sanad-agent: Skill for Claude Code

.agents/skills/sanad-pull-request-review/SKILL.md

Sanad Pull Request Review is a skill for Claude Code, Codex from EastStarAI/sanad-agent. It costs 32 tokens per session (842 once invoked), scanned A, original, MIT.

A review procedure for checking a Sanad pull request against its related issue, plan, contracts, tests, security boundaries, and required labels.

In plain words
What is it for?
Use it to inspect the full diff, acceptance criteria, project instructions, tests, security implications, protected paths, and required checks. It reports findings but does not approve or merge the request.
Why use it?
It makes the review evidence-based and helps catch correctness, security, documentation, testing, dependency, and release problems before approval.

Skill for Claude CodeCodex

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

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-pull-request-review/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 Pull Request Review

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/eaststarai/sanad-agent/sanad-pull-request-review"><img src="https://agentmods.dev/badge/skills/eaststarai/sanad-agent/sanad-pull-request-review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 32 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 842 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 $0.00032 $0.00842
Opus 5.5 $0.00013 $0.00337
Sonnet 5.5 $0.00006 $0.00168
Haiku 4.5 $0.00003 $0.00084

Measured yesterday against content hash 4240013ce577, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

Sanad Pull Request Review 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-pull-request-review/SKILL.md · 46 lines

How it starts

The opening of the file, as written. The whole thing — 46 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Sanad Pull Request Review

Use this skill for evidence-first review. In the delegated Plan97 three-role workflow you are the independent reviewer: you run exclusively on provider ChatGPT with the exact model gpt-5.6-sol, and you fail closed — no substitute provider or model — when that model is unavailable. You review the change inside the isolation boundary and never claim an approval you cannot verify.

Review Procedure

  1. Read the linked Issue, accepted Discussion, or owning task plan and extract acceptance criteria.
  2. Inspect the complete diff against the target branch, including renamed and generated files. Confirm the branch has a common ancestor with main.
  3. Read the nearest AGENTS.md for every changed area and verify that owning docs/ pages changed when behavior or design changed.
  4. Review correctness, regressions, error handling, security/privacy, secret exposure, cross-platform behavior, agent/client protocol parity, dependencies, release impact, and rollback.
  5. Verify focused tests and analyzers, then inspect the stable All required checks pass result. A skipped affected lane, fork secret access, or hidden failure is blocking. Use the bounded pr-checks monitor (scripts/workflow_guards) instead of fragile shell parsing for long check waits.
  6. Map paths to protected labels:
    • .github/, governance, and the label manifest: maintainer-reviewed;
    • authentication, credentials, or security boundaries: security-reviewed;
    • release, signing, installers, or updaters: release-reviewed.
  7. Confirm a user with triage/write authority supplied each required positive-review label, and that protected-labels.yml re-verified it for the current head SHA. Never add one merely to make CI green; a label applied or removed without that dispatch leaves the aggregate result stale.
  8. Confirm the pull request also carries its mandatory non-protected labels: exactly one type/* and at least one comp/*, plus platform/* only when the change is platform-specific and a size/* entry when the size is material. Apply or request the missing labels, and report an unlabeled or misclassified pull request as a finding instead of reviewing around it. A green All required checks pass never proves these labels exist, because the protected-label job checks protected labels only.
  9. Review dependency and lockfile diffs explicitly.

Read the full file on GitHub · 46 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. yesterday Changed 4240013ce577
  2. 21d ago Changed · +1 lines 2df8e7260066
  3. 1mo ago Changed · +8 lines 8aeb3787f508
  4. 2mo ago First seen · 37 lines · 32 tokens per session scan A 1f150c541983

Subscribe to this mod's changes

Sanad Pull Request Review is a skill published in the GitHub repository EastStarAI/sanad-agent (47 stars, last pushed yesterday), licensed MIT. It adds 32 tokens to every session and 842 once invoked, about $0.0001 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 2026-08-30.

Related

Sanad Pull Request Review compared with skills from other repositories

Sanad Pull Request Review next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
Sanad Pull Request ReviewEastStarAI/sanad-agentSkill47yesterdayMITA32Claude Code, Codex
code-reviewevanca/flutter-ai-rulesSkill669yesterdayMITA27Claude Code
flutter-mcp-boundary-auditArenukvern/mcp_flutterSkill39520d agoMITA92Claude Code
security-reviewsgaabdu4/building-flutter-appsSkill254d agoMITA58Claude Code, Codex
code-reviewsgaabdu4/building-flutter-appsSkill254d agoMITA39Claude Code, Codex
gitnexus-impact-analysisArenukvern/mcp_flutterSkill39520d agoMITA50Claude Code
flutterpledgeandgrow/pledge-skillsSkill103mo agoMITA126Claude Code, Codex