review-security

review-security is a skill for Cursor from saski/arnesto. It costs 12 tokens per session (777 once invoked), scanned A, a copy of review-security, Unlicense.

A code-review instruction that runs a security-focused review of the repository's changes.

In plain words
What is it for?
Checking the current repository changes for security issues with a dedicated review agent.
Why use it?
It helps find security weaknesses in changed code before they reach users or production systems.

Skill for Cursor

Written for Cursor: installed under .cursor/. Also seen: mentions subagents.

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add skills/saski/arnesto/review-security
Any agent
npx skills add saski/arnesto --skill review-security
Clone the repo
git clone --depth 1 https://github.com/saski/arnesto

Made for: Cursor.

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 review-security

README.md
[![agentmods](https://agentmods.dev/badge/skills/saski/arnesto/review-security.svg)](https://agentmods.dev/skills/saski/arnesto/review-security)
Your own site
<a href="https://agentmods.dev/skills/saski/arnesto/review-security"><img src="https://agentmods.dev/badge/skills/saski/arnesto/review-security.svg" alt="Measured on agentmods" height="20"></a>
Per session 12 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. Scan, not verified.
Origin 100% copy Near-identical to another mod 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 $0.00012 $0.00777
Opus 5 $0.00006 $0.00388
Sonnet 5 $0.00002 $0.00155
Haiku 4.5 $0.00001 $0.00078

Measured 2d ago against content hash d007ec5a617e, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

review-security 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 2d 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.

Origin

This is a copy

100% identical to review-security — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

.cursor/skills-cursor/review-security/SKILL.md · 52 lines

What it actually says

Review Security

Use this skill when the user asks to run /review-security.

Launch exactly one security-review subagent with:

  • run_in_background: false unless explicitly asked to run in background
  • description: "Security Review"
  • subagent_type: "security-review"

The review subagent computes the local diff from the repository path, so do not compute the diff yourself before launching it. The repository path should be the active workspace or repository root for the code the user wants reviewed.

By default, the review subagent infers the repository's actual base branch, such as main, when computing branch changes. In most cases, do not provide Base Branch. Only provide it if you know the current branch or PR should be compared against a specific branch other than the repository's default base branch, such as when you created the current branch from another branch.

Special case: if the user explicitly asks to review a specific PR or branch, make sure that target is checked out before launching the subagent:

  • Examples include github.com/... /review, review {link}, or review {branch-name}.
  • Resolve the provided PR link, PR number, or branch name to the PR head branch or named branch.
  • Check whether the target branch is already the currently checked out local branch. If it is, continue.
  • If a different branch is currently checked out, try to switch to the target branch.
  • If Git refuses to switch because local files would be overwritten, conflicts need resolution, or another checkout blocker occurs, explain the blocker and ask whether the user wants to stash local changes before retrying.
  • Only stash after the user confirms. If the stash succeeds, retry switching to the target branch.
  • Launch the review subagent only after the target branch is checked out locally.

Use this exact prompt shape:

Full Repository Path: <absolute repository path>
Diff: <one of: "branch changes", "uncommitted changes">
Base Branch: <only include this line when reviewing branch changes against a known specific base branch>
Custom Instructions: <only include this line when the user gave specific review instructions>

Default to branch changes, which reviews branch changes against the merge-base with the default/base branch, including committed, staged, and unstaged changes. If the user asks to review only uncommitted, local working tree, dirty, or not-yet-committed changes, use uncommitted changes.

If the review subagent fails before producing findings, inspect the failure text.

  • If the failure is caused by calling the subagent incorrectly, such as a missing Full Repository Path, missing Diff, wrong prompt shape, or wrong subagent type, correct the invocation and retry it once immediately.
  • For any other subagent failure, retry once with the same prompt shape.
  • If the same failure persists after the retry, stop. Briefly tell the user that the review subagent could not complete and include the short error or blocker. Do not keep retrying.

After the subagent finishes, summarize the result:

  • If it reports that no diff was found or the diff is empty, tell the user in one sentence that there was no diff to review.
  • If it found no issues, give a one-line status such as "Security review found 2 findings / Security review found no issues".
  • If it found issues, print a compact markdown table with one row per finding, sorted by severity (highest first), using exactly these columns: Severity, Location (file:line), Finding. Put the file and line in the location column as file:line.

Do not fix findings or rerun review unless the user explicitly asks for that next step.

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. 2d ago First seen · 52 lines · 12 tokens per session scan A d007ec5a617e

Subscribe to this mod's changes

review-security is a skill published in the GitHub repository saski/arnesto (5 stars, last pushed 10d ago), licensed Unlicense. It adds 12 tokens to every session and 777 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to review-security, differing in 0 lines, and is treated as a copy.

Related

Other skills, from other repositories

pixir-delegate

Use Pixir as a headless subagent runtime from Claude Code or any harness with skill ! preprocessing (Codex roots and other no-hydration hosts use pixir-delegate-codex instead) — one-shot workers (pixir --json), parallel fan-out to N children (pixir delegate --spec), resumable steering (pixir resume), evidence…

Ranvier-Technologies/pixir · 126 tokens

pixir-delegate-codex

Use when a Codex CLI/Desktop root should fan out subagents, delegate to Pixir workers, run parallel workers, or manage a resident delegation daemon via Pixir Delegate; covers Codex preflight, AGENTS.md, approvals/sandbox, dry-run, daemon start/status/attach/cancel, closure evidence, and audited single-run execution…

Ranvier-Technologies/pixir · 89 tokens

pixir-diagnostics

Diagnose Pixir and T3 Code Pixir incidents from local canonical evidence. Use when a Pixir run, ACP/T3 thread, subagent/workflow, provider replay, or daily-driver dogfood session appears stuck, inconsistent, missing tool output, or hard to classify.

Ranvier-Technologies/pixir · 61 tokens

readonly-review

Run a no-network read-only review practice with two explorer steps and one synthesis step.

Ranvier-Technologies/pixir · 20 tokens

pixir-delegate-native

Delegate work to subagents from INSIDE a Pixir session using the native Subagent tools (spawnagent, waitagent, closeagent, listagents, sendinput) instead of shelling out to the pixir CLI. Use when you are a Pixir session that needs to fan out parallel workers, steer a child, or run skill-backed workflow templates …

Ranvier-Technologies/pixir · 89 tokens

repo-harness-assessment

Use when evaluating repository agent-readiness, mapping harness roles, choosing the next smallest improvement, or designing and reconciling agent entrypoints such as AGENTS.md, CLAUDE.md, GEMINI.md, Cursor rules, or GitHub instructions.

yfge/agent-harness-skills · 56 tokens