Enable and explain the reusable human-in-the-loop gates used by persistent agent loops for destructive actions, false-positive overrides, and recovery escalation.
Scanned 9/3/2026
Install to Claude Code
Skills Directorynpx -y skills add jmagly/aiwg --skill agent-persistence --agent claude-codeInstalls into .claude/skills of the current project.
Are you the author of Agent Persistence?
Add the live security badge to your README — it updates automatically with every re-scan.
[](https://www.skillsdirectory.com/skills/jmagly-agent-persistence-aiwg)More formats (shields.io, HTML) on the badges page.
---
namespace: aiwg
name: agent-persistence
platforms: [all]
description: Enable and explain the reusable human-in-the-loop gates used by persistent agent loops for destructive actions, false-positive overrides, and recovery escalation.
triggers:
- enable agent persistence gates
- configure human checkpoints for agent loops
- add destructive action authorization
- configure recovery escalation gates
---
# Agent Persistence
Use this driver to activate or understand the `agent-persistence` addon:
```bash
aiwg use agent-persistence
```
The addon supplies deterministic gate definitions, not a replacement loop
runtime. Compose it with `agent-loop` or another orchestrator that supports
human checkpoints.
## Canonical gates
- `destructive-action-gate.yaml` requires authorization before destructive work.
- `false-positive-override-gate.yaml` records reviewed policy overrides.
- `recovery-escalation-gate.yaml` escalates bounded recovery failures.
Read the gate contract before integrating it, preserve its authorization
boundary, and use the owning loop's status surface to verify activation.
## References
- @$AIWG_ROOT/${CLAUDE_PLUGIN_ROOT}/docs/hitl-integration.md
- @$AIWG_ROOT/agentic/code/addons/agent-loop/skills/agent-loop/SKILL.md
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.
