---
title: "persistence-self-monitoring"
description: "Persist-or-quit self-check for coding agents. Bundles the persistence-self-monitoring skill (the 'what': name the hypothesis held, count the variants, name a rival, decide) with per-host hooks (the 'when') that count wha"
canonical: https://agentpluginsdirectory.com/plugins/persistence-self-monitoring
last-updated: 2026-09-16
---

# persistence-self-monitoring
Persist-or-quit self-check for coding agents. Bundles the persistence-self-monitoring skill (the 'what': name the hypothesis held, count the variants, name a rival, decide) with per-host hooks (the 'when') that count what an agent cannot feel, the same file edited N times, the same command or error failing N times, tool calls piling up since the user's last message, and speak only when a threshold is crossed. Never blocks. Portable core: the skill only; hooks are host-specific (hooks/ for Claude Code, cursor/ for Cursor).
- Slug: persistence-self-monitoring
- Publisher: David Giordano
- Repository: https://github.com/3dgiordano/agent-plugins
- Manifest: plugins/persistence-self-monitoring/plugin.json
- Version: 0.1.2
- License: Apache-2.0
- Category (editorial): other
- Skills: 1 (persistence-self-monitoring)
- MCP servers: 0
- Stars: 0
- Repository created: 2026-09-15
- Repository last pushed: 2026-09-15
- Publisher type: User
- Listing: https://agentpluginsdirectory.com/plugins/persistence-self-monitoring
- Schema: https://agent-plugins.org/schemas/1.0.0/plugin.schema.json

## What persistence-self-monitoring does, in the publisher's words

Persist-or-quit self-check for coding agents. Counts the two things an agent cannot feel, repeating variants of the same attempt and effort out of proportion to the request, and, only when a threshold is crossed, hands the agent the number and asks for an explicit decision: one more try with a stop condition, switch approach, step back to the plan, or report to the user.

It answers "is it still worth insisting on this?": the third question of the collection, after am I doing what the plan asks? (executive-self-monitoring) and is what I concluded true? (epistemic-self-monitoring).

It never blocks. The value is the objective count at the right moment; the judgment stays with the agent, and with the user, who sees the decision.

From the project README, punctuation lightly normalized. Full text: https://raw.githubusercontent.com/3dgiordano/agent-plugins/HEAD/plugins/persistence-self-monitoring/README.md

## Skills

- persistence-self-monitoring: Persist-or-quit self-check for when an approach has stopped working. Detects two things agents cannot feel, repeating variants of the same attempt, and effort out of proportion to the request, and turns them into an explicit decision: one more try with a stop condition, switch approach, step back t…

Descriptions come from the frontmatter of each SKILL.md, punctuation lightly normalized.