bernstein-approve

bernstein-approve is a skill for Cursor from sipyourdrink-ltd/bernstein. It costs 43 tokens per session (401 once invoked), scanned A, original, Apache-2.0.

A workflow for reviewing and deciding on pending Bernstein approvals, including proposed plans or completed agent tasks.

In plain words
What is it for?
Use it to list pending approvals, inspect task or plan summaries, approve or reject work, and confirm what happens after the decision.
Why use it?
It shows what needs approval together with changed files and test results, then records an approval or rejection with a reason.

Skill for Cursor

Written for Cursor: shipped in a Cursor plugin.

Part of the bernstein plugin — 8 skills shipped together

Good fit Use it to list pending approvals, inspect task or plan summaries, approve or reject work, and confirm what happens after the decision.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/sipyourdrink-ltd/bernstein/bernstein-approve
About the project

Bernstein is an open-source governance layer for AI agents that applies written policies, schedules agent work deterministically, controls approvals, and records verifiable execution history. It is used to coordinate CLI coding agents and other agent workloads, including parallel runs and offline review, while the catalogue entries provide its agent workflows and controls.

sipyourdrink-ltd/bernstein · 1,126 stars · on GitHub · bernstein.run

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 sipyourdrink-ltd/bernstein --skill bernstein-approve
Clone the repo
git clone --depth 1 https://github.com/sipyourdrink-ltd/bernstein

Made for: Cursor.

Or install bernstein, the plugin that ships this one along with the rest of its 8 skills.

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 bernstein-approve

README.md
[![agentmods](https://agentmods.dev/badge/skills/sipyourdrink-ltd/bernstein/bernstein-approve/github.svg)](https://agentmods.dev/skills/sipyourdrink-ltd/bernstein/bernstein-approve)
Your own site
<a href="https://agentmods.dev/skills/sipyourdrink-ltd/bernstein/bernstein-approve"><img src="https://agentmods.dev/badge/skills/sipyourdrink-ltd/bernstein/bernstein-approve/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 bernstein-approve

Your own site · 80×15
<a href="https://agentmods.dev/skills/sipyourdrink-ltd/bernstein/bernstein-approve"><img src="https://agentmods.dev/badge/skills/sipyourdrink-ltd/bernstein/bernstein-approve.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 43 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 401 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 $0.00043 $0.00401
Opus 5 $0.00022 $0.00200
Sonnet 5 $0.00009 $0.00080
Haiku 4.5 $0.00004 $0.00040

Measured 9d ago against content hash fbd9a881bfe9, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

bernstein-approve 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.

The scan reads SKILL.md. This mod also ships 1 executable file (scripts/approvals.sh), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

packages/cursor-plugin/skills/bernstein-approve/SKILL.md · 55 lines

What it actually says

Bernstein Approvals

Review pending approvals and plans, then approve or reject them.

When to Use

  • User asks "any pending approvals?" or "what needs my review?"
  • User wants to approve or reject a completed task
  • User wants to review and approve/reject a plan before agents execute it
  • User says "approve that" or "reject task X"

Instructions

List pending approvals

  1. Run scripts/approvals.sh list to fetch pending approvals and plans.
  2. Present each item with its diff summary and test results:
## Pending Approvals

### Task TASK-042: Fix auth middleware
**Agent:** claude-backend-01 | **Role:** backend
**Files changed:** src/auth/middleware.py (+42 -8)
**Tests:** 14/14 passing

[Approve] [Reject]

Approve or reject

  1. When the user decides:

    • Approve: scripts/approvals.sh approve <task_id> "reason"
    • Reject: scripts/approvals.sh reject <task_id> "reason"
  2. For plans (multi-task proposals):

    • List plans: scripts/approvals.sh plans
    • Approve plan: scripts/approvals.sh approve-plan <plan_id>
    • Reject plan: scripts/approvals.sh reject-plan <plan_id>

After approval

  1. Confirm the action and note what happens next:
    • Approved tasks → agent commits and merges
    • Approved plans → planned tasks promoted to open, agents start picking them up
    • Rejected → task goes back to open for retry, or gets cancelled
Files

What ships with it

1 file 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. 9d ago First seen · 55 lines · 43 tokens per session scan A fbd9a881bfe9

Subscribe to this mod's changes

bernstein-approve is a skill published in the GitHub repository sipyourdrink-ltd/bernstein (1,126 stars, last pushed today), licensed Apache-2.0. It adds 43 tokens to every session and 401 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.

Related

Other skills, from other repositories

ara-research-manager

Records research provenance as a post-task epilogue, scanning conversation history at the end of a coding or research session to extract decisions, experiments, dead ends, claims, heuristics, and pivots, and writing them into the ara/ directory with user-vs-AI provenance tags. Use as a session epilogue — never during…

Orchestra-Research/AI-Research-SKILLs · 91 tokens

where

Present-tense orientation — where everything stands right now, answered from what is already in context plus one scoped read of this session's Neotoma tasks, so work that aged out of the window is still reported. What is running, what just landed, what is waiting on the operator and why it is theirs, and one…

markmhendrickson/neotoma · 147 tokens

process_issues

Use this skill to work the Neotoma issue queue end-to-end.

markmhendrickson/neotoma · 6 tokens

close-session

Archive the working session at the end. Writes a sessionclose record to the state layer, logs every outbound interaction as a first-class row, writes task entities for follow-ups, and writes a project-level task ledger as a human-readable safety net. Run at the end of every working session to ensure nothing is lost.

markmhendrickson/neotoma · 66 tokens

remember-meetings

Import meeting transcripts and extract decisions, action items, attendees, and commitments into persistent memory.

markmhendrickson/neotoma · 23 tokens

Create /new-project Claude Code skill

Claude Code skill wrapping fw init/setup for in-session guided onboarding. Agent says /new-project, skill walks through setup interactively. Source: T-294 Phase 3 item T-N, uncaptured during dialogue.

DimitriGeelen/agentic-engineering-framework · 51 tokens