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.
git clone --depth 1 https://github.com/moshcoder/moshcodeWrote 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/commands/moshcoder/moshcode/help)<a href="https://agentmods.dev/commands/moshcoder/moshcode/help"><img src="https://agentmods.dev/badge/commands/moshcoder/moshcode/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/commands/moshcoder/moshcode/help"><img src="https://agentmods.dev/badge/commands/moshcoder/moshcode/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 | $0.00015 | $0.00480 |
| Opus 5.5 | $0.00006 | $0.00192 |
| Sonnet 5.5 | $0.00003 | $0.00096 |
| Haiku 4.5 | $0.00002 | $0.00048 |
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 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.
What it actually says
Task
List what this plugin provides. Do not call any tool — everything needed is below. Render it as a compact table, then the notes.
| command | what it does |
|---|---|
/crypto:report <PAIR> |
the full report — price, technicals, score, supply, order book |
/crypto:quote <PAIR> |
the short answer — latest trade, bid/ask, spread |
/crypto:lookup <name> |
asset name → pair (bitcoin → BTC/USD) |
/crypto:book <PAIR> |
top of the order book, both sides |
/crypto:bars <PAIR> |
historical OHLCV at any supported timeframe |
/crypto:spark <PAIR…> |
recent moves across several pairs, ranked |
/crypto:pairs |
every supported pair, grouped by quote asset |
Notes to pass on
- Pairs are accepted as
BTC,BTC-USD,BTC/USDorBTCUSD. A bare asset resolves to that asset's USD pair. - Every command name is namespaced
/crypto:…. A bare/reportis not a command — Claude Code always prefixes plugin commands with the plugin name. stocks@moshcodeis the sibling plugin, and the four shared names mean the same thing there:/stocks:report,/stocks:quote,/stocks:lookup,/stocks:help. It adds/stocks:signals,/stocks:research,/stocks:listand/stocks:discover— transcript and filing work that has no crypto equivalent.- These are live venue reads, not stored snapshots — the opposite of the stocks plugin. Prices are Alpaca's US crypto venue alone and can differ materially from other exchanges. Crypto trades 24/7: no close, no halt.
- The crypto technical score counts venue-local liquidity, so it is not
comparable to a
/stocks:reportscore. Do not rank the two against each other.
If the user asked for something no command covers, say so rather than improvising one that does not exist.
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 · 40 lines · 15 tokens per session scan A 1e07381e3458
help is a command published in the GitHub repository moshcoder/moshcode (3 stars, last pushed 4d ago), licensed MIT. It adds 15 tokens to every session and 480 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 2026-08-31.
Other commands, from other repositories
deploy
Deploy a program to devnet, or to mainnet after the user's explicit go-ahead.
connect-vybe
Connect and authenticate the Vybe Solana MCP server over OAuth.
audit-strict
Multi-pass consensus audit — runs the audit twice with different prompts, only reports consensus findings. Aggressively cuts false positives.
invariant
Generate Foundry invariant tests for property-based fuzzing. The high-value command for serious teams.
docs-remove
Remove a user-defined source alias from sources.yaml, optionally deleting its cached Markdown.
checklist
Generate a custom checklist for the current feature based on user requirements.