# Skill Monitor

> >-

- **Type:** Skill
- **Install:** `agentstack add skill-wei63w-skill-monitor-skill-monitor`
- **Verified:** Yes — security-reviewed for prompt injection and unsafe behavior
- **Seller:** [wei63w](https://agentstack.voostack.com/s/wei63w)
- **Installs:** 0
- **Category:** [Agent Skills](https://agentstack.voostack.com/c/agent-skills)
- **Latest version:** 0.1.0
- **License:** MIT
- **Upstream author:** [wei63w](https://github.com/wei63w)
- **Source:** https://github.com/wei63w/skill-monitor/tree/main/skills/skill-monitor
- **Website:** https://skills.sh/wei63w/skill-monitor

## Install

```sh
agentstack add skill-wei63w-skill-monitor-skill-monitor
```

Requires the [AgentStack CLI](https://agentstack.voostack.com/docs/cli). Works with Claude Code, Cursor, and any MCP-compatible agent.

## About

# Skill Monitor

Track skill usage, always-on context bloat, and sub-agent startup cost in the
project-local `data/` directory. Capture is best-effort.

## Quick setup

```bash
node .cursor/skills/skill-monitor/scripts/cli.mjs setup --project . --hooks
node .cursor/skills/skill-monitor/scripts/cli.mjs backfill
node .cursor/skills/skill-monitor/scripts/cli.mjs backfill-tasks
node .cursor/skills/skill-monitor/scripts/cli.mjs analyze --project . --write
node .cursor/skills/skill-monitor/scripts/cli.mjs bloat --project . --snapshot --write
node .cursor/skills/skill-monitor/scripts/cli.mjs analyze-tasks --project . --write
```

`setup --hooks` installs:

- `beforeReadFile` → record `SKILL.md` loads
- `subagentStart` + `preToolUse` (Task) → record sub-agent starts with Rules/AGENTS volume

## Commands

| Command | Purpose |
| --- | --- |
| `setup [--hooks]` | Init `data/`; merge Cursor hooks |
| `record --path ` | Record one skill use |
| `analyze [--write]` | Skill frequency + est. tokens |
| `bloat [--snapshot] [--write]` | Rules / AGENTS.md bloat + budgets |
| `record-task --type ` | Record one Task / sub-agent start |
| `analyze-tasks [--write]` | Startup cost: starts × avg prompt volume |
| `backfill` | Skills from Cursor transcripts |
| `backfill-tasks` | Task/subagent starts from transcripts |
| `reestimate` | Refresh skill `estTokens` |
| `list-skills` / `summary` | Discovery / aggregates |

## Data layout

- `data/events.jsonl` — skill loads (`estTokens`)
- `data/summary.json` — skill aggregates
- `data/tasks.jsonl` — sub-agent starts (`systemPromptTokens`)
- `data/context-snapshots.jsonl` — optional bloat history
- `data/report.md` / `bloat-report.md` / `tasks-report.md`

## Agent workflow

1. Skill stats → `analyze --write`
2. Context inflation → `bloat --snapshot --write`
3. Sub-agent cost → `analyze-tasks --write` (after hooks or `backfill-tasks`)
4. Mention limits: estimates are not provider billing; hooks are strongest in Cursor.

## Manual fallbacks

```bash
node .cursor/skills/skill-monitor/scripts/cli.mjs record --path "C:/path/to/skill/SKILL.md"
node .cursor/skills/skill-monitor/scripts/cli.mjs record-task --type explore --project .
```

## Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

- **Author:** [wei63w](https://github.com/wei63w)
- **Source:** [wei63w/skill-monitor](https://github.com/wei63w/skill-monitor)
- **License:** MIT
- **Homepage:** https://skills.sh/wei63w/skill-monitor

Install and usage instructions live in the source repository linked above.

## Pricing

- **Free** — Free

## Security capabilities

Automated source analysis of v0.1.0 — what this tool can access:

- **Network access:** no
- **Filesystem access:** no
- **Shell / process execution:** no
- **Environment & secrets:** no
- **Dynamic code execution:** no

*"Yes" means the capability is present in the source — more access means more to trust, not that it is unsafe.*


## Versions

- **0.1.0** — security scan: passed — Imported from the upstream source.

## Links

- Listing page: https://agentstack.voostack.com/l/skill-wei63w-skill-monitor-skill-monitor
- Seller: https://agentstack.voostack.com/s/wei63w
- Browse the marketplace: https://agentstack.voostack.com/browse

---
Listed on AgentStack — the marketplace for AI agent skills and MCP servers. Every listing is security-reviewed. Creators keep 70%.