agent-risk-review

agent-risk-review is a command for Claude Code, Cursor from emaraschio/cursor-commands. It costs 20 tokens per session (548 once invoked), scanned A, original, MIT.

A short permission review for deciding what access an AI agent should receive to a system, tool, or account. It covers the request, discovery, draft, clarification, and final brief, with access limited to what is necessary.

In plain words
What is it for?
Use it before granting an agent permissions, especially for systems or accounts where mistakes could affect production data or settings.
Why use it?
It reduces the risk of giving an agent broad or destructive access without documented limits.

Command for Claude CodeCursor

Written for Cursor and Claude Code: installed under .cursor/, but also a Claude Code command (commands/*.md).

Good fit Use it before granting an agent permissions, especially for systems or accounts where mistakes could affect production data or settings.

Compare 6 commands from other repositories ↓
Install with agentmods
npx agentmods add commands/emaraschio/cursor-commands/agent-risk-review
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.

Clone the repo
git clone --depth 1 https://github.com/emaraschio/cursor-commands

Made for: Claude Code, 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 agent-risk-review

README.md
[![agentmods](https://agentmods.dev/badge/commands/emaraschio/cursor-commands/agent-risk-review/github.svg)](https://agentmods.dev/commands/emaraschio/cursor-commands/agent-risk-review)
Your own site
<a href="https://agentmods.dev/commands/emaraschio/cursor-commands/agent-risk-review"><img src="https://agentmods.dev/badge/commands/emaraschio/cursor-commands/agent-risk-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 agent-risk-review

Your own site · 80×15
<a href="https://agentmods.dev/commands/emaraschio/cursor-commands/agent-risk-review"><img src="https://agentmods.dev/badge/commands/emaraschio/cursor-commands/agent-risk-review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 20 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 548 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.
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 $0.00020 $0.00548
Opus 5 $0.00010 $0.00274
Sonnet 5 $0.00004 $0.00110
Haiku 4.5 $0.00002 $0.00055

Measured 9d ago against content hash 5299200586c5, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

agent-risk-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 9d 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.

.cursor/commands/agent-risk-review.md · 40 lines

How it starts

The opening of the file, as written. The whole thing — 40 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Overview

Produce a one-page agent permission brief before granting an AI agent access to a system, tool, or account. Full workflow: .cursor/skill-contracts/agent-risk-review/SKILL.md (user install: ~/.cursor/skill-contracts/agent-risk-review/SKILL.md).

Defaults

None. See skill for workflow defaults.

Steps

  1. Read .cursor/skill-contracts/agent-risk-review/SKILL.md for the full agent contract; if that file is missing, read ~/.cursor/skill-contracts/agent-risk-review/SKILL.md.
  2. Execute phases in order (Intake → Discovery → Draft → Clarify gate → Deliver); do not skip the clarify-before-finalize gate.
  3. Report the final seven-section brief in chat; offer optional save under docs/agent-permissions/<slug>.md when the host has docs/.

Anti-patterns

  • Default to least privilege, never blanket access. Trigger: drafting the allowed-actions tier. Wrong: granting full admin or broad write access without explicit limits. Correct: scope each grant to least privilege and require documented limits for anything destructive. Reason: an over-permissioned agent turns a small mistake into a production-wide one.
  • Resolve ambiguity before finalizing. Trigger: a permission tier, limit, or log destination is unclear. Wrong: publishing the final brief on guessed or maximal defaults. Correct: stop at the clarify gate and ask before finalizing. Reason: a brief shipped on assumptions authorizes access no one actually reviewed.
  • Never route secrets into logs. Trigger: specifying the required-logs section. Wrong: logging tokens, credentials, PII, or PHI in plain text. Correct: place them under must-not-log and never-allowed. Reason: logs are retained and broadly readable, so a logged secret is a leaked secret.

Examples

  • /agent-risk-review with "GitHub org token for merge bot"
  • /agent-risk-review with "AWS prod read-only for incident agent"

Maintainers

Behavioral eval: .cursor/skill-contracts/agent-risk-review/eval/cases.md. Ship gate sections: A, S before changing SKILL.md or this command.

Read the full file on GitHub · 40 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. 9d ago First seen · 40 lines · 20 tokens per session scan A 5299200586c5

Subscribe to this mod's changes

agent-risk-review is a command published in the GitHub repository emaraschio/cursor-commands (9 stars, last pushed 1mo ago), licensed MIT. It adds 20 tokens to every session and 548 once invoked, about $0.0001 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 2026-08-31.