A help command that shows the commands currently available to the user. It works in a command-line tool, web chat, or messaging apps.

It is for answering requests such as /help, /commands, or “what commands can I use?” with a readable list.

It avoids outdated help text by fetching the current command list whenever someone asks for help.

help — Skill by crisandrews

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/crisandrews/clawcode/help

Any agent

npx skills add crisandrews/ClawCode --skill help

Clone the repo

git clone --depth 1 https://github.com/crisandrews/ClawCode

Made for: Claude Code, Codex.

Per session 41 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 589 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.

Model	Per session	Once invoked
Fable 5	$0.00041	$0.00589
Opus 5	$0.00020	$0.00295
Sonnet 5	$0.00008	$0.00118
Haiku 4.5	$0.00004	$0.00059

Measured yesterday against content hash a35d8da07092, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

help 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 yesterday.

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.

skills/help/SKILL.md · 51 lines

How it starts

The opening of the file, as written. The whole thing — 51 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Help — list commands

Show a concise, LIVE list of all available commands. Never hardcode — always pull from the list_commands MCP tool so recently installed or removed skills are reflected.

Steps

Detect the surface. If the incoming message has a <channel source="..."> marker, you're on a messaging channel. Otherwise you're on CLI or WebChat.
Call list_commands with the right format:
- CLI / WebChat: list_commands({ format: "table", includeTools: false }) — grouped markdown, readable.
- Messaging (WhatsApp, Telegram, Discord, iMessage): list_commands({ format: "compact", includeTools: false }) — one line per command, mobile-friendly.
Leave includeTools: false for the user-facing help — MCP tools are agent-invoked, not user-typed. Users who want the internals can ask "what MCP tools do you have?" and you call with includeTools: true.
Print the output from the tool as-is. Do not rewrite or reorder.
Adapt formatting to the channel after the tool output:
- WhatsApp: strip **bold** → *bold*, remove markdown headers if too noisy
- Telegram: keep **bold** or convert to HTML
- Discord: markdown as-is
- iMessage: strip markdown to plain text
- CLI / WebChat: markdown as-is

Append a short native-tools note at the end (only on CLI):

Native Claude Code commands (CLI only): /status /usage /cost /compact /clear /mcp /model /help

Example flows

CLI user asks `/help`

Call list_commands({ format: "table", includeTools: false }). Print the returned markdown. Append the native-tools note.

WhatsApp user says "what can you do?"

Call list_commands({ format: "compact", includeTools: false }). Convert any **bold** to *bold*. Don't include the native-tools note (doesn't apply).

Notes

/help and /commands are aliases.
Keep the response short on mobile channels. compact format handles that.
If the user wants the internals ("tools", "MCP"), call with includeTools: true so they see them too.
If nothing comes back, something's wrong with the install — suggest /agent:doctor.

Read the full file on GitHub · 51 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.

yesterday First seen · 51 lines · 41 tokens per session scan A a35d8da07092

Subscribe to this mod's changes

help is a skill published in the GitHub repository crisandrews/ClawCode (62 stars, last pushed 2d ago), licensed MIT. It adds 41 tokens to every session and 589 once invoked, about $0.0002 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.

Memory and context ai-agent autonomous-agent claude claude-code claude-code-plugin dreaming

proof-checker

Rigorous mathematical proof verification and fixing workflow. Reads a LaTeX proof, identifies gaps via cross-model review (external reviewer backend, ultra reasoning), fixes each gap with full derivations, re-reviews, and generates an audit report. Use when user says "检查证明", "verify proof", "proof check", "审证明"…

wanshuiyin/Auto-claude-code-research-in-sleep · 87 tokens

citation-audit

Zero-context verification that every bibliographic entry in the paper is real, correctly attributed, and used in a context the cited paper actually supports — catching hallucinated authors, wrong years, fabricated venues, version mismatches, and wrong-context citations. Use when user says "审查引用", "check citations"…

wanshuiyin/Auto-claude-code-research-in-sleep · 86 tokens

idea-creator

Generate and rank research ideas given a broad direction. Use when user says "找idea", "brainstorm ideas", "generate research ideas", "what can we work on", or wants to explore a research area for publishable directions.

wanshuiyin/Auto-claude-code-research-in-sleep · 51 tokens

paper-illustration

Generate publication-quality AI illustrations for academic papers using Gemini image generation. Creates architecture diagrams, method illustrations with Claude-supervised iterative refinement loop. Use when user says "生成图表", "画架构图", "AI绘图", "paper illustration", "generate diagram", or needs visual figures for papers.

wanshuiyin/Auto-claude-code-research-in-sleep · 67 tokens

idea-discovery

Workflow 1: Full idea discovery pipeline to go from a broad research direction to validated, pilot-tested ideas. Use when user says "找idea全流程", "idea discovery pipeline", "从零开始找方向", or wants the complete idea exploration workflow.

wanshuiyin/Auto-claude-code-research-in-sleep · 56 tokens

paper-illustration-image2

Generate publication-quality academic illustrations through a local Codex app-server bridge that uses Codex native image generation. This is a separate experimental alternative to paper-illustration, intended for Claude Code users who want a GPT-image-style renderer without modifying the original skill.

wanshuiyin/Auto-claude-code-research-in-sleep · 59 tokens