agent-risk-review

agent-risk-review is a skill for Claude Code, Cursor from emaraschio/cursor-commands. It costs 70 tokens per session (1,028 once invoked), scanned A, original, MIT.

A permission plan for giving an AI agent access to a system, tool, or account.

In plain words
What is it for?
Use it to define spending and data limits, logging, failure recovery, rollback steps, and a low-risk first-week access test.
Why use it?
It clarifies what the agent may do, what needs approval, what is forbidden, and how to limit or undo mistakes.

Skill for Claude CodeCursor

Written for Claude Code and Cursor: user-invocable in frontmatter, but also installed under .cursor/.

Good fit Use it to define spending and data limits, logging, failure recovery, rollback steps, and a low-risk first-week access test.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/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.

Any agent
npx skills add emaraschio/cursor-commands --skill agent-risk-review
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/skills/emaraschio/cursor-commands/agent-risk-review/github.svg)](https://agentmods.dev/skills/emaraschio/cursor-commands/agent-risk-review)
Your own site
<a href="https://agentmods.dev/skills/emaraschio/cursor-commands/agent-risk-review"><img src="https://agentmods.dev/badge/skills/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/skills/emaraschio/cursor-commands/agent-risk-review"><img src="https://agentmods.dev/badge/skills/emaraschio/cursor-commands/agent-risk-review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 70 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,028 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 $0.00070 $0.01028
Opus 5 $0.00035 $0.00514
Sonnet 5 $0.00014 $0.00206
Haiku 4.5 $0.00007 $0.00103

Measured 10d ago against content hash 13cd700db7e3, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, 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 10d 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/skill-contracts/agent-risk-review/SKILL.md · 117 lines

How it starts

The opening of the file, as written. The whole thing — 117 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Agent risk review

Role

You are my agent-risk reviewer. I am considering giving an AI agent access to [system/tool/account].

Create a one-page permission brief with:

  1. Actions the agent is allowed to take.
  2. Actions the agent must ask approval for.
  3. Actions the agent is never allowed to take.
  4. Spending, data, or customer-impact limits.
  5. Required logs and where they should live.
  6. Failure scenarios and rollback steps.
  7. A first-week test plan using low-risk tasks.

Ask clarifying questions before finalizing if any permission is ambiguous.

Workflow

Run phases in order. Do not publish the final brief until Phase 3 passes.

Phase 0: Intake

  1. Extract the target from the user message: system, tool, account, environment, and principal (human or service identity).
  2. If the target is missing, ask one focused question before proceeding.
  3. Produce a one-paragraph scope summary: what the agent would touch, why access is needed, and who owns the decision.

Phase 1: Discovery

Ask structured clarifying questions (use AskQuestion when available). Cover what is not already answered:

  • Data classification (public, internal, PII, PHI, credentials)
  • Customer or production blast radius
  • Spend or rate limits
  • Existing IAM, API scopes, MCP servers, or tool bindings
  • Audit and compliance requirements
  • Incident and rollback owner
  • Read vs write vs admin intent

Aim for 4 to 8 non-obvious questions. Skip questions the user already answered.

Phase 2: Draft brief

Fill the Permission brief template below. Keep the deliverable one page (~500 to 900 words): prefer tables and bullets over long prose.

Apply Tiering rules while drafting:

  • Default deny for destructive, irreversible, or customer-facing production changes unless the user explicitly accepts risk with documented limits.
  • Approval required for: spend, credential rotation, data export, production writes, permission grants, merges, and deploys.
  • Never for: undeclared secret exfiltration, disabling audit logs, force-push to protected branches, and disabling security controls (unless the user documents an exception with compensating controls).

Read the full file on GitHub · 117 lines

Files

What ships with it

3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 10d ago First seen · 117 lines · 70 tokens per session scan A 13cd700db7e3

Subscribe to this mod's changes

agent-risk-review is a skill published in the GitHub repository emaraschio/cursor-commands (9 stars, last pushed 1mo ago), licensed MIT. It adds 70 tokens to every session and 1,028 once invoked, about $0.0003 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.

Related

Other skills, from other repositories

grok-build-supervisor

Initialize the persistent local proxy, then immediately ensure a visible Grok Build TUI for the current workspace when /grokexecute on activates, and continuously supervise that coding-agent session through a user-level Supervisor daemon as the user sends work, waits for completion, reconnects from another host task…

Vanyangyang/cursor-bridge · 103 tokens

cursor-delegate

Delegate bounded light-to-medium implementation, investigation, documentation, configuration, testing, and tooling work to Cursor Bridge after the primary agent owns direction and risk boundaries. Also use when the user explicitly asks to create, keep, continue, inspect, or close the same Cursor execution session…

Vanyangyang/cursor-bridge · 163 tokens

cce-routing

Use Cursor Bridge's read-only cursorcontextengine for unfamiliar project understanding when the exact code location is unknown or the task requires tracing behavior, symbols, callers and callees, data flow, registrations, interface implementations, ownership boundaries, or cross-module relationships. Trigger for…

Vanyangyang/cursor-bridge · 168 tokens

grok-executor-off

Explicitly disable Grok executor mode for this task without cancelling work or closing its terminal. Select this skill directly; no argument is required.

Vanyangyang/cursor-bridge · 34 tokens

grok-executor-on

Explicitly enable Grok executor mode for this task and prepare its visible terminal. Select this skill directly; no argument is required.

Vanyangyang/cursor-bridge · 32 tokens

design-review

Stress-test a plan or design against domain language, docs, and code. Ask hard questions one at a time. Update CONTEXT.md and ADRs as decisions crystallize. Use when you already have a draft plan or spec and want to find gaps before implementation.

netanelavr/dotcursor · 56 tokens