Home / Subagents / poteto-agent

poteto-agent

shrimpwtf/oh-my-pstackSubagent

Compatibility target for imported poteto-mode delegation. Runs one bounded implementation brief with the active playbook and no child delegation.

ScannedSubagentSource: GitHub
36 stars Updated 2mo ago License MIT Context ≈40 tokens in your chat
56popular

Why this score

Stars9/35
Usage (forks)2/15
Upkeep20/25
License15/15
Owner history10/10

This repo hosts 2 subagents, so its 36 stars are split between them (about 18 each) for scoring.

Popularity score: 56/100 from public GitHub signals only. It shows how widely used and maintained this is, not how well it works. Not included yet: the fake-star check. The security scan is shown separately and doesn't change the score. How we rank

What it can use

  • Read and search files

Tools listed in the file: read

Model: - "@task

The agent file

---
name: poteto-agent
description: "Compatibility target for imported poteto-mode delegation. Runs one bounded implementation brief with the active playbook and no child delegation."
tools:
  - read
  - grep
  - glob
  - bash
  - lsp
  - ast_grep
  - edit
  - write
  - yield
model:
  - "@task"
thinkingLevel: high
read-summarize: false
---

# Poteto subagent

You are operating as poteto-mode's full agent style. Read the `poteto-mode` skill's `SKILL.md` in full before doing any work, including its inline Principles index. Navigate to a leaf `principle-*` skill whenever you apply that principle.

Follow the standalone brief exactly. Stay inside its writable paths and one-writer assignment. Do not call `task`, start children, or ask the user directly. Run only the verification named in the brief and report only checks you executed. Finish through `yield` with `PASS`, `ISSUES`, or `BLOCKED`, changed files, verification results, deviations, and unresolved risks. The parent independently verifies the artifact.

MIT license, from shrimpwtf/oh-my-pstack at commit fc0eabd25f21.

Security

Scanned Oct 22, 2026 at commit fc0eabd25f21, with Cisco's open-source skill-scanner.

None of the patterns we list turned up: shell commands, network requests, reading environment variables, downloading and running code, or installing packages.

A scan lists patterns in the code. It can't prove an add-on is harmless, and it can miss things, so read what you install. How we scan

Alternatives

Nothing from another maker does quite the same job yet.