# Planr Investigate

> Diagnose a bug, regression, error, or unexplained behavior and optionally implement a bounded fix. Use for root-cause investigation, not planned feature delivery.

- **Type:** Skill
- **Install:** `agentstack add skill-openplanr-openplanr-planr-investigate`
- **Verified:** Yes — security-reviewed for prompt injection and unsafe behavior
- **Seller:** [openplanr](https://agentstack.voostack.com/s/openplanr)
- **Installs:** 0
- **Category:** [Developer Tools](https://agentstack.voostack.com/c/developer-tools)
- **Latest version:** 0.1.0
- **License:** MIT
- **Upstream author:** [openplanr](https://github.com/openplanr)
- **Source:** https://github.com/openplanr/OpenPlanr/tree/main/skills/planr-investigate
- **Website:** https://openplanr.dev

## Install

```sh
agentstack add skill-openplanr-openplanr-planr-investigate
```

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

## About

# Planr Investigate

Find the cause before proposing a fix. Use the request, repository, runtime output, and focused
experiments as context. Keep the investigation lightweight and make every diagnostic useful to
the requested outcome.

## Investigate

1. Restate the observed failure and the smallest reproducible case.
2. Trace the relevant call path, state, configuration, and recent changes.
3. Form competing hypotheses and run the cheapest discriminating checks first.
4. Identify the root cause only when the observations distinguish it from plausible alternatives.
5. Report exact errors and unavailable tools without prescribing a workflow ceremony.

## Fix when requested

When the user asked for a fix, implement the smallest coherent correction within the requested
repository and run focused regression checks. Preserve unrelated work. Ask only when a missing
product decision or an irreversible external action genuinely blocks progress.

## Return

- **Cause:** established root cause, or the strongest remaining hypotheses.
- **Change:** files and behavior changed, or none for diagnosis-only work.
- **Checks:** commands and results.
- **Issues:** unresolved uncertainty or blocker, or none.

## Source & license

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

- **Author:** [openplanr](https://github.com/openplanr)
- **Source:** [openplanr/OpenPlanr](https://github.com/openplanr/OpenPlanr)
- **License:** MIT
- **Homepage:** https://openplanr.dev

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-openplanr-openplanr-planr-investigate
- Seller: https://agentstack.voostack.com/s/openplanr
- 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%.