# Wh0FF24

> Open-source publisher. Listings imported from github.com/Wh0FF24 — credited to the original author with their license.

- **Listings:** 5
- **Total installs:** 0
- **Profile:** https://agentstack.voostack.com/s/wh0ff24
- **Website:** https://github.com/Wh0FF24

## Published listings

- [Whoff Agents](https://agentstack.voostack.com/l/mcp-wh0ff24-whoff-agents) — MCP server · Free · security-reviewed — `agentstack add mcp-wh0ff24-whoff-agents`
  Production-tested Claude Code skills for multi-agent workflows. Free context-anchor skill + Atlas Starter Kit.
- [Agent Handoff](https://agentstack.voostack.com/l/skill-wh0ff24-whoff-agents-agent-handoff) — Skill · Free · security-reviewed — `agentstack add skill-wh0ff24-whoff-agents-agent-handoff`
  Generate a structured context packet before dispatching any subagent. Prevents the #1 cause of subagent failure: the agent acts on a wrong assumption that was never stated. Use before every Agent tool call, tmux dispatch, or session delegation.
- [Context Anchor](https://agentstack.voostack.com/l/skill-wh0ff24-whoff-agents-context-anchor) — Skill · Free · security-reviewed — `agentstack add skill-wh0ff24-whoff-agents-context-anchor`
  Drop a working reference at any point in a session to prevent cascading context drift. Use when switching tasks, resuming after a break, or handing off between agents.
- [Cost Cap Guard](https://agentstack.voostack.com/l/skill-wh0ff24-whoff-agents-cost-cap-guard) — Skill · Free · security-reviewed — `agentstack add skill-wh0ff24-whoff-agents-cost-cap-guard`
  Enforce per-session token budgets before dispatching agents. Calculates expected token cost, flags over-budget operations, and generates a trimmed prompt that fits within your limit — without losing the objective.
- [Dead Letter](https://agentstack.voostack.com/l/skill-wh0ff24-whoff-agents-dead-letter) — Skill · Free · security-reviewed — `agentstack add skill-wh0ff24-whoff-agents-dead-letter`
  Capture a failed or blocked task before it disappears. Categorizes the failure mode, extracts what was learned, and generates either a retry packet with the root cause fixed or an escalation message with specific decision points. Use whenever an agent returns a blocker, error, or partial result.

---
Seller on AgentStack — the marketplace for AI agent skills and MCP servers. Every listing is security-reviewed. Install any with `agentstack add <slug>`.