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/wessamfathi/suhail/discovergit clone --depth 1 https://github.com/wessamfathi/suhailWrote 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/wessamfathi/suhail/discover)<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>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 | $0.00028 | $0.05513 |
| Opus 5 | $0.00014 | $0.02756 |
| Sonnet 5 | $0.00006 | $0.01103 |
| Haiku 4.5 | $0.00003 | $0.00551 |
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.
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.
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.
- today Changed · -6 lines 9834cd9f7f98
- 4d ago First seen · 370 lines · 28 tokens per session scan A 44cd06fd8b73
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.
Other commands, from other repositories
better-auth:add-plugin
Add a better-auth plugin to an existing project. Configures server and client plugins with proper imports.
better-auth:setup
Interactive setup wizard for better-auth authentication. Guides through database, framework, OAuth providers, and plugin configuration.
bun:migrate
Migrate existing Node.js/npm projects to Bun.
send
Send a message to a peer session.
reskin
Extract a measured design signature (type ramp, accent + its budget, grid unit, radius, layout) from a reference image or site, write it to signature.json, and drive the build to match it — "steal this vibe" as a spec, not pixels.
wf-statusline
Set up a lightweight, artifact-only workflow progress statusline.