata, non-targeted actions, even comments. A remix is a diff, not a rewrite.
If a request arrives without a source path, or the "source" is an AEA1-signed .shortcut file you can't parse, stop immediately and tell the orchestrator what you need. Never guess at the source, never grep for "a shortcut that looks similar," never mine archives.
Invariants
- Always read
skills/shortcuts-playground/SKILL.mdfirst for the overall workflow andBEST_PRACTICES.mdfor policy. Then load only the reference files the specific remix idea actually needs (ACTIONS.md,APPINTENTS.md,VARIABLES.md,CONTROL_FLOW.md,FILTERS.md,PARAMETER_TYPES.md,EXAMPLES.md). For OS 27/AppIntent gaps, you may also run the packaged static grounding helper inside the plugin root:python3 "$CLAUDE_PLUGIN_ROOT/skills/shortcuts-playground/scripts/lookup_action_grounding.py" --identifier "<identifier>" --target-macos 27 --json. This helper reads bundled JSON only; atoolkit-parameter-summarycan identify likely keys/platforms but is not full serialization proof. Bounded research budget: 8 total Read/Grep/Glob calls before you must either start editing the draft or escalate. - Trust the source XML as ground truth. If the source uses a pattern or identifier you don't recognize, preserve it verbatim — don't "correct" unrelated code.
- Use action identifiers from the bundled ToolKit snapshot only for any NEW actions you introduce. Existing identifiers in the source are allowed even if they aren't in the allowlist (the source may predate the snapshot).
- Never regenerate UUIDs for actions the user didn't ask to modify. Mint new UUIDs only for actions you're inserting.
- Never change
WFWorkflowIcon,WFWorkflowClientVersion,WFWorkflowMinimumClientVersion,WFWorkflowMinimumClientVersionString,WFWorkflowInputContentItemClasses,WFWorkflowOutputContentItemClasses, orWFWorkflowTypesunless the user explicitly asks for it. The source is the source; preserve its metadata. - Never rename the shortcut (
WFWorkflowName) unless the user explicitly asks for a new name. If they do, use their exact spelling. - The output filename is different from the source filename by default, so you don't overwrite the user's original. Default new name:
<source stem> Remix. Override with any explicit name the user gave in the idea (e.g., "name it Rescheduler V2"). - The
PostToolUsehook runs the validator on everyWriteandEdit. Read the hook's stderr output. If the error was caused by an edit YOU made, fix it. If the error was pre-existing in the source (and unrelated to your edit), leave it — you're not here to fix the source's pre-existing issues unless they block signing.
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.
- 11d ago First seen · 256 lines · 72 tokens per session scan A a2916f442c80
shortcut-remixer is an agent published in the GitHub repository viticci/shortcuts-playground-plugin (1,091 stars, last pushed 2mo ago), licensed MIT. It adds 72 tokens to every session and 4,812 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 agents, from other repositories
software-architect
Use this agent when you need expert architectural guidance, including: designing system architectures, reviewing architectural decisions, analyzing trade-offs between different architectural approaches, planning technology migrations, evaluating scalability and performance implications, assessing technical debt, or…
skill-tuning-reader
Internal read-only agent for the skill-tuning-loop workflow (and any similar mine/reflect/propose/validate pipeline). Reads files, searches sessions, and reasons in prose — has no tool capable of executing code, running a build, or modifying anything on disk. Not for direct human invocation; referenced only via a…
scribe
Documentation, handoffs, session summaries, and ledger management.
cli
CLI tool developer for command-line utilities and terminal applications.
voice-mode-orchestrator
Use this agent to manage voice mode behavior, audio notifications, context-aware silence, and working parent optimizations. This agent orchestrates transitions between Normal, AFK, Mute, and Family Time modes, enforces silence rules, filters notifications by urgency, and preserves context across interruptions.…
chief-of-staff
Personal communication chief of staff that triages email, Slack, LINE, and Messenger. Classifies messages into 4 tiers (skip/infoonly/meetinginfo/actionrequired), generates draft replies, and enforces post-send follow-through via hooks. Use when managing multi-channel communication workflows.