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/sanad-pull-request-review/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/sanad-pull-request-review)<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.
<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>- NVIDIA SkillSpector pass
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 | $0.00032 | $0.00459 |
| Opus 5 | $0.00016 | $0.00230 |
| Sonnet 5 | $0.00006 | $0.00092 |
| Haiku 4.5 | $0.00003 | $0.00046 |
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 11d 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.
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 Pull Request Review
Use this skill for evidence-first review. It reports findings but does not approve, merge, add protected labels, or perform another maintainer action without explicit authorization.
Review Procedure
- Read the linked Issue, accepted Discussion, or owning task plan and extract acceptance criteria.
- Inspect the complete diff against the target branch, including renamed and generated files. Confirm the branch has a common ancestor with
main. - Read the nearest
AGENTS.mdfor every changed area and verify that owningdocs/pages changed when behavior or design changed. - Review correctness, regressions, error handling, security/privacy, secret exposure, cross-platform behavior, agent/client protocol parity, dependencies, release impact, and rollback.
- Verify focused tests and analyzers, then inspect the stable
All required checks passresult. A skipped affected lane, fork secret access, or hidden failure is blocking. - 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.
- Confirm a user with triage/write authority supplied each required positive-review label. Never add one merely to make CI green.
- Review dependency and lockfile diffs explicitly.
Findings Format
Order findings by severity:
- Blocker: unsafe, incorrect, acceptance-breaking, secret-exposing, or required evidence missing.
- Warning: material risk or maintainability problem that should be resolved before merge.
- Suggestion: non-blocking improvement.
Each finding includes a precise path/location, impact, evidence, and actionable correction. If no finding remains, state the residual risks and exact verification reviewed. Do not claim approval for a security-sensitive change solely because this skill produced no findings.
Mutation Boundary
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.
- 11d ago First seen · 37 lines · 32 tokens per session scan A 1f150c541983
Sanad Pull Request Review is a skill published in the GitHub repository EastStarAI/sanad-agent (44 stars, last pushed yesterday), licensed MIT. It adds 32 tokens to every session and 459 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.
Other skills, from other repositories
code-review
Use when asked to review a PR, MR, branch, or diff, audit changed files, or check code quality.
flutter-mcp-boundary-audit
Generic contract/schema boundary audit across authoring, discovery, validation, and execute—detecting split-brain between listings and invoke paths, gateway divergence, and permissive placeholders. Use when changing tool registration, RPC/plugin registries, dynamic tools, MCP or WebMCP surfaces, CLI exec aliases…
mine-plan-review
Strictly review one implemented repository plan against AGENTS.md, architecture, the immutable plan, implementation commits, real runtime behavior, verification evidence, and downstream contracts. Use when the user invokes the host-specific mine-plan-review skill with a plan path, asks whether a plan can be accepted…
gh-address-comments
Help address review/issue comments on the open GitHub PR for the current branch using gh CLI; verify gh auth first and prompt the user to authenticate if not logged in.
review-checklist
A structured checklist for reviewing work and bringing the review to a clear close. It covers preparing evidence, freezing the checklist, updating status, and resolving remaining items.
audit-tech-design
A review checklist for technical designs, covering architecture, technology choices, and the plan for implementing a system or feature.