Agent skill · Audited from source

Bernstein Plan

skill · sipyourdrink-ltd/bernsteinApache-2.0 licenceAudited 14 Oct 2026 · source 6ba64a7d2489

★ 1,237pushed today
✓SAFEGrade B · 89/100 · 14 Oct 2026 · 6ba64a7
1,237repo stars · whole sipyourdrink-ltd/bernstein

Is it safe? Yes — SAFE, grade B (89/100). We read this skill's source at commit 6ba64a7d2489 and observed network access and no hard-coded secrets. What it does: Create and manage multi-step execution plans in Bernstein. Plans decompose complex goals into stages with dependencies. Use when the user wants to plan a complex feature, break down a large task, or review an execution…

Ask an AI about this pageGChatGPTCClaudePPerplexityGeGeminiXGrok
More
Cite

Cite this page

ModelsAtlas. “Bernstein Plan (sipyourdrink-ltd/bernstein)”. Retrieved 14 Oct 2026. https://modelsatlas.com/skills/sipyourdrink-ltd/bernstein-plan

Trust audit

Audit 0.4.1 · source read 14 Oct 2026

Trust score89/100✓SAFE B
0 critical0 high1 medium0 low0 info

SAFE means nothing in the source contradicts what the skill says it does. Grade B is shared by 13,985 of 14,816 audited skills.

What the source does

  • FilesystemNone observedNo reads or writes in the source
  • NetworkDeclared4 observations
  • ShellNone observedNo commands run in the source
  • DependenciesPinnedNothing floats
  • SecretsNone foundNo keys in source

Five audit layers

LayerWhat we checkResultFindings
L0 ProvenanceRepo owner, licence, archive status, activityPASS0
L1 Static sourceSecrets, path traversal, supply chain, hidden codeWARN1
L2 InstructionsPrompt injection, authority framing, hidden directivesPASS0
L3 InventoryThe files and declarations match the sourcePASS0
L4 SandboxRun in isolation and watch behaviourSKIPPED why0

Gates applied: no behavioural pass.

Findings (1)

MEDIUMNetwork egressnet.raw_ip · scripts/plan.sh:6
F-04 Network egressCWE-200 · CWE-319Layer L1
API="${BERNSTEIN_API_URL:-http://127.0.0.1:8052}"
Why
No further detail recorded for this rule.
Fix
—

Audit 0.4.1 · source sha 6ba64a7d2489 · 14 Oct 2026Report an issue or request a re-scan

Provenance

Who published it, and what the verdict is pinned to

  • Publishersipyourdrink-ltd GitHub organizationOwner of the repository this skill is read from
  • Source foldersipyourdrink-ltd/bernstein/packages/cursor-plugin/skills/bernstein-planThe exact folder we audited
  • LicenceApache-2.0As the repository states it
  • Commit pinned for this verdict6ba64a7d2489A new audit runs when the source changes
  • Repository statusNot archivedPushed today
  • Sandboxed runNot runSkills are read, not executed; layer L4 is skipped

What it tells the agent

Full source on GitHub ↗

Its description: Create and manage multi-step execution plans in Bernstein. Plans decompose complex goals into stages with dependencies. Use when the user wants to plan a complex feature, break down a large task, or review an execution…

---
name: bernstein-plan
description: >
  Create and manage multi-step execution plans in Bernstein. Plans decompose
  complex goals into stages with dependencies. Use when the user wants to
  plan a complex feature, break down a large task, or review an execution plan
  before agents start working.
---

# Bernstein Plan Mode

Create structured execution plans that get human approval before agents start.

## When to Use

- User describes a complex feature: "implement user authentication with OAuth"
- User wants to break down a large task into stages
- User says "plan this out" or "create a plan for..."
- User wants to review what agents will do before they start

## Instructions

### Creating a plan

1. Analyze the user's request and decompose it into stages and tasks.
2. Write a plan YAML file using this structure:

```yaml
name: "{descriptive plan name}"
description: "{what this plan achieves}"
stages:
  - name: foundation
    steps:
      - goal: "Create database models for user and session"
        role: backend
        scope: small
        complexity: low
      - goal: "Add migration scripts"
        role: backend
        scope: tiny

  - name: implementation
    depends_on: [foundation]
    steps:
      - goal: "Implement OAuth2 flow with Google provider"
        role: backend
        scope: medium
        complexity: medium
      - goal: "Create login/signup UI components"
        role: frontend
        scope: medium

  - name: verification
    depends_on: [implementation]
    steps:
      - goal: "Write integration tests for auth flow"
        role: qa
        scope: medium
      - goal: "Security review of token handling"
        role: security
        scope: small
```

3. Save the plan to `plans/{plan-name}.yaml` in the project root.
4. Tell the user to execute it: `bernstein run plans/{plan-name}.yaml`

### Or submit via API

5. Run `scripts/plan.sh submit plans/{plan-name}.yaml` to submit for approval.
6. The plan enters `pending` state - use `/bernstein-approve` to review and approve.
7. Once approved, planned tasks promote to `open` and agents start picking them up.

### Reviewing plans

8. Run `scripts/plan.sh list` to see all plans and their status.
9. Show the plan with stages, dependencies, and estimated cost/time.

## Tips

- Keep stages to 2-5 tasks each
- Use `depends_on` to enforce ordering (foundation before implementation)
- Assign appropriate roles: backend, frontend, qa, security, devops, docs
- Mark risky tasks with `complexity: high` - they'll get more capable models
- Foundation stages should be `tiny` or `small` scope

Excerpt, first 2,593 characters of SKILL.md, verbatim from the audited commit. It is text from someone else’s repository, quoted so you can judge it before your agent reads it.

Install

Pinned to the audited commit 6ba64a7

Download folder ↗
git clone https://github.com/sipyourdrink-ltd/bernstein
git -C bernstein checkout 6ba64a7d2489

The author documents no install command, so this uses the repository directly. Our verdict covers commit 6ba64a7d2489 only.

Works in

The author has not said which agents this skill supports, and we have not tested it in any.

Audit history

Every audit, every source change

  1. ✓SAFE B 89 / 100

    first audit · source 6ba64a7d2489

README badge

For maintainers · shows the latest audit

ModelsAtlas: SAFE BMODELSATLASSAFE · B
[![ModelsAtlas: SAFE B](https://modelsatlas.com/skills/sipyourdrink-ltd/bernstein-plan/badge.svg)](https://modelsatlas.com/skills/sipyourdrink-ltd/bernstein-plan/)

The badge shows our verdict and grade for this skill, and links back to this page. It changes when the audit does.

Similar skills

Add this badge to your README

[![ModelsAtlas: SAFE B](https://modelsatlas.com/skills/sipyourdrink-ltd/bernstein-plan/badge.svg)](https://modelsatlas.com/skills/sipyourdrink-ltd/bernstein-plan/)

Questions about Bernstein Plan

What does the Bernstein Plan skill do?
The open-source governance layer for AI agents: write the rules declaratively, Bernstein enforces them and produces the verifiable, replayable record. Free, Apache-2.0. https://bernstein.run
Is Bernstein Plan safe to install?
The audit found nothing in the source that contradicts what it says it does, and graded it B (89/100). Grade A is held back for packages that have also passed a sandboxed behavioural run, which is why a clean skill reads B.
What can Bernstein Plan access on my machine?
The audit observed that it reaches the network. Each of those is consistent with what it says it does. Secrets in the source: none found.
How current is this page?
The grade is for one exact copy of the source (6ba64a7d2489), read on 2026-10-14. The repository is watched, and a new audit runs when it changes — this is the first audit.

Sources

Spotted something wrong? Report a correction · Methodology

Keep going in your AI

Opens with this page as the source. We add nothing else to the prompt.