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.
npx skills add markus-global/markus --skill claude-codegit clone --depth 1 https://github.com/markus-global/markusWrote 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.
[](https://agentmods.dev/skills/markus-global/markus/claude-code)<a href="https://agentmods.dev/skills/markus-global/markus/claude-code"><img src="https://agentmods.dev/badge/skills/markus-global/markus/claude-code/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/markus-global/markus/claude-code"><img src="https://agentmods.dev/badge/skills/markus-global/markus/claude-code.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 2 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 Excessive Agency · line 24 Skill selects an external model or provider that may use a different account or billing plan than the operator expects. Undisclosed model switches can cause unexpected cost or quota consumption.Fix: Remove the model/provider override or disclose it prominently and require explicit operator approval before invoking an external coding CLI or billed model.
- medium Excessive Agency · line 33 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00023 | $0.02225 |
| Opus 5.5 | $0.00009 | $0.00890 |
| Sonnet 5.5 | $0.00005 | $0.00445 |
| Haiku 4.5 | $0.00002 | $0.00222 |
Grade A, and why
claude-code 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 1mo 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.
How it starts
The opening of the file, as written. The whole thing — 240 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Claude Code
Claude Code (claude binary) is Anthropic's agentic coding CLI. Markus invokes it via invoke_coding_tool({ tool: "claude-code", ... }). Use it for complex, multi-turn coding tasks where deep reasoning and broad file exploration are needed.
Installation
npm install -g @anthropic-ai/claude-code
claude --version
Verify with markus doctor. Requires authentication via one of: ANTHROPIC_API_KEY env var, ANTHROPIC_BASE_URL for custom endpoints, or interactive claude login.
How Markus Invokes Claude Code
Markus runs Claude Code in non-interactive print mode with structured streaming output:
claude --print --output-format stream-json --verbose --max-turns 50 --permission-mode bypassPermissions "<prompt>"
| Flag | Purpose |
|---|---|
--print |
Non-interactive mode — runs to completion without user input |
--output-format stream-json |
Emits structured JSON events for progress parsing |
--verbose |
Detailed progress output |
--max-turns 50 |
Allows up to 50 agent turns for complex tasks |
--permission-mode bypassPermissions |
Auto-approves all file edits and commands — required because --print mode has no interactive stdin for approval prompts |
Additional args can be configured per-deployment via CodingToolConfig.defaultArgs.
Stream-JSON Output
Each stdout line is a JSON event. Key event types:
| Event type | Meaning |
|---|---|
assistant with text content |
Progress message / reasoning summary |
assistant with tool_use |
File edit, shell command, or other tool invocation |
result |
Final outcome with cost and token data |
The result event includes:
result— Final summary textinput_tokens,output_tokens— Token usagecache_read_tokens,cache_write_tokens— Prompt cache statscost_usd— Estimated cost in USD
Markus parses these into progress events (file_edit, progress, completed) and extracts cost reports automatically.
CLAUDE.md Context File
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.
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.
- 1mo ago First seen · 240 lines · 23 tokens per session scan A 4e9a09817b3b
claude-code is a skill published in the GitHub repository markus-global/markus (205 stars, last pushed today), licensed Apache-2.0. It adds 23 tokens to every session and 2,225 once invoked, about $0.0001 per session on Opus 5.5. 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.
Other skills, from other repositories
muse-governance
Governance behavior for Muse agents governed by DashClaw. Teaches the governance protocol over REST: when to call guard, how to interpret allow/warn/block/requireapproval, recording actions and outcomes, plan-first execution with preflight approval, and waiting for human review. Trigger on: governed agent, dashclaw…
openai-whisper-api
Transcribe audio via OpenAI Audio Transcriptions API (Whisper).
ppt-review
Read this skill before the first deck or output quality review, so its criteria are available when the rendered images arrive. Apply the criteria to current officereview structural output and relevant rendered images. Do not use source code, a tool success flag, or the first-slide preview as a substitute for deck…
seo-crawl
Agent-wide core connector rule: when any connected search console is used, discover its operations with listconnectortools and invoke each selected operation through callconnectortool; naming listsites or an analytics operation without the core invocation is not execution.
material-organizer
Organize only the materials the user has already provided or explicitly pointed to. The job is to make messy inputs easier to scan, reuse, archive, or continue from later while preserving source traceability.
swiftui-dev
Use this skill for SwiftUI development, architecture, structure, performance, and Apple native app profiling. It combines.