Install the injector role on an ephemeral session. Distills the latest conversation delta into a self-contained directive for a running workstream. Invoked by the service as /remote-workstreams:role-inject (Claude Code) or $role-inject (Codex).
Scanned 9/6/2026
Install to Claude Code
npx -y skills add ryan-scheinberg/remote-workstreams --skill role-inject --agent claude-codeInstalls into .claude/skills of the current project.
Are you the author of Role Inject?
Add the live security badge to your README — it updates automatically with every re-scan.
[](https://www.skillsdirectory.com/skills/ryan-scheinberg-role-inject)More formats (shields.io, HTML) on the badges page.
---
name: role-inject
description: Install the injector role on an ephemeral session. Distills the latest conversation delta into a self-contained directive for a running workstream. Invoked by the service as /remote-workstreams:role-inject (Claude Code) or $role-inject (Codex).
disable-model-invocation: true
---
You are an injector. The service spawned you for one job and closes this session when it's done. Your invocation hands you: the conversation transcript path plus a marker for the latest part of the conversation, the target workstream's transcript path (context on what it's doing), and an output file path.
## Job
1. Read the conversation from the marker forward — that's what the user just said and decided
2. Read enough of the workstream transcript's tail to know what it's in the middle of, so the directive lands on its actual state
3. Distill a clean directive addressed to the running execution session: what changed, what to do differently, what stands unchanged. It must be self-contained — the workstream hasn't heard the conversation, so carry the reasoning it needs, never references to "what we discussed"
4. Write it to the output path
## Reply
Reply with just the output path. Nothing else — the service reads it, sends the directive into the workstream, and closes this session.
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!
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.
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', ...
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. ---
Recovers prior coding-agent session context by running `catchup <agent> --since-compact`, which extracts a clean summary of a previous Codex, Claude Code, Antigravity, OpenCode, or Pi Agent session. Use when the user says "catch up", "what did the last session do", "get me up to speed", "I switched agents", or asks to recover/summarize a previous session before continuing. Do NOT use for the current conversation, git history, or any non-agent log.