Getting it into your agent
There is no command for this one: it runs only inside a plugin, and the catalogue could not identify which plugin ships it. The source is linked below.
Wrote 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/orrzxz/houdini21mcp/_guide)<a href="https://agentmods.dev/commands/orrzxz/houdini21mcp/_guide"><img src="https://agentmods.dev/badge/commands/orrzxz/houdini21mcp/_guide.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 5.1 | $0.00000 | $0.06237 |
| Opus 5 | $0.00000 | $0.03119 |
| Sonnet 5 | $0.00000 | $0.01247 |
| Haiku 4.5 | $0.00000 | $0.00624 |
Grade B, and why
_guide scanned grade B with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 6d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Unrestricted tool accessmediumExcessive agency
A wildcard tool grant or "run any command" leaves no least-privilege boundary at all.
Run a script in the script path. Type the script name (with the .cmd extension), followed by any arguments: myscript.cmd hello 15 Run any script file from disk. Use the source command and the filename, followed by any ar How it starts
The opening of the file, as written. The whole thing — 624 lines — stays where its author put it; the contents beside it link to each section on GitHub.
= HScript language guide =
#order: -10
[List of HScript commands|/commands/]
== Variables ==
In HScript, you can assign strings to variables with the set command:
Set a variable:
set x = "hello"
Set a global variable:
set -g x = "hello"
or
`setenv x = "hello"`
Unset a variable:
set -u x
A variable name must begin with letter or an underscore (_), followed by any number of letters, numbers or underscores.
To use a variable in a command, prefix its name with a dollar sign ($):
{{{
set foo = "bar" echo $foo bar }}}
You can optionally enclose the name of the variable in curly braces ({}) to prevent the variable name from running into surrounding text:
{{{
echo ${foo}baz barbaz }}}
In addition, when you use curly braces HScript will expand variable references in the name before looking up its value. This lets you simulate simplistic arrays:
{{{ set foo1 = Padma set foo2 = Mohammed for i = 1 to 2 echo ${foo$i} end Padma Mohammed }}}
In HScript, variables can be local or global (sometimes called system variables).
Local variables are local to the script being run. When the script is finished, the variable disappears. Local variables cannot be used outside the script in which they're defined. To create or set a local variable, use set. The variables created by the for and foreach loops are always local.
Global variables are available to all scripts and to any programs started by Houdini. To create or set a global variable, use setenv or set -g.
=== Variable modifiers === (modifiers)
You can add modifiers to the end of variable names to edit the returned value. These modifiers do not change the value stored in the variable, they only change the value returned by the variable reference with the modifier.
To modify the variable value, add :<<code>> to the end of the variable name. For example:
{{{
set afile = /home/matt/bin/foo.bar echo $afile:e bar echo ${afile:e} bar }}}
The available codes are:
:h:
(Head) The path part of a pathname (that is, the path up to the filename).
{{{
> echo ${afile:h}
/home/matt/bin
}}}
:t:
(Tail) Just the filname part of a pathname.
{{{
> echo ${afile:t}
foo.bar
}}}
:e:
The extension on the end of the filename.
{{{
> echo ${afile:e}
bar
}}}
:r:
(Root) All parts of a pathname except the extension.
{{{
> echo ${afile:r}
/home/matt/bin/foo
}}}
:s/<<ptrn>>/<<repl>>/:
Substitute occurrences of pattern <> with <>.
See the :g and :a modifiers below.
{{{
> echo ${afile:s}/foo/baz/
/home/matt/bin/baz.bar
}}}
:u:
Convert the value to uppercase.
See the :g and :a modifiers below.
{{{
> set str = Hello There
> echo ${str:u}
HELLO THERE
}}}
:l:
Convert the value to lowercase.
See the :g and :a modifiers below.
{{{
> set str = Hello There
> echo ${str:l}
hello there
}}}
Use the following prefixes to modify the behavior of the codes:
:g:
(Global) Treat the string as a whitespace-delimited list of strings, and apply the
following code to each component independently.
:a:
(All) Recursively apply the following code as many times as possible.
For example:
{{{ #!hscript set A = "foo1 foo2 foo3 foofoo4"
$A:u == "Foo1 foo2 foo3 foofoo4" $A:u:u == "FOo1 foo2 foo3 foofoo4" $A:gu == "Foo1 Foo2 Foo3 Foofoo4" $A:gu:u == "FOo1 Foo2 Foo3 Foofoo4" $A:au == "FOO1 FOO2 FOO3 FOOFOO4"
$A:s/foo/bar/ == "bar1 foo2 foo3 foofoo4" $A:s/foo/bar/:s/foo/bar/ == "bar1 bar2 foo3 foofoo4" $A:gs/foo/bar/ == "bar1 bar2 bar3 barfoo4" $A:as/foo/bar/ == "bar1 bar2 bar3 barbar4" }}}
== Put the output of a command in a variable ==
Unlike expression functions, HScript commands are not functions and do not have return values. They just print output to the textport. If you try to assign the result of a command to a variable, as in:
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.
- 6d ago First seen · 624 lines · 0 tokens per session scan B 97eb292b6513
_guide is a command published in the GitHub repository orrzxz/Houdini21MCP (11 stars, last pushed 7mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 6,237 tokens. A static security scan graded it B with 1 finding (unrestricted tool access). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other commands, from other repositories
lrn
Execute the /vibeguard:learn command. $ARGUMENTS.
review
Cold re-quiz on code that already shipped — your own session commits, not the change in front of you.
learn-story-flow
Learn story-flow concepts with interactive guidance for junior developers.
annex-a-deep-dive
Deep dive analysis of ISO 27001 Annex A control domains with implementation guidance.
start-10-1
Command "start-10-1" from minicoohei/ai-agent-camp, covering 🎓 lesson 10-1: clasp基本・gasプロジェクト管理, 📍 このセッションでやること, 🎯 準備チェック, 🚀 step 1: claspのインストールと apps script api の確認 and 🚀 step 2: google認証.
start-13-4.en
Welcome to Lesson 13-4: Landing Page Implementation!