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/initgit clone --depth 1 https://github.com/wessamfathi/suhailWhat 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 | $0.00036 | $0.02075 |
| Opus 5 | $0.00018 | $0.01038 |
| Sonnet 5 | $0.00007 | $0.00415 |
| Haiku 4.5 | $0.00004 | $0.00208 |
Grade A, and why
init 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 2d 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 — 128 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/su:init — Suhail Initializer
You are now acting as the Suhail initializer for this turn. Your job is to scan the current project once and cache structured intel that downstream Suhail commands and subagents consult as a baseline. You delegate the actual scanning to the indexer subagent; you do not read project source files yourself.
/su:go and /su:discover refuse to run until this intel exists. Run /su:init once per project. Re-run with refresh after large structural changes (new modules, stack swap, monorepo split) to update the cache.
User arguments: $ARGUMENTS
Argument shapes
| Shape | Meaning |
|---|---|
(empty) |
Run the indexer. If intel already exists, ask the user whether to refresh, skip, or show what's there. |
refresh |
Force a rescan and overwrite without asking. |
What you produce
The indexer subagent writes four files under .suhail/intel/:
| File | Contains |
|---|---|
stack.md |
Languages, frameworks, package managers, canonical build/test/lint/run commands (root + nested). |
layout.md |
Top-level directory map with one-line purpose per directory. |
conventions.md |
Distilled house style from CLAUDE.md, AGENTS.md, .cursorrules, README. |
modules.md |
Key modules / packages, their entry points, and one-line responsibilities. |
You also ensure the following directories exist (create if missing, do not touch existing contents):
.suhail/.suhail/intel/.suhail/plans/
Process
-
In-flight check. If
.suhail/state.jsonexists AND its top-levelabortedis nottrueAND itsrun_phaseis not a terminal value (finishedorcompleted), a Suhail run is already in flight. End with one sentence: "A Suhail run is in-flight (.suhail/state.json). Finish or abort it before re-running /su:init." Do not dispatch. A run whoserun_phaseisfinished/completed, or whoseaborted == true, is terminal — not in-flight — so proceed to the next step. -
Project detection. If there is no
.gitentry (directory or file — in a linked git worktree.gitis a plain pointer file) and no root manifest (package.json,pyproject.toml,go.mod,Cargo.toml,Gemfile,mix.exs,*.csproj,composer.json,pom.xml), end with one sentence: "No project detected at the current directory. Run /su:init from a project root."
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.
- 2d ago First seen · 128 lines · 36 tokens per session scan A 3c271437c6a1
init is a command published in the GitHub repository wessamfathi/suhail (2 stars, last pushed 1mo ago), licensed MIT. It adds 36 tokens to every session and 2,075 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.
Other commands, from other repositories
providers
Display Better Auth available authentication providers and their configuration.
thread
Manage conversation threads (create, switch, update, delete, show).
fe-start
前端开发 - 需输入任务描述 (如: /fe-start "开发组件").
verify
Verify any change surface against approved acceptance criteria and preserve evidence.
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.