skill-building

A guide for creating Markus skill packages, which are folders of instructions or bundled tools that teach agents how to perform new tasks. It covers the required manifest and documentation files and where to save the package.

In plain words
What is it for?
Use it to build instruction-based skills, package an MCP server when new tools are needed, and create the associated files and manifest.
Why use it?
It explains the package structure and storage location needed for a skill to be recognized and installed correctly.

Skill for Claude CodeCodex

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add skills/markus-global/markus/skill-building
Any agent
npx skills add markus-global/markus --skill skill-building
Clone the repo
git clone --depth 1 https://github.com/markus-global/markus

Made for: Claude Code, Codex.

Per session 19 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,392 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00019 $0.03392
Opus 5 $0.00010 $0.01696
Sonnet 5 $0.00004 $0.00678
Haiku 4.5 $0.00002 $0.00339

Measured 3d ago against content hash 7966475d5834, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

skill-building 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 3d 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.

templates/skills/skill-building/SKILL.md · 257 lines

How it starts

The opening of the file, as written. The whole thing — 257 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Skill Building

This skill teaches you how to create Markus skill packages — directory-based artifacts that teach agents new capabilities. A skill can work in two ways (or both):

  1. Instruction-based: A SKILL.md file with instructions injected into the agent's context, guiding it to use existing tools in new ways.
  2. MCP-based: A bundled MCP server (script) that provides entirely new tools to the agent. The skill directory can contain any scripts, config files, or resources the MCP server needs.

Most skills are instruction-based. Use MCP-based skills when the capability requires new tools that don't exist yet (e.g., connecting to an external API, browser automation, hardware control).

Artifact Directory

CRITICAL: Skill artifacts MUST be saved under this exact path — the Builder page, install system, and deliverable detection all depend on it:

~/.markus/builder-artifacts/skills/{skill-name}/
├── skill.json       # Manifest (auto-created from your JSON output)
├── SKILL.md         # Instruction document (you write via file_write)
├── README.md        # Human-readable documentation (optional)
├── images/          # Skill icon images (optional)
│   └── icon.png     # Skill icon — used in UI after install
└── ...              # Any other files: scripts, MCP servers, configs, templates, etc.

Do NOT write artifacts to ~/.markus/shared/, your working directory, or any other location. Only ~/.markus/builder-artifacts/skills/ is recognized by the system.

A skill directory can contain any files needed for the skill to work — not just SKILL.md and README.md. For example:

  • MCP server scripts (e.g., server.mjs) that provide new tools to the agent
  • Configuration templates or data files
  • Helper scripts used by the instructions

When the user installs the artifact, the entire directory (all files) is deployed to ~/.markus/skills/{skill-name}/. SKILL.md is loaded and injected into the agent's context when the skill is activated. If the manifest declares mcpServers, those servers are started and their tools registered to the agent. skill.json contains metadata used by the skill registry. README.md provides documentation for humans browsing or sharing the skill.

Read the full file on GitHub · 257 lines

Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 3d ago First seen · 257 lines · 19 tokens per session scan A 7966475d5834

Subscribe to this mod's changes

skill-building is a skill published in the GitHub repository markus-global/markus (157 stars, last pushed 6d ago), licensed Apache-2.0. It adds 19 tokens to every session and 3,392 once invoked, about $0.0001 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 2026-08-30.