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/autogit 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/auto)<a href="https://agentmods.dev/commands/wessamfathi/suhail/auto"><img src="https://agentmods.dev/badge/commands/wessamfathi/suhail/auto.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 | $0.00015 | $0.00813 |
| Opus 5 | $0.00008 | $0.00407 |
| Sonnet 5 | $0.00003 | $0.00163 |
| Haiku 4.5 | $0.00002 | $0.00081 |
Grade A, and why
auto 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 — 59 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/su:auto — Suhail auto-runner
You are running the most recent Suhail plan in autorun mode. If a plan path is supplied as $ARGUMENTS, use it directly. Otherwise scan .suhail/plans/ for candidate plans and ask the user which one to run.
On every invocation
If $ARGUMENTS is non-empty
Treat $ARGUMENTS as the explicit plan path. Skip the auto-detection section entirely and jump to Locating go.md below, using $ARGUMENTS as <plan-path>.
Auto-detection (only when $ARGUMENTS is empty)
- Scan
.suhail/plans/for files matching*.md, sorted by last-modified descending. If the directory does not exist, treat it as empty. - Branch on the number of results:
- None found — end with: "No plans found in
.suhail/plans/— run/su:discoverto draft one or pass a plan path directly." - One found — present an AskUserQuestion:
- Prompt: "Found one plan:
<filename>. Run it in autorun mode?" - Options: "Yes", "Pick a different plan", "Cancel"
- If Yes: proceed to Locating
go.mdwith that plan's path. - If Pick a different plan: ask the user to type a path, then proceed to Locating
go.mdwith the typed path. - If Cancel: end with: "Cancelled."
- Prompt: "Found one plan:
- Multiple found — present an AskUserQuestion:
- Prompt: "Select a plan to run in autorun mode:"
- Options: the 3 most recent filenames (basenames), plus "Other (type a path)"
- If a filename is selected: proceed to Locating
go.mdwith the full path for that file. - If Other (type a path): ask the user to type a path, then proceed to Locating
go.mdwith the typed path.
- None found — end with: "No plans found in
Locating go.md
Check these paths in order:
- Plugin install:
${CLAUDE_PLUGIN_ROOT}/commands/go.md— resolves only when installed as a Claude Code plugin (token substituted inline before this file is read); otherwise the token is left literal and the path will not exist, so it falls through. - The same directory as this command file (sibling).
- Project install:
<repo>/.claude/commands/go.md. - User install:
~/.claude/commands/go.md.
- Project install:
- If no path is found, end with: "Cannot locate
go.md— reinstall Suhail."
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 · 59 lines · 15 tokens per session scan A 40d77aa259ff
auto is a command published in the GitHub repository wessamfathi/suhail (2 stars, last pushed 1mo ago), licensed MIT. It adds 15 tokens to every session and 813 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.
skill-inbox
Unified entry point for managing skill suggestions and browsing all installed skills. Provides two views: suggestions (default) and all skills.
eval-merge
Use the Read tool to load .skill-compass/{skill-name}/manifest.json. Verify.
cti-report
Render case deliverables — relationship graph (PNG/SVG/Mermaid) and a polished PDF/DOCX assessment. Usage: /cti-report [--graph|--pdf].
cti-status
Health check — backend tier, case store, MCP tools, API credit balances. Run this when something behaves oddly. Usage: /cti-status.
send
Send a message to a peer session.