One slash for the entire sub-brain workflow — list, create, switch, team-dispatch, retire, cancel. Behavior follows from args; nothing else to remember.
Scanned 9/3/2026
Install to Claude Code
Skills Directorynpx -y skills add xgre1/troth --skill agent --agent claude-codeInstalls into .claude/skills of the current project.
Are you the author of Agent?
Add the live security badge to your README — it updates automatically with every re-scan.
[](https://www.skillsdirectory.com/skills/xgre1-agent)More formats (shields.io, HTML) on the badges page.
---
name: agent
description: One slash for the entire sub-brain workflow — list, create, switch, team-dispatch, retire, cancel. Behavior follows from args; nothing else to remember.
argument-hint: [name] [+ | --new] [--tag X] [--persona "..."] | <name>,<name2> <task> | stop [group_id] | retire <name>
allowed-tools: []
kind: deterministic
---
The operator wants something with sub-brains. The skill picks the right action from the args:
> $ARGUMENTS
Argument shape → behavior:
| Args | What happens |
|---|---|
| (empty) | List registered sub-brains, mark the active one |
| `<name>` (exists) | Switch active sub-brain to `<name>` |
| `<name>` (missing) | Error — suggest `+` to create |
| `<name> +` or `<name> --new [--tag X] [--persona "..."]` | Create sub-brain, parent = current active agent |
| `<name1>,<name2>[,...] <task...>` | Team dispatch — fan task across N sub-brains in parallel, each in its own substrate slice |
| `stop` or `stop <group_id>` | Cancel team dispatch (most recent group, or specified) |
| `retire <name>` | Mark sub-brain inactive (kept for audit) |
Why one skill: minimum surface area for the operator. The substrate-as-identity workflow has one entry point (the agent), and what you do with it is shaped by what you say next — no separate `/create`, `/team`, `/brains`, `/kill` to memorize.
Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.
No comments yet. Be the first to comment!
Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...
Ultra-compressed communication mode. Cuts token usage ~75% by speaking like caveman while keeping full technical accuracy. Supports intensity levels: lite, full (default), ultra, wenyan-lite, wenyan-full, wenyan-ultra. Use when user says "caveman mode", "talk like caveman", "use caveman", "less tokens", "be brief", or invokes /caveman. Also auto-triggers when token efficiency is requested.
Routes multi-tool workflows through MCP servers for large datasets and pipelines. Use when Bash tool overhead is limiting throughput on data-heavy tasks.
**Complete production-ready guide for Google Gemini embeddings API** This skill provides comprehensive coverage of the `gemini-embedding-001` model for generating text embeddings, including SDK usage, REST API patterns, batch processing, RAG integration with Cloudflare Vectorize, and advanced use cases like semantic search and document clustering. ---
Interview, source-challenge, verify, save, and ADR-gate fuzzy coding requests into Codex-ready implementation specs. Use when a feature, bugfix, refactor, migration, repo-wide change, or architecture task needs user-verified requirements, source-backed decisions, durable architecture decisions, acceptance criteria, validation commands, rollout notes, saved spec/ADR files, and a Codex execution prompt. Do not use when already fully specified or when the user wants direct implementation now.
