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 agentmods add commands/mangrovetechnologies/mangrove-agent/helpgit clone --depth 1 https://github.com/MangroveTechnologies/mangrove-agentWrote 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/mangrovetechnologies/mangrove-agent/help)<a href="https://agentmods.dev/commands/mangrovetechnologies/mangrove-agent/help"><img src="https://agentmods.dev/badge/commands/mangrovetechnologies/mangrove-agent/help.svg" alt="Measured on agentmods" 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 | $0.00008 | $0.00125 |
| Opus 5 | $0.00004 | $0.00063 |
| Sonnet 5 | $0.00002 | $0.00025 |
| Haiku 4.5 | $0.00001 | $0.00013 |
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 4d 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
Help
Display all available commands and their descriptions.
Steps
- List all commands in the plugin's
commands/directory - Present them in a formatted table:
| Command | Description |
|---|---|
| /help | Show this help message |
- Include a note about the MCP tools available via the server:
"This app also exposes MCP tools. Use the tool discovery endpoint at
/api/v1/docs/toolsto see all available tools, or connect directly via MCP at/mcp."
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.
- 4d ago First seen · 22 lines · 8 tokens per session scan A 6982da641365
help is a command published in the GitHub repository MangroveTechnologies/mangrove-agent (5 stars, last pushed 1mo ago), licensed MIT. It adds 8 tokens to every session and 125 once invoked, about $0.0000 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 2026-08-31.
Other commands, from other repositories
checkpoint
Create a checkpoint by staging the changes you have made using git. usage: git [-v | --version] [-h | --help] [-C ] [-c = ] [--exec-path[= ]] [--html-path] [--man-path] [--info-path] [-p | --paginate | -P | --no-pager] [--no-replace-objects] [--bare] [--git-dir= ] [--work-tree= ] [--namespace= ] [--super-prefix= ]…
os-meeting
快速创建和管理AI团队会议.
spec-intake
Execute the canonical workflow: .agent/workflows/spec-intake.md.
test
Execute the canonical workflow: .agent/workflows/test.md.
check-chain
Verify that the tastytrade option chain and delta-based strike selection are working for the relevant trading session, for every symbol in config.json's symbols list. Tests today's expiration if before 16:00 ET on a trading day; otherwise tests the next trading day. Repeat Steps 2–4 below once per symbol; report one…
mesh
Show what the mesh can do right now — discover live capabilities and this agent's MESH balance.