---
title: "coverage-self-monitoring"
description: "Parts-ledger discipline for multi-part or hard tasks. Bundles the coverage-self-monitoring skill (the 'what': write the ledger first, the parts, which is hardest and why, hardest first, and close each part as done, block"
canonical: https://agentpluginsdirectory.com/plugins/coverage-self-monitoring
last-updated: 2026-09-16
---

# coverage-self-monitoring
Parts-ledger discipline for multi-part or hard tasks. Bundles the coverage-self-monitoring skill (the 'what': write the ledger first, the parts, which is hardest and why, hardest first, and close each part as done, blocked with an observed reason, or returned to the owner) with per-host hooks (the 'when') that count the stub / placeholder / TODO markers written per turn, ask for a ledger when the prompt enumerates three or more items, and scan the final message for deferred work with no [COVERAGE CHECK]. Never blocks. Portable core: the skill only; hooks are host-specific (hooks/ for Claude Code, cursor/ for Cursor).
- Slug: coverage-self-monitoring
- Publisher: David Giordano
- Repository: https://github.com/3dgiordano/agent-plugins
- Manifest: plugins/coverage-self-monitoring/plugin.json
- Version: 0.1.1
- License: Apache-2.0
- Category (editorial): other
- Skills: 1 (coverage-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/coverage-self-monitoring
- Schema: https://agent-plugins.org/schemas/1.0.0/plugin.schema.json

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

Parts-ledger discipline for coding agents. Before a multi-part or hard task the agent writes down the parts, names the hardest one and why, and takes it first; at the end every part is closed as done, blocked with an observed reason, or returned to the owner, never silently dropped. The hooks count the stubs, placeholders and TODOs written per turn, ask for the ledger when the prompt enumerates three or more items, and notice deferral language in the final message that no closing ledger accounts for.

It answers "does what I delivered cover every part of the request, including the hard one?": the complement of executive-self-monitoring, which asks whether the work is outside the plan. This one asks whether it is below it.

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

## Skills

- coverage-self-monitoring: Parts-ledger discipline for multi-part or hard tasks. An agent produces the tractable subset of a request with the same fluency as the whole, the easy parts get done, the hard one becomes a stub, a 'simplified version' or a follow-up. This skill anchors delivery to a ledger written before starting…

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