# Passive Review Skill

> Use this skill as an example of a local review-oriented skill that can optionally record minimal usage metadata for later manual review.

- **Type:** Skill
- **Install:** `agentstack add skill-podcast72-agent-skill-starter-kit-passive-review-skill`
- **Verified:** Yes — security-reviewed for prompt injection and unsafe behavior
- **Seller:** [Podcast72](https://agentstack.voostack.com/s/podcast72)
- **Installs:** 0
- **Category:** [Agent Skills](https://agentstack.voostack.com/c/agent-skills)
- **Latest version:** 0.1.0
- **License:** MIT
- **Upstream author:** [Podcast72](https://github.com/Podcast72)
- **Source:** https://github.com/Podcast72/agent-skill-starter-kit/tree/main/examples/passive-review-skill

## Install

```sh
agentstack add skill-podcast72-agent-skill-starter-kit-passive-review-skill
```

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

## About

# Passive Review Skill

## What this skill does

Use this skill when you want a reusable local skill that can keep a small audit trail of usage events without storing sensitive content and without changing itself.

## Activation

Activate this skill when manual review matters more than automation and when logging, if used at all, should stay minimal.

## Scope

- Local skill use only.
- Minimal usage metadata only.
- Manual review only.
- No network access.
- No global configuration changes.
- No automatic self-modification.

## Optional script

`scripts/usage_log_example.py` is an optional example that appends small JSONL entries inside this example folder only.

## Rules

- Logging is optional and must be explicitly allowed by the user.
- Do not store full prompts.
- Do not store secrets, personal data, file contents, or credentials.
- Do not modify the skill automatically.
- Do not make automatic improvement decisions from the log.
- Use the log only to support later manual review.

## Stop rules

- Stop if the request asks for full prompt logging.
- Stop if the request asks for automatic upgrades or self-modification.
- Stop if the task would move logs outside the example folder.
- Stop if the user wants hidden or non-reviewable behavior.

## Final report format

```text
MODE:
TASK:
LOGGING USED:
FILES CHANGED:
VALIDATION:
LIMITS:
STATUS:
```

## Source & license

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

- **Author:** [Podcast72](https://github.com/Podcast72)
- **Source:** [Podcast72/agent-skill-starter-kit](https://github.com/Podcast72/agent-skill-starter-kit)
- **License:** MIT

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-podcast72-agent-skill-starter-kit-passive-review-skill
- Seller: https://agentstack.voostack.com/s/podcast72
- 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%.