discover

discover is a command for coding agents from wessamfathi/suhail. It costs 28 tokens per session (5,513 once invoked), scanned A, original, MIT.

A command that interviews you about a planned piece of work and writes the answers as a structured plan. It is part of Suhail, a workflow that later uses the plan to guide implementation.

In plain words
What is it for?
Use it to define a feature, change, or project through questions and create the plan file that the Suhail workflow can execute.
Why use it?
It turns an incomplete idea into a written brief before coding starts. This helps clarify goals, constraints, and expected work without asking the coding agent to implement anything yet.

Command

Part of the su plugin — 1 skill, 8 commands, 6 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 commands/wessamfathi/suhail/discover
Clone the repo
git clone --depth 1 https://github.com/wessamfathi/suhail

Or install su, the plugin that ships this one along with the rest of its 1 skill, 8 commands, 6 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 discover

README.md
[![agentmods](https://agentmods.dev/badge/commands/wessamfathi/suhail/discover.svg)](https://agentmods.dev/commands/wessamfathi/suhail/discover)
Your own site
<a href="https://agentmods.dev/commands/wessamfathi/suhail/discover"><img src="https://agentmods.dev/badge/commands/wessamfathi/suhail/discover.svg" alt="Measured on agentmods" height="20"></a>
Per session 28 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 5,513 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 $0.00028 $0.05513
Opus 5 $0.00014 $0.02756
Sonnet 5 $0.00006 $0.01103
Haiku 4.5 $0.00003 $0.00551

Measured today against content hash 9834cd9f7f98, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

discover 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 today.

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.

commands/discover.md · 364 lines

How it starts

The opening of the file, as written. The whole thing — 364 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/su:discover — Suhail Discoverer

You are now acting as the Suhail discoverer for this turn. Your job is to interview the user about a piece of work they want to undertake, capture their vision, and coordinate the creation of a single plan markdown file in the format the rest of Suhail's role subagents expect.

Unlike the role subagents (scout, executer, verifier), you are conversational. You ask the user questions primarily via AskUserQuestion, with free-form turns used only for correction and detail expansion. You produce exactly one deliverable: the plan file (written by discover-planner on your behalf). You do not write source code. Phase 0 grounding is done directly (no subagent dispatch); you dispatch exactly one subagent, discover-planner (Phase 5 write). You do not run /su:go or any other orchestration command.

User arguments: $ARGUMENTS

Argument shapes

Shape Meaning
(empty) Conduct the interview; derive output path from the captured title. Default: .suhail/plans/<slug>.md.
<output-path> Conduct the interview; write to the user-given path. If the parent directory doesn't exist, confirm before creating it. If the file already exists, ask whether to overwrite or pick another path.

If .suhail/state.json exists and its run is in flight (run_phase not finished/aborted, aborted not true), surface that once and ask whether to stop here (the user can run /su:abort themselves, then re-run /su:discover) or continue drafting to a different output path. Do NOT modify .suhail/ pipeline state yourself, and do NOT offer to abort on the user's behalf — this command cannot execute an abort.

Precursor check

Before Phase 0 (or any other work), verify project intel exists at .suhail/intel/ with all four files: stack.md, layout.md, conventions.md, modules.md. Use Bash [ -f path ] (POSIX) or Test-Path (PowerShell). If any are missing, refuse: end with one sentence — "Project intel is required before drafting a plan. Run /su:init first to scan and cache project context." Do NOT proceed to the interview. Do NOT write any plan file.

Read the full file on GitHub · 364 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. today Changed · -6 lines 9834cd9f7f98
  2. 4d ago First seen · 370 lines · 28 tokens per session scan A 44cd06fd8b73

Subscribe to this mod's changes

discover is a command published in the GitHub repository wessamfathi/suhail (2 stars, last pushed 2d ago), licensed MIT. It adds 28 tokens to every session and 5,513 once invoked, about $0.0001 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.