📦

ohmg

Name: ohmg
Author: supercent-io

v1.0.0 Content revision r1 High Risk ⚙️ External commands🌐 Network access

Coordinate Multi-Agent Development Workflows

Complex projects need clear handoffs between planning, implementation, QA, and debugging agents. This skill defines a Serena Memory based workflow for coordinating specialized agents and monitoring progress.

Supports: Claude Codex Code(CC)

⚠️ 38 Poor

Stop for confirmation before installing.

Review the plan and obtain explicit user consent before changing files.

Install with my Agent

Copy this request to your Agent. It includes the canonical Skill page and manifest.

Agent request

Review the Skillstore skill "ohmg" from https://skillstore.io/skills/supercent-io-ohmg.md and its manifest at https://skillstore.io/api/skills/supercent-io-ohmg/manifest. Verify the artifact. Stop and obtain explicit user consent before installing or changing files.

Your Agent should still show its plan and request any confirmation required by the security policy.

Agent-readable resources

Use these links when an AI agent, crawler, or script needs clean context instead of reading the full page.

Markdown detail GET /skills/supercent-io-ohmg.md Signed manifest GET /api/skills/supercent-io-ohmg/manifest Signed lockfile GET /api/skills/supercent-io-ohmg/lockfile

Test it

Using "ohmg". Coordinate a new authentication feature.

Expected outcome:

Agent plan with PM requirements, backend API work, frontend form tasks, QA checks, and shared Serena Memory checkpoints.

Using "ohmg". Verify my ohmg setup before a sprint.

Expected outcome:

Checklist covering Bun, uv, oh-my-ag doctor, agent skill installation, CLI mapping, and dashboard readiness.

Using "ohmg". Monitor a stalled multi-agent session.

Expected outcome:

Triage summary showing current agent status, missing handoffs, next owner, and suggested dashboard checks.

Security Audit

High Risk

v4 • 7/7/2026 Open versioned report

The skill documents useful multi-agent coordination workflows, but several examples ask users to run unpinned external CLI commands. I found no prompt injection or credential exfiltration intent, but setup, update, dashboard, and bridge commands require explicit approval and safer pinning.

Files scanned

134

Lines analyzed

Review items

False positives ignored

Confirmed security concerns (1)

High

SKILL.md:49-56 SKILL.md:108-111

Unpinned Remote CLI Execution

The setup and update workflow tells users to run bunx oh-my-ag without a pinned version or integrity check. This can execute changing third-party package code in a project workspace.

The documented commands directly invoke bunx package execution and include an update command. Legitimate use is possible, but the supply-chain risk is clear.

Capability review items (10)

These are real local capabilities that may be expected for this skill, so they require review but are not counted as confirmed malicious behavior.

Medium

SKILL.md:49-51

Ruby/shell backtick execution

```bash

The code block includes bunx oh-my-ag, which can execute an unpinned external package during setup. That is real shell execution from a community skill.

Medium

SKILL.md:55-57

Ruby/shell backtick execution

```bash

The verification block includes bunx oh-my-ag doctor. It invokes external CLI tooling and may execute package code in the user environment.

Medium

SKILL.md:70-73

Ruby/shell backtick execution

```bash

The block shows oh-my-ag agent:spawn with a task argument. It directs the user or agent to run an external CLI command.

Medium

SKILL.md:76-77

Ruby/shell backtick execution

- Terminal: `bunx oh-my-ag dashboard`

The terminal dashboard example runs bunx oh-my-ag dashboard. It invokes external CLI tooling and can start a local monitoring process.

Medium

SKILL.md:77-85

Ruby/shell backtick execution

- Web: `bunx oh-my-ag dashboard:web` (http://localhost:9847)

The web dashboard example runs bunx oh-my-ag dashboard:web and exposes a local HTTP dashboard. This is executable external tooling with network-facing behavior.

Medium

SKILL.md:85-87

Ruby/shell backtick execution

```bash

The code block runs bunx oh-my-ag bridge against a local SSE endpoint. This executes external CLI code and creates a bridge process.

Medium

SKILL.md:108-109

Ruby/shell backtick execution

| `bunx oh-my-ag` | Interactive installer |

The quick reference repeats bunx oh-my-ag as an interactive installer. Running it can execute unpinned external package code.

Medium

SKILL.md:110-111

Ruby/shell backtick execution

| `bunx oh-my-ag doctor` | System check & repair |

The quick reference repeats bunx oh-my-ag doctor. It runs external CLI tooling for system checks and repair.

Medium

SKILL.md:111-112

Ruby/shell backtick execution

| `bunx oh-my-ag update` | Update skills |

The quick reference includes bunx oh-my-ag update. An updater can fetch or modify skill files, so it needs user approval and pinning.

Low

SKILL.md:86

Hardcoded URL

bunx oh-my-ag bridge http://localhost:12341/sse

The bridge command targets a local SSE endpoint and may relay tool traffic through a network protocol. It is localhost-only, so the severity remains low.

Risk Factors

Audited by: codex View Audit History →

Share & cite this report

Share the versioned assessment report, neutral badge, embed card, and citations. Skillstore reports evidence without deciding whether this Skill is safe.

Open versioned report

Copy report link

https://skillstore.io/skills/supercent-io-ohmg/audits/4?utm_source=security_passport&utm_medium=share&utm_campaign=versioned_report

Markdown badge

[![Skillstore security assessment](https://skillstore.io/badges/skills/supercent-io-ohmg/security.svg)](https://skillstore.io/skills/supercent-io-ohmg?utm_source=security_passport_badge)

HTML badge

<a href="https://skillstore.io/skills/supercent-io-ohmg?utm_source=security_passport_badge"><img src="https://skillstore.io/badges/skills/supercent-io-ohmg/security.svg" alt="Skillstore security assessment" loading="lazy"></a>

Embed card

<iframe src="https://skillstore.io/embed/skills/supercent-io-ohmg.html" title="Skillstore Security Assessment" sandbox="allow-popups allow-popups-to-escape-sandbox" loading="lazy" referrerpolicy="no-referrer" width="420" height="180"></iframe>

Academic citations (APA · BibTeX · CFF)

APA citation

supercent-io. (2026). ohmg security audit report (audit version 4) [Author version 1.0.0]. Skillstore. https://skillstore.io/skills/supercent-io-ohmg/audits/4

BibTeX citation

@techreport{supercent-io-supercent-io-ohmg-2026,
  author = {supercent-io},
  title = {ohmg security audit report (audit version 4)},
  institution = {Skillstore},
  year = {2026},
  number = {4},
  url = {https://skillstore.io/skills/supercent-io-ohmg/audits/4},
  note = {Author version 1.0.0}
}

CITATION.cff

cff-version: 1.2.0
message: "If you use this Skill, cite its author and this versioned security audit report."
title: "ohmg security audit report (audit version 4)"
version: "1.0.0"
type: report
authors:
  - name: "supercent-io"
date-released: "2026-07-07"
url: "https://skillstore.io/skills/supercent-io-ohmg/audits/4"
identifiers:
  - type: other
    value: "skillstore:supercent-io-ohmg:audit:4"
    description: "Skillstore immutable audit report identifier"

Skillstore Score

Why this score Evidence Confidence: Medium

Architecture

100

Maintainability

Content

Community

Spec Compliance

What You Can Build

Coordinate Full Stack Delivery

Assign planning, frontend, backend, QA, and debugging work across specialized agents.

Set Up Agent Workflows

Install the oh-my-ag workflow and verify local tools before starting coordinated work.

Monitor Multi-Agent Sessions

Use Serena Memory and dashboards to follow status across active agent tasks.

Try These Prompts

Start Coordination

Use ohmg to coordinate this project: [goal]. Identify the agents needed and the first shared state entries.

Plan Agent Roles

Break down [feature] into PM, frontend, backend, QA, and debug responsibilities using the ohmg workflow.

Configure CLI Mapping

Create a per-agent CLI mapping for a project that uses Codex for backend, Claude for QA, and Gemini for frontend.

Run Observability Review

Review my multi-agent session plan. Include Serena Memory checkpoints, dashboard monitoring, bridge needs, and security concerns.

Best Practices

Review every shell command before execution, especially installer, update, bridge, and dashboard commands.
Keep Serena Memory entries structured so agents can resume work without guessing.
Map each agent to a CLI that matches the task and your account limits.

Avoid

Do not run unpinned package commands in sensitive repositories without approval.
Do not spawn agents before defining shared goals, owners, and completion criteria.
Do not expose bridges or dashboards outside localhost without authentication.

Frequently Asked Questions

What does this skill help me do?

It helps coordinate specialized AI agents for planning, frontend, backend, QA, debugging, and monitoring work.

Does it install agents by itself?

No. It documents commands that can install or update the oh-my-ag workflow when a user approves them.

Which tools does it mention?

It mentions Gemini, Claude, Codex, Claude Code, Bun, uv, Serena Memory, and Google Antigravity.

Does it require network access?

Some documented commands may fetch packages or open local dashboard and bridge endpoints.

Can I use it for a single small task?

Yes, but it is most useful when work spans several domains or agents.

What should I review before use?

Review package commands, local bridge URLs, dashboard access, and changes written under agent or Serena directories.

Developer Details

Author

supercent-io

License

MIT

Author version

v1.0.0

Skillstore revision

Repository

https://github.com/supercent-io/skills-template/tree/main/.agent-skills/ohmg/

Ref

f93e9bb0daca99badb6a7e574b97737155d57cb3

Maintenance freshness

7/18/2026

Usage

8 downloads · 97 views

File structure

📄 SKILL.md

📄 SKILL.toon