What is sanad-delegate?

An instruction guide for external orchestrators to run delegated tasks through the sanad command-line interface. An orchestrator coordinates separate task runs, their files, status, and interventions.

It is for connecting tools such as CI/CD pipelines or other coding agents to `sanad run` for delegated task execution.

It defines a consistent way to pass task briefs, keep execution areas separate, coordinate results, and stop or intervene in delegated work.

How EastStarAI/sanad-agent configures Claude Code and Codex

Reuse

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.

Copy the file

curl -O https://raw.githubusercontent.com/EastStarAI/sanad-agent/main/.agents/skills/sanad-delegate/SKILL.md

Clone the repo

git clone --depth 1 https://github.com/EastStarAI/sanad-agent

Made for: Claude Code, Codex.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/eaststarai/sanad-agent/sanad-delegate/github.svg)](https://agentmods.dev/skills/eaststarai/sanad-agent/sanad-delegate)

Your own site

<a href="https://agentmods.dev/skills/eaststarai/sanad-agent/sanad-delegate"><img src="https://agentmods.dev/badge/skills/eaststarai/sanad-agent/sanad-delegate/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/eaststarai/sanad-agent/sanad-delegate"><img src="https://agentmods.dev/badge/skills/eaststarai/sanad-agent/sanad-delegate.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 47 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 5,177 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

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	$0.00047	$0.05177
Opus 5.5	$0.00019	$0.02071
Sonnet 5.5	$0.00009	$0.01035
Haiku 4.5	$0.00005	$0.00518

Measured yesterday against content hash 2d47aaa52897, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

sanad-delegate 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 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.

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.

.agents/skills/sanad-delegate/SKILL.md · 401 lines

How it starts

The opening of the file, as written. The whole thing — 401 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Sanad Delegate Execution Skill

The sanad-delegate skill teaches external orchestrators (such as delegate-task-supervisor, OpenCode, Antigravity, or CI/CD pipelines) how to drive the native, daemon-backed sanad run CLI machine contract for delegated tasks.

1. System Topology & Responsibilities

┌─────────────────────────────────────────────────────────────┐
│                 delegate-task-supervisor                    │
│      (Orchestrator: Concurrency, Timelines, State)          │
└──────────────┬───────────────────────────────┬──────────────┘
               │                               │
               ▼                               ▼
┌──────────────────────────────┐ ┌───────────────────────────┐
│        sanad-delegate        │ │    opencode / agy-delegate │
│   (Instruction & Contract)   │ │    (Other Implementers)   │
└──────────────┬───────────────┘ └───────────────────────────┘
               │
               ▼
┌─────────────────────────────────────────────────────────────┐
│                       Sanad CLI                             │
│       `sanad run --brief-file <f> --out-dir <d> ...`        │
│        (attached to the active local daemon)                │
└─────────────────────────────────────────────────────────────┘

Separation of Concerns:
- delegate-task-supervisor: Orchestrates task queues, concurrency limits, supervisor runs, and unified event timelines.
- sanad-delegate: Global instruction skill that guides orchestrators to invoke the native sanad run machine contract with proper prompt transport, workspace separation, and artifact tracking.
- sanad run: Built directly into the Sanad binary. Manages brief ingestion, registered-workspace or temporary-root targeting, serialized artifact emission, timeout handling, and signal termination without requiring auxiliary scripts or packages.

2. Command Invocation

2.1. Production / Installed Usage (Standard)

Orchestrators invoke the installed sanad binary directly:

Read the full file on GitHub · 401 lines

Changes

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 · +51 lines 2d47aaa52897
14d ago Changed · +8 lines 7f4d52a00967
16d ago Changed · +29 lines a327fb68fbca
22d ago Changed · +131 lines b7495bafd87e
1mo ago Changed · +1 lines e53036035ffa
1mo ago Changed · +1 lines 60987fe57c1b
1mo ago First seen · 180 lines · 47 tokens per session scan A c0b522ac856f

Subscribe to this mod's changes

sanad-delegate is a skill published in the GitHub repository EastStarAI/sanad-agent (47 stars, last pushed yesterday), licensed MIT. It adds 47 tokens to every session and 5,177 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-09-23.

Building agents ai-agent coding-agent dart desktop developer-tools flutter

sanad-delegate next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
sanad-delegateEastStarAI/sanad-agent	Skill	47	yesterday	MIT	A	47	Claude Code, 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

sanad-agent: Skill for Claude Code