sanad-agent: Skill for Claude Code

.agents/skills/sanad-contribution-triage/SKILL.md

Sanad Contribution Triage is a skill for Claude Code, Codex from EastStarAI/sanad-agent. It costs 33 tokens per session (492 once invoked), scanned A, original, MIT.

A set of rules for sorting Sanad community questions, ideas, bugs, documentation requests, and accepted work into the right GitHub or Discord location. Sanad is the project this guidance applies to.

In plain words
What is it for?
Use it to decide whether a request belongs in Discord, a GitHub Discussion, an Issue, or a tracked plan, and to apply the repository's defined labels.
Why use it?
It helps contributors avoid duplicate reports, incorrect routing, unsafe public discussion of vulnerabilities, and labels that the repository does not support.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: 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-contribution-triage/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 Contribution Triage

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/eaststarai/sanad-agent/sanad-contribution-triage"><img src="https://agentmods.dev/badge/skills/eaststarai/sanad-agent/sanad-contribution-triage.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 492 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 pass 7 Sept 2026
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 $0.00492
Opus 5 $0.00016 $0.00246
Sonnet 5 $0.00007 $0.00098
Haiku 4.5 $0.00003 $0.00049

Measured 12d ago against content hash f151965c1145, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

Sanad Contribution Triage 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-contribution-triage/SKILL.md · 37 lines

How it starts

The opening of the file, as written. The whole thing — 37 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Sanad Contribution Triage

Use this skill to classify an incoming question, idea, bug, documentation request, or accepted work item. It advises or prepares repository-native work; it does not mutate GitHub without explicit authorization.

Routing

  1. Stop immediately if the report may describe an undisclosed vulnerability. Direct it to GitHub Private Vulnerability Reporting or [email protected]; do not quote, summarize, or recreate sensitive details publicly.
  2. Search existing Discussions, Issues, and pull requests for a duplicate.
  3. Route quick help to Discord, an open-ended idea or RFC to a Discussion, and reproducible or accepted work to an Issue.
  4. Require an Epic Issue plus one docs/plans/tasks/ plan only when the change affects a protocol/API, schema/migration, security/privacy boundary, release contract, cross-component architecture, major UX workflow, or coordinated multi-PR delivery.
  5. When a Discussion direction is accepted, have a maintainer record the decision and open or approve the actionable Issue. Votes alone do not accept a design.

Labels

Read .github/labels.yml before classifying. Never invent or apply a label that is absent from the manifest.

  • Start a new Issue with needs-triage and exactly one type/* label.
  • Add at least one comp/* label and a platform label only when the scope is platform-specific.
  • A maintainer assigns exactly one priority and one size after triage.
  • Add ready-for-contributor only after scope, acceptance, and dependencies are clear.
  • Add good-first-issue only when no architectural decision remains.
  • Keep type/security limited to publicly safe hardening; private vulnerabilities never become ordinary Issues before coordinated disclosure.
  • Protected review labels require an authorized maintainer and are not triage decoration.

Output

Return: destination, duplicate-search result, proposed existing labels, missing information, plan threshold result, and the next human decision. On request, draft content but do not create, close, assign, or relabel work without explicit authorization.

Read the full file on GitHub · 37 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 · 37 lines · 33 tokens per session scan A f151965c1145

Subscribe to this mod's changes

Sanad Contribution Triage is a skill published in the GitHub repository EastStarAI/sanad-agent (44 stars, last pushed 2d ago), licensed MIT. It adds 33 tokens to every session and 492 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.