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 d-gangz/dgang-skills --skill helpgit clone --depth 1 https://github.com/d-gangz/dgang-skillsWrote 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/d-gangz/dgang-skills/help)<a href="https://agentmods.dev/skills/d-gangz/dgang-skills/help"><img src="https://agentmods.dev/badge/skills/d-gangz/dgang-skills/help/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/d-gangz/dgang-skills/help"><img src="https://agentmods.dev/badge/skills/d-gangz/dgang-skills/help.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00093 | $0.00939 |
| Opus 5 | $0.00046 | $0.00469 |
| Sonnet 5 | $0.00019 | $0.00188 |
| Haiku 4.5 | $0.00009 | $0.00094 |
Grade B, and why
help scanned grade B with 1 finding 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 11d 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.
Asks for rootmediumPrivilege escalation
A mod that escalates privileges can change anything on the machine, not only the project.
- **UAC / sudo / password prompts** that interactive installers trigger — these hang Bash, so hand the command to the user when one is imminent How it starts
The opening of the file, as written. The whole thing — 64 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Help Skill
You help non-technical users get Claude Code set up and configured. Your goal is the best possible UX for the user — which means doing as much yourself as possible rather than handing them a wall of instructions to follow.
Core principle: do, don't delegate
For each step in any procedure, ask: can I do this via Bash, Read, Edit, or WebFetch? If yes, do it. Only hand the user something to type if they have to type it themselves.
The user genuinely has to do these — everything else, you do:
- Type slash commands inside Claude Code (
/plugin,/mcp,/reload-plugins, etc.) — only the user can type into the Claude Code prompt - Restart Claude Code (
/exit, thenclaude) - Browser OAuth flows (the auth handshake itself; you can still set up everything around it)
- UAC / sudo / password prompts that interactive installers trigger — these hang Bash, so hand the command to the user when one is imminent
- Keyboard shortcuts in the Claude Code TUI (Tab, arrow keys, Alt+V to paste images, etc.)
- Run interactive CLIs in a separate terminal (e.g.
npx skills addis interactive — Claude Code's Bash tool can't drive interactive prompts)
When you do hand something off, give the user one clear command to copy-paste, not a multi-step walkthrough they have to translate.
Decisions: ask, don't assume
When a step needs a user decision, use the AskUserQuestion tool — never plain text questions. The most common decision across these references is scope (user-level vs project-level for MCPs, plugins, skills). Confirm scope before acting; the wrong scope is invisible and frustrating to undo.
Topics
| User needs help with... | Reference | Default mode |
|---|---|---|
| Setting up MCP servers | references/mcp-setup.md |
Agent does it via Bash / file edits |
| Installing plugins | references/plugins.md |
User runs slash commands; agent guides |
| Finding and installing skills via skills.sh | references/skills-sh.md |
User runs interactive CLI; agent guides |
| Creating a hook | references/hooks-creation.md |
Agent scaffolds, verifies, hands off |
| User-level vs project-level configuration | references/configuration-scopes.md |
Agent decision guide; confirm scope with user |
| Windows-specific issues | references/windows-troubleshooting.md |
Agent diagnoses + fixes via Bash; hands off only when forced to |
What ships with it
7 files 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.
- 11d ago First seen · 64 lines · 93 tokens per session scan B 400f19a07696
help is a skill published in the GitHub repository d-gangz/dgang-skills (2 stars, last pushed 2mo ago), licensed MIT. It adds 93 tokens to every session and 939 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it B with 1 finding (asks for root). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
orbit-notion
Open Orbit briefing skill — selected by the Orbit pipeline when Notion is the user's only connected connector, or when the user explicitly scopes their daily digest to Notion. Pulls the past 24 hours of document edits, comments, mentions, and database row changes from the user's authenticated Notion connection and…
Cortex
Operate Cortex, the LifeOS memory system — the typed Knowledge Archive (People, Companies, Ideas, Research with typed related: links) plus recall of prior work sessions, ISAs, and conversations. Search, add, harvest, develop, ingest, distill, graph-navigate, recall. USE WHEN cortex, knowledge, knowledge base, search…
pinchtab-mcp
Use this skill when a task requires browser automation through PinchTab's MCP server connected to a remote browser instance. Covers navigation, element interaction, data extraction, form filling, multi-step flows, and session management via MCP tools.
feishu
Work with Feishu or Lark bots, docs, sheets, bitables, approval flows, and OpenAPI/MCP setup without hardcoding credentials.
peekaboo
Capture and automate macOS UI with the Peekaboo CLI.
mochi-remind
Handle due reminders — notify the user with natural language and mark them done.