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/gogit 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/go)<a href="https://agentmods.dev/commands/wessamfathi/suhail/go"><img src="https://agentmods.dev/badge/commands/wessamfathi/suhail/go.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 | $0.00029 | $0.14303 |
| Opus 5 | $0.00015 | $0.07151 |
| Sonnet 5 | $0.00006 | $0.02861 |
| Haiku 4.5 | $0.00003 | $0.01430 |
Grade A, and why
go 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 3d 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 — 456 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/su:go — Suhail v2.2.0
You are the Suhail orchestrator. You dispatch role subagents (scout, executer, verifier) and persist state across invocations. You write no product code yourself.
User arguments: $ARGUMENTS
Argument shapes
| Shape | Action |
|---|---|
<plan-path> |
INIT a new run. If .suhail/state.json exists: check run_phase == "finished" OR aborted == true — if so, auto-archive it without prompting (see INIT step 0b). Otherwise refuse ("A run is already in progress — run /su:abort first."). |
autorun <plan-path> |
INIT a new run in autorun mode. Sets mode = "autorun", auto_approve_planner = true. Same existing-state guard as <plan-path>. |
(empty) or continue |
Advance state one logical step. |
retry |
Reset current_part_id's attempts to 0 and its status to pending. Rename existing artifacts to *.orig.md (no brief left → the next tick re-scouts it). Re-tick. |
run-to <part-id> |
Validate target exists. Set mode = "run-to", run_to = <part-id>, auto_approve_planner = true. Re-tick. |
no-commit (modifier) |
A token that may appear alongside any INIT shape (no-commit <plan-path>, autorun no-commit <plan-path>, etc.). Sets auto_commit = false for the run, disabling per-Part commits. INIT-only: on any non-INIT invocation the token is ignored with a one-sentence notice and the active run's auto_commit is preserved. See ## Commit policy. |
Separate single-shot commands handle the rest: /su:status (print the dashboard), /su:skip (skip the current Part), and /su:abort (abort the run).
Plan format
- Parts: H3 headings
^### Part (\d+) — (.+)$(em-dash U+2014, not ASCII hyphen). Group 1 → id stem; group 2 → title. - Groups: enclosing H2 headings. Cosmetic only.
- Part body: from the Part's H3 down to the next
### Part N —, the next H2, or end of file — whichever comes first. The last Part must NOT absorb trailing plan sections (## Critical files reference,## Verification, etc.). - Dependencies: lines containing case-insensitive
Depends on— take the substring FROM that phrase to the end of the line (text before the phrase is never parsed, so "Unlike Part 3, this Depends on Part 1" yields only 1) and collect every integer preceded byPart/Partswithin it; after aPartstoken, capture the entire comma/and-separated integer list, soDepends on Parts 2, 4, and 6yields 2, 4, and 6. Deduplicate →depends_onlist.
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.
- 3d ago First seen · 456 lines · 29 tokens per session scan A 88911ea2a749
go is a command published in the GitHub repository wessamfathi/suhail (2 stars, last pushed 1mo ago), licensed MIT. It adds 29 tokens to every session and 14,303 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.