su

su is a skill for Claude Code, Codex from wessamfathi/suhail. It costs 46 tokens per session (640 once invoked), scanned A, original, MIT.

A routing skill for Suhail that sends named jobs such as `init`, `discover`, or `status` to their matching command instructions.

In plain words
What is it for?
Use it to start, inspect, continue, skip, automate, or stop Suhail jobs, or to see the available job names when none is specified.
Why use it?
It gives one front desk for several jobs, so the user does not need to remember which command file handles each one.

Skill for Claude CodeCodex

Installs and runs on its own, but its text points at files inside its plugin — anything it tells you to read at a ${CLAUDE_PLUGIN_ROOT} path is only there once the plugin is installed. Installing the plugin gets both.

Part of the su plugin — 1 skill, 8 commands, 5 agents shipped together

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/wessamfathi/suhail/su
Any agent
npx skills add wessamfathi/suhail --skill su
Clone the repo
git clone --depth 1 https://github.com/wessamfathi/suhail

Made for: Claude Code, Codex.

Or install su, the plugin that ships this one along with the rest of its 1 skill, 8 commands, 5 agents.

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.

agentmods badge for su

README.md
[![agentmods](https://agentmods.dev/badge/skills/wessamfathi/suhail/su.svg)](https://agentmods.dev/skills/wessamfathi/suhail/su)
Your own site
<a href="https://agentmods.dev/skills/wessamfathi/suhail/su"><img src="https://agentmods.dev/badge/skills/wessamfathi/suhail/su.svg" alt="Measured on agentmods" height="20"></a>
Per session 46 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 640 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00046 $0.00640
Opus 5 $0.00023 $0.00320
Sonnet 5 $0.00009 $0.00128
Haiku 4.5 $0.00005 $0.00064

Measured 5d ago against content hash 6701c1aed707, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

su 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 5d 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.

skills/su/SKILL.md · 45 lines

How it starts

The opening of the file, as written. The whole thing — 45 lines — stays where its author put it; the contents beside it link to each section on GitHub.

su — Suhail front desk

This skill is a pure router: it locates and defers to the matching commands/<job>.md, and never restates or advances the orchestrator's own state machine.

1. Argument routing

If $ARGUMENTS is non-empty, or the user's message plainly names a job, take the first token and match it case-insensitively against the eight job names: go, init, discover, next, auto, skip, status, abort.

On a match: locate the corresponding command file (see "Locating the command file" below), read it into memory, and follow its instructions exactly as if the user had invoked /su:<job> directly — passing any remaining tokens through as that command's own arguments.

On no match: state so in one sentence and list the eight job names. Do not proceed further.

Do not infer a job from vague conversational context — only a non-empty $ARGUMENTS or an unambiguous, plainly-named job triggers routing. If neither is present, proceed to the menu below instead.

2. Locating the command file

Given a job name, resolve commands/<job>.md by checking these two paths in order:

  1. Plugin install: ${CLAUDE_PLUGIN_ROOT}/commands/<job>.md — this resolves only when Suhail is installed as a Claude Code plugin, because the token is substituted inline before this file is read; in a non-plugin context the token stays literal and the path will not exist, so resolution falls through to the next step.
  2. Dev repo: ./commands/<job>.md.

If neither path exists, end with: "Cannot locate commands/<job>.md — reinstall Suhail."

Do not duplicate or summarize the orchestrator logic here. The canonical state machine lives in commands/go.md.

3. Menu

When no job is named, ask a single AskUserQuestion with header "Job", single-select, and exactly these four options:

  • Run plan → route to go (then ask for the plan path via go's own flow).
  • Discover plan → route to discover.
  • Init intel → route to init.
  • Status → route to status.

Read the full file on GitHub · 45 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.

  1. 5d ago First seen · 45 lines · 46 tokens per session scan A 6701c1aed707

Subscribe to this mod's changes

su is a skill published in the GitHub repository wessamfathi/suhail (2 stars, last pushed 3d ago), licensed MIT. It adds 46 tokens to every session and 640 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 2026-08-31.