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/commands/viticci/shortcuts-playground-plugin/remix)<a href="https://agentmods.dev/commands/viticci/shortcuts-playground-plugin/remix"><img src="https://agentmods.dev/badge/commands/viticci/shortcuts-playground-plugin/remix.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 | $0.00086 | $0.00821 |
| Opus 5 | $0.00043 | $0.00411 |
| Sonnet 5 | $0.00017 | $0.00164 |
| Haiku 4.5 | $0.00009 | $0.00082 |
Grade B, and why
remix scanned grade B 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 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.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
- **Never grep `~/Documents` broadly, `~/Agent`, `~/.claude/skills`, `~/.claude/plugins`, `~/.claude/projects`, `~/Library`, `/Applications`, or `/System`.** Even when the agent escalates on "I don't know this schema" or How it starts
The opening of the file, as written. The whole thing — 35 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Delegate to the shortcut-remixer agent (via the Agent tool with subagent_type: shortcut-remixer) to apply a surgical diff to an existing Shortcuts XML plist. Pass the full instruction below to the agent so it can parse out the source path and the remix idea:
$ARGUMENTS
The agent owns the full remix workflow end-to-end. Your job as the orchestrator is minimal:
- Invoke the agent with
subagent_type: shortcut-remixer, passing$ARGUMENTSverbatim. The agent will extract the source path and the remix idea itself. - Wait for the agent's result. The agent is responsible for: resolving the output directory, parsing its input, validating the source (path exists, is unsigned XML, parses as a plist), reading it, baselining it against the validator, reading skill reference files, planning the diff, writing the draft, Craig-Loop validating, archiving, signing, verifying the signed file exists, and reporting.
- Relay the agent's report to the user verbatim. Do not re-run any steps the agent already did.
When the agent escalates
The remixer will escalate to you (the orchestrator) in three main cases:
- No source path found in
$ARGUMENTS. The agent will ask the user to re-run the command with an explicit absolute path. Relay the agent's message verbatim and stop. - Source is signed (
.shortcut/ AEA1). The agent will ask the user to export the shortcut as unsigned XML first. Relay the message verbatim. - Source is missing, unreadable, or not a Shortcuts plist. The agent will report the specific reason. Relay and stop.
In all escalation cases: do not do the agent's work for it. Do not grep for "similar" files, do not try to plutil/xxd the signed file, do not search the user's filesystem for a matching shortcut. Just relay the escalation to the user and wait.
Hard rules for this command
All the same rules that apply to /shortcuts-playground:build apply here:
- Never grep
~/Documentsbroadly,~/Agent,~/.claude/skills,~/.claude/plugins,~/.claude/projects,~/Library,/Applications, or/System. Even when the agent escalates on "I don't know this schema" or "I can't find the source." Those paths may contain the user's private files, deleted plugin versions, session logs, or system binaries — none of them are authoritative reference material. - Never run
plutil,xxd,file, or other binary inspectors on signed.shortcutfiles. Signed shortcuts are Apple Encrypted Archives (AEA1); they cannot be read as plaintext plists. - Never mine prior archived shortcuts as a reference corpus for the agent to crib from. The source the user gave the remixer is its ONLY reference for context; the plugin directory is the ONLY reference for patterns.
- Never overwrite the source file. The remixer writes to
<OUTPUT_DIR>/drafts/<new name>.xmlunder a new name so the user's original stays intact. - Do not execute the shortcut or import it into Shortcuts.app. The user will open the signed file themselves. Your job ends at "signed file exists, here is its path."
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 · 35 lines · 86 tokens per session scan B bce9f6e29112
remix is a command published in the GitHub repository viticci/shortcuts-playground-plugin (1,087 stars, last pushed 2mo ago), licensed MIT. It adds 86 tokens to every session and 821 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other commands, from other repositories
triage
Triage Linear issue with comprehensive analysis.
todo.template
This prompt was authored for Claude-style slash workflows. In Codex runtime, adapt tool calls as follows.
terse
Switch reply compression level — /terse [lite|full|ultra|off]. Complements RTK (input savings) with output-side savings.
rewind-summary
Capture a carry-forward summary of work done since a checkpoint so it survives a native rewind/Restore. Run before rewinding.
end-session
Close session — update log and document progress.
cancel-loop
A command for stopping an active automated loop managed through a local Fireauto state file.