marketplace-dev

marketplace-dev is a skill for Claude Code from dork-labs/dorkos. It costs 55 tokens per session (4,216 once invoked), scanned A, original, MIT.

A guide for creating, checking, and publishing packages for a coding-agent marketplace. It covers agents, plugins, skill packs, and adapters that can be used by DorkOS or Claude Code.

In plain words
What is it for?
Use it when building a marketplace item, working in the marketplace repository, fixing package validation errors, or publishing a package.
Why use it?
It gives marketplace packages a consistent structure and catches validation problems before submission.

Skill for Claude Code

Written for Claude Code: Claude Code plugin machinery. Also seen: reads .claude/ paths; mentions Claude Code.

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is "source": "./plugins/my-package", // MUST use ./plugins/ prefix.

Part of the flow plugin — 32 skills, 43 commands, 5 agents, 4 hooks shipped together

Good fit Use it when building a marketplace item, working in the marketplace repository, fixing package validation errors, or publishing a package.

Compare 6 skills from other repositories ↓
Install

Getting it into your agent

It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.

Clone the repo
git clone --depth 1 https://github.com/dork-labs/dorkos
agentmods
npx agentmods add skills/dork-labs/dorkos/marketplace-dev

Made for: Claude Code.

Or install flow, the plugin that ships this one along with the rest of its 32 skills, 43 commands, 5 agents, 4 hooks.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for marketplace-dev

README.md
[![agentmods](https://agentmods.dev/badge/skills/dork-labs/dorkos/marketplace-dev.svg)](https://agentmods.dev/skills/dork-labs/dorkos/marketplace-dev)
Your own site
<a href="https://agentmods.dev/skills/dork-labs/dorkos/marketplace-dev"><img src="https://agentmods.dev/badge/skills/dork-labs/dorkos/marketplace-dev.svg" alt="Measured on agentmods" height="20"></a>
Per session 55 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 4,216 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector warn 7 Sept 2026
SkillSpector: 4 findings, up to high

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

  • high Rogue Agent · line 14
    Skill modifies its own code, configuration, or behavior at runtime. Self-modification enables an agent to escalate privileges, disable safety constraints, or install persistent backdoors.
    Fix: Prevent the skill from modifying its own code, SKILL.md, or configuration files. Treat skill files as read-only at runtime.
  • high Rogue Agent · line 272
    Skill modifies its own code, configuration, or behavior at runtime. Self-modification enables an agent to escalate privileges, disable safety constraints, or install persistent backdoors.
    Fix: Prevent the skill from modifying its own code, SKILL.md, or configuration files. Treat skill files as read-only at runtime.
  • medium Prompt Injection · line 261
    Large whitespace padding was detected (a block of blank lines or a long run of spaces). This can push injected instructions below or to the right of the visible area so a human reviewer never sees them while the agent still reads them. Manual review of the hidden content is recommended.
    Fix: Remove the large whitespace padding (blank-line blocks or long space runs) and review any content hidden below or to the right of it. Keep skill files compact and reviewable so no instructions can be
  • medium Rogue Agent · line 272
    Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.
    Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00055 $0.04216
Opus 5 $0.00028 $0.02108
Sonnet 5 $0.00011 $0.00843
Haiku 4.5 $0.00006 $0.00422

Measured 4d ago against content hash 44d51db4bd9c, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

marketplace-dev scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 4d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

.claude/skills/marketplace-dev/SKILL.md · 408 lines

How it starts

The opening of the file, as written. The whole thing — 408 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Marketplace Package Development

Build packages that work for both DorkOS and Claude Code. Every package must pass dorkos package validate before submission.

When to Use

Signal Example Action
Creating a new marketplace item "create a code-review agent for the marketplace" Scaffold with dorkos package init, fill manifest, write skills
Working in the marketplace repo Any work in dork-labs/marketplace Follow same-repo monorepo conventions (ADR-0237)
Building a personal package "I want to make a skill pack for my workflow" Scaffold in ~/.dork/personal-marketplace/packages/
Fixing validation errors dorkos package validate fails Diagnose using issue codes below
Adding to the registry "publish this to the marketplace" Add entries to marketplace.json + dorkos.json sidecar

Package Types

There are exactly 5 types. Choose based on what the package delivers:

Type What It Is Has .claude-plugin/plugin.json? Key Directories
agent Reusable agent definition with persona, skills, tasks No .claude/skills/, .dork/tasks/
plugin Claude Code extension with commands, hooks, UI Yes skills/, hooks/, commands/
skill-pack Bundle of SKILL.md files providing reusable expertise Yes skills/
adapter Integration bridge (relay transport, mesh discovery) Yes .dork/adapters/
shape A "place" composing packages, agents, schedules, and chrome Yes extensions/

Read the full file on GitHub · 408 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 4d ago First seen · 408 lines · 55 tokens per session scan A 44d51db4bd9c

Subscribe to this mod's changes

marketplace-dev is a skill published in the GitHub repository dork-labs/dorkos (9 stars, last pushed today), licensed MIT. It adds 55 tokens to every session and 4,216 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.