Borrowing it
Nothing to install: this file belongs to EastStarAI/sanad-agent. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/EastStarAI/sanad-agent/main/.agents/skills/install-sanad/SKILL.mdgit clone --depth 1 https://github.com/EastStarAI/sanad-agentWrote 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/skills/eaststarai/sanad-agent/install-sanad)<a href="https://agentmods.dev/skills/eaststarai/sanad-agent/install-sanad"><img src="https://agentmods.dev/badge/skills/eaststarai/sanad-agent/install-sanad/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/eaststarai/sanad-agent/install-sanad"><img src="https://agentmods.dev/badge/skills/eaststarai/sanad-agent/install-sanad.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00095 | $0.02923 |
| Opus 5.5 | $0.00038 | $0.01169 |
| Sonnet 5.5 | $0.00019 | $0.00585 |
| Haiku 4.5 | $0.00010 | $0.00292 |
Grade D, and why
install-sanad scanned grade D with 3 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 yesterday.
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.
Asks for rootmediumPrivilege escalation
A mod that escalates privileges can change anything on the machine, not only the project.
curl -fsSL https://sanad.eaststarai.com/install.sh | sudo bash -s -- --login Downloads and executes remote codehighSupply chain
curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.
curl -fsSL https://sanad.eaststarai.com/install.sh | bash -s -- --login Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -fsSL https://sanad.eaststarai.com/install.sh | bash -s -- --login How it starts
The opening of the file, as written. The whole thing — 280 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Install Sanad
Guide the user from inspection through a verified Sanad installation or update. Keep the release-user and developer-source workflows separate.
Safety Rules
- Inspect before changing anything. Treat installation, package replacement, service registration, application launch, and Git updates as mutations that require the user's informed approval.
- Never search an entire home directory or disk for a checkout. Inspect the current directory, a path supplied by the user, and standard installed-command locations only. Ask for the project path when it cannot be identified safely.
- Never overwrite, reset, clean, stash, commit, or discard a dirty repository unless the user explicitly authorizes that exact action.
- Never request, quote, log, or reconstruct access tokens, refresh tokens, provider credentials, signing secrets, or user content. For an explicitly authorized agent-operated remote install only, accept the user's complete Add device command containing its short-lived, single-use creation token. Validate the official bootstrap, transmit it without echoing, tracing, or persisting it in project artifacts, and never extract/reconstruct its token. Explain that this consent covers creation-command exposure in chat/tool history and that the generated installer command may use token arguments; do not claim zero exposure. Keep SSH transport arguments credential-free. If the user does not accept that exposure, have them execute it directly or use interactive Portal sign-in. This exception never covers durable credentials.
- Use only official Sanad sources:
- repository:
https://github.com/EastStarAI/sanad-agent - releases:
https://github.com/EastStarAI/sanad-agent/releases/latest - installers:
https://sanad.eaststarai.com/install.shandhttps://sanad.eaststarai.com/install.ps1
- repository:
- Do not disable operating-system security controls. Read the latest release notes before describing current signing or platform support.
- Preserve Sanad Home and user workspaces during installation and update.
What ships with it
3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- yesterday Changed · +41 lines scan C → D 870b7347f3fb
- 17d ago Changed · -2 lines 311a767f4721
- 22d ago Changed · +22 lines · +13 tokens per session 3ecbd4cd0436
- 2mo ago First seen · 219 lines · 82 tokens per session scan C 68d2977e140a
install-sanad is a skill published in the GitHub repository EastStarAI/sanad-agent (47 stars, last pushed yesterday), licensed MIT. It adds 95 tokens to every session and 2,923 once invoked, about $0.0004 per session on Opus 5.5. A static security scan graded it D with 3 findings (asks for root, downloads and executes remote code, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
install-sanad compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| install-sanadEastStarAI/sanad-agent | Skill | 47 | yesterday | MIT | D | 95 | Codex |
| flutterpledgeandgrow/pledge-skills | Skill | 10 | 3mo ago | MIT | A | 126 | Claude Code, Codex |
| at_client_skills-sdkatsign-foundation/at_client_sdk | Skill | 1.4k | yesterday | BSD-3-Clause | A | 220 | Claude Code |
| flutter-pre-cachingevanca/flutter-ai-rules | Skill | 669 | yesterday | MIT | A | 36 | Claude Code |
| firebase-authevanca/flutter-ai-rules | Skill | 669 | yesterday | MIT | A | 29 | Claude Code |
| firebase-messagingevanca/flutter-ai-rules | Skill | 669 | yesterday | MIT | A | 35 | Claude Code |
| code-reviewevanca/flutter-ai-rules | Skill | 669 | yesterday | MIT | A | 27 | Claude Code |