sanad-agent: Skill for Claude Code

.agents/skills/sanad-orchestrator/SKILL.md

Sanad Project Orchestrator is a skill for Claude Code, Codex from EastStarAI/sanad-agent. It costs 33 tokens per session (777 once invoked), scanned A, original, MIT.

A project-management procedure for Sanad repositories. It turns feature requests into plans and small coding tasks, then routes work and coordinates review and merging.

In plain words
What is it for?
Auditing a repository, researching an external open-source project, writing plans in docs/plans, breaking work into 15–30-minute tasks, and coordinating merges.
Why use it?
It gives a large change a structured path from research through implementation and code review.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: mentions subagents; installed under .agents/ (shared by several agents).

This is EastStarAI/sanad-agent's own configuration. It tells Claude Code and Codex how to work on sanad-agent itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything sanad-agent configures →

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-orchestrator/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.

agentmods badge for Sanad Project Orchestrator

README.md
[![agentmods](https://agentmods.dev/badge/skills/eaststarai/sanad-agent/sanad-orchestrator/github.svg)](https://agentmods.dev/skills/eaststarai/sanad-agent/sanad-orchestrator)
Your own site
<a href="https://agentmods.dev/skills/eaststarai/sanad-agent/sanad-orchestrator"><img src="https://agentmods.dev/badge/skills/eaststarai/sanad-agent/sanad-orchestrator/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.

agentmods 80×15 button for Sanad Project Orchestrator

Your own site · 80×15
<a href="https://agentmods.dev/skills/eaststarai/sanad-agent/sanad-orchestrator"><img src="https://agentmods.dev/badge/skills/eaststarai/sanad-agent/sanad-orchestrator.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 33 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 777 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. Third-party audits
  • NVIDIA SkillSpector warn 7 Sept 2026
SkillSpector: 2 findings, up to medium

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

  • medium Agent Snooping · line 56
    Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.
    Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
  • medium Agent Snooping · line 57
    Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.
    Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
How audits are shown
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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00033 $0.00777
Opus 5 $0.00016 $0.00388
Sonnet 5 $0.00007 $0.00155
Haiku 4.5 $0.00003 $0.00078

Measured 12d ago against content hash 9b794183f528, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

Sanad Project Orchestrator 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 12d 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.

.agents/skills/sanad-orchestrator/SKILL.md · 58 lines

How it starts

The opening of the file, as written. The whole thing — 58 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Sanad Project Orchestrator (SOP)

You are the Sanad Project Orchestrator, the strategic mind and architectural lead of this repository. Your primary goal is to guide the user, break down complex requirements into precise testable plans, assign tasks dynamically, and verify code quality.


1. Objective & Scope

This SOP defines the step-by-step procedure for managing the lifecycle of project features, from research and planning through task breakdown, execution routing, review, and merge coordination.


2. Standard Operating Procedure (Step-by-Step)

Phase 1: Research & Repository Audit

  1. When provided with an open-source GitHub repository URL or custom design instructions, analyze the feature structure, database entities, or protocols.
  2. Clone any target repositories to a temporary directory if needed.
  3. Formulate a concrete adaptation plan mapping the learned pattern directly onto the Sanad architecture.
  4. Save this high-level roadmap under docs/plans/<major_feature_name>.md.

Phase 2: Hierarchical Task Breakdown

  1. Break down roadmaps into independent task items designed to take 15–30 minutes to execute.
  2. Generate a detailed task plan file in the relative path: docs/plans/tasks/<task_id>-<task_name>.md.
  3. Task Plan Requirements: The file must include:
    • Goal Description: Clear summary of what the task accomplishes.
    • DoD (Definition of Done): Clear, verifiable check-list.
    • Success Test Scenario: The exact test commands or manual steps to prove the task succeeded.

Phase 3: Repository-Native Tracking

  1. Keep the owning roadmap and task plan status current; do not create a second project-management source of truth.
  2. Route executable public work to GitHub Issues when the public repository exists, and keep large or risky implementation detail in docs/plans/tasks/.
  3. Record dependencies, progress, acceptance gates, and handoff evidence in the owning task file.

Phase 4: Execution & Invocation Decision

  1. Evaluate task complexity and runtime risk:
    • Focused live update: When the user explicitly wants the currently running source checkout updated in place and focused startup/recovery verification can keep the restart safe, load sanad-agentic-developer and use its live current-checkout workflow.
    • Simple non-runtime tweak: Execute a trivial documentation or configuration change directly on the active branch when no isolation boundary is needed.
    • Parallel, risky, or complex implementation: Invoke a subagent with the sanad-subagent-developer skill and pass only the relevant task plan. Supervisor/bootstrap, migration, broad runtime, and PR-bound work belongs in an isolated worktree unless the user explicitly accepts the live-update risk.

Read the full file on GitHub · 58 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.

  1. 12d ago First seen · 58 lines · 33 tokens per session scan A 9b794183f528

Subscribe to this mod's changes

Sanad Project Orchestrator is a skill published in the GitHub repository EastStarAI/sanad-agent (44 stars, last pushed yesterday), licensed MIT. It adds 33 tokens to every session and 777 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 2026-08-30.