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 BrentFarris/echo --skill create-slash-commandgit clone --depth 1 https://github.com/BrentFarris/echoWrote 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/brentfarris/echo/create-slash-command)<a href="https://agentmods.dev/skills/brentfarris/echo/create-slash-command"><img src="https://agentmods.dev/badge/skills/brentfarris/echo/create-slash-command/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/brentfarris/echo/create-slash-command"><img src="https://agentmods.dev/badge/skills/brentfarris/echo/create-slash-command.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 | $0.00043 | $0.03088 |
| Opus 5.5 | $0.00017 | $0.01235 |
| Sonnet 5.5 | $0.00009 | $0.00618 |
| Haiku 4.5 | $0.00004 | $0.00309 |
Grade A, and why
create-slash-command 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 12d 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 — 186 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Create an Echo slash command
Use an existing tool or app when it already does the requested work. Generate a plugin only when the command needs new behavior. A slash command is an owner-defined shortcut saved on an Echo machine; adding a skill or plugin file does not register a command.
Workflow
- Identify the machine that owns the command and, for plugin/app actions, the selected or fixed bot. Commands belong to that machine's profile and are shared across its browsers. Chat suggestions follow the selected bot's machine, with the chat's home machine as fallback. Settings has its own machine selector. Remote machines must advertise
slash-commands/1. - Read existing commands and the destination catalog through the owner API, or inspect Settings → General → Slash commands. Reuse actual plugin, tool, view, feature, and bot IDs from that machine. The catalog includes tool parameter schemas and
unavailablereasons; disabled or pending plugins can still appear. - Choose
text,plugin, orappusing the complete options below. For a new plugin, read Plugin generation examples, obtainplugin_template, install the package, then register the command separately. - Create or edit the definition in Settings, or use the owner API below when an authorized owner session is available. Echo currently exposes no
slash_command_savemodel tool.plugin_installinstalls packages, not commands. Do not invent a tool, write the private settings database, or describe a prepared definition as already registered. - Verify the saved definition and exercise its intended behavior. Invoking a plugin command executes its tool immediately, so use suitable sample arguments and the intended bot. Report the command name, owning machine, action, and any remaining registration or package-approval step.
Complete command options
Create/update JSON has this shape: {"name":"review","description":"Review the draft","action":{...}}.
| Field | Type | Rules and defaults |
|---|---|---|
name |
string, required | Enter without /. Trimmed and lowercased on save. Pattern ^[a-zA-Z][a-zA-Z0-9_-]{0,63}$: starts with a letter, at most 64 ASCII characters, then letters/digits/_/-. Unique ignoring case, including names of removed built-ins. |
description |
string, optional | Human-readable suggestion text; trimmed; at most 1,000 UTF-8 bytes on the server. Empty is allowed. |
action |
object, required | Exactly one of the action types below. Saving retains only the fields relevant to that type. |
id |
string, server-managed | Generated on create. Update/delete by this ID in the URL, not by the slash name. A body id does not select the command to update. |
builtin |
boolean, server-managed | Custom saves always set false; clients cannot create a built-in this way. |
enabled |
boolean, server-managed | Custom saves always set true. There is no custom disable toggle; delete custom commands. Removed built-ins remain listed with false and can be restored. |
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.
- 12d ago First seen · 186 lines · 43 tokens per session scan A d5ceb16e619f
create-slash-command is a skill published in the GitHub repository BrentFarris/echo (12 stars, last pushed 9d ago), licensed MIT. It adds 43 tokens to every session and 3,088 once invoked, about $0.0002 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 2026-11-04.
create-slash-command compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| create-slash-commandBrentFarris/echo | Skill | 12 | 9d ago | MIT | A | 43 | Claude Code, Codex |
| claude_code_delegationsiddsachar/row-bot | Skill | 1.7k | today | Apache-2.0 | A | 31 | Claude Code, Codex |
| developer_codingsiddsachar/row-bot | Skill | 1.7k | today | Apache-2.0 | A | 17 | Claude Code, Codex |
| code-runnerxyva-yuangui/XyvaClaw | Skill | 21 | 3mo ago | MIT | A | 65 | Claude Code, Codex |
| add-resendnanocoai/nanoclaw | Skill | 31k | today | MIT | A | 16 | Claude Code |
| add-macos-statusbarnanocoai/nanoclaw | Skill | 31k | today | MIT | A | 49 | Claude Code |
| Cortexdanielmiessler/LifeOS | Skill | 20k | 10d ago | MIT | A | 184 | Claude Code |