Atlas / Skills / anthropics / Brief

BriefSAFE

skills/anthropics/brief

Open source repository of plugins primarily intended for knowledge workers to use in Claude Cowork

Verdict
SAFE
Grade
B
Trust score
89 /100
Version
—
Hosts
—
License
Apache-2.0
Stars
33,432
01

Overview

Open source repository of plugins primarily intended for knowledge workers to use in Claude Cowork

Read from source at commit fbc0c4cf804eOBSERVED · 2026-10-28
Advertisement
02

What it tells the agent

The instruction file, verbatim from the audited commit — this is the text the model reads, and the surface the audit's instruction layer examines. Quoted here so you can judge it without cloning anything.

---
name: brief
description: Generate contextual briefings for legal work — daily summary, topic research, or incident response. Use when starting your day and need a scan of legal-relevant items across email, calendar, and contracts, when researching a specific legal question across internal sources, or when a developing situation (data breach, litigation threat, regulatory inquiry) needs rapid context.
argument-hint: "[daily | topic <query> | incident]"
---

# /brief -- Legal Team Briefing

> If you see unfamiliar placeholders or need to check which tools are connected, see [CONNECTORS.md](../../CONNECTORS.md).

Generate contextual briefings for legal work. Supports three modes: daily brief, topic brief, and incident brief.

**Important**: This command assists with legal workflows but does not provide legal advice. Briefings should be reviewed by qualified legal professionals before being relied upon.

## Invocation

```
/brief daily              # Morning brief of legal-relevant items
/brief topic [query]      # Research brief on a specific legal question
/brief incident [topic]   # Rapid brief on a developing situation
```

If no mode is specified, ask the user which type of brief they need.

## Modes

---

### Daily Brief

A morning summary of everything a legal team member needs to know to start their day.

#### Sources to Scan

Check each connected source for legal-relevant items:

**Email (if connected):**
- New contract requests or review requests
- Compliance questions or reports
- Responses from counterparties on active negotiations
- Flagged or urgent items from the legal team inbox
- External counsel communications
- Regulatory or legal update newsletters

**Calendar (if connected):**
- Today's meetings that need legal prep (board meetings, deal reviews, vendor calls)
- Upcoming deadlines this week (contract expirations, filing deadlines, response deadlines)
- Recurring legal team syncs

**Chat (if connected):**
- Overnight messages in legal team channels
- Direct messages requesting legal input
- Mentions of legal-relevant topics (contract, compliance, privacy, NDA, terms)
- Escalations or urgent requests

**CLM (if connected):**
- Contracts awaiting review or signature
- Approaching expiration dates (next 30 days)
- Newly executed agreements

**CRM (if connected):**
- Deals moving to stages that require legal involvement
- New opportunities flagged for legal review

#### Output Format

```
## Daily Legal Brief -- [Date]

### Urgent / Action Required
[Items needing immediate attention, sorted by urgency]

### Contract Pipeline
- **Awaiting Your Review**: [count and list]
- **Pending Counterparty Response**: [count and list]
- **Approaching Deadlines**: [items due this week]

### New Requests
[Contract review requests, NDA requests, compliance questions received since last brief]

### Calendar Today
[Meetings with legal relevance and what prep is needed]

### Team Activity
[Key messages or updates from legal team channels]

### This Week's Deadlines
[Upcoming deadlines and filing dates]

### Sources Not Available
[Any sources that were not connected or returned errors]
```

---

### Topic Brief

Research and brief on a specific legal question or topic across available sources.

#### Workflow

1. Accept the topic query from the user
2. Search across connected sources:
   - **Documents**: Internal memos, prior analyses, playbooks, precedent
   - **Email**: Prior communications on the topic
   - **Chat**: Team discussions about the topic
   - **CLM**: Related contracts or clauses
3. Synthesize findings into a structured brief

#### Output Format

```
## Topic Brief: [Topic]

### Summary
[2-3 sentence executive summary of findings]

### Background
[Context and history from internal sources]

### Current State
[What the organization's current position or approach is, based on available documents]

### Key Considerations
[Important factors, risks, or open questions]

### Internal Precedent
[Prior decisions, memos, or positions found in internal sources]

### Gaps
[What information is missing or what sources were not available]

### Recommended Next Steps
[What the user should do with this information]
```

#### Important Notes
- Topic briefs synthesize what is available in connected sources; they do not substitute for formal legal research
- If the topic requires current legal authority or case law, recommend the user consult a legal research platform (Westlaw, Lexis, etc.) or outside counsel
- Always note the limitations of the sources searched

---

### Incident Brief

Rapid briefing for developing situations that require immediate legal attention (data breaches, litigation threats, regulatory inquiries, IP disputes, etc.).

#### Workflow

1. Accept the incident topic or description
2. Rapidly scan all connected sources for relevant context:
   - **Email**: Communications about the incident
   - **Chat**: Real-time discussions and escalations
   - **Documents**: Relevant policies, response plans, insurance coverage
   - **Calendar**: Scheduled response meetings
   - **CLM**: Affected contracts, indemnification provisions, insurance requirements
3. Compile into an actionable incident brief

#### Output Format

```
## Incident Brief: [Topic]
**Prepared**: [timestamp]
**Classification**: [severity assessment if determinable]

### Situation Summary
[What is known about the incident]

### Timeline
[Chronological summary of events based on available sources]

### Immediate Legal Considerations
[Regulatory notification requirements, preservation obligations, privilege concerns]

### Relevant Agreements
[Contracts, insurance policies, or other agreements that may be implicated]

### Internal Response
[What response activity has already occurred based on email/chat]

### Key Contacts
[Relevant internal and external contacts identified from sources]

### Recommended Immediate Actions
1. [Most urgent action]
2. [Second priority]
3. [etc.]

### Information Gaps
[What is not yet known and ne
03

Trust audit

SAFEgrade B · trust 89/100 Nothing in the source contradicts what it says it does. Grade A is reserved for packages that have also passed the behavioural sandbox.

LayerWhat it checksResult
L0Provenance & inventoryPASS
L1Static analysis of the codeNA
L2Instruction surface (what it tells the agent)PASS
L3Class-specific surfacePASS
L4Behavioural (sandbox)SKIPPED

What the source does

Filesystem
none-observed
Network
none-observed
Shell
none-observed
Dependencies
pinned
Secrets in source
none-found

Findings (0)

No findings outside the package's declared scope.

Gates applied: no_behavioural_pass.

Audited 2026-10-28 · audit v0.4.1 · source sha fbc0c4cf804efull audit observations/trust-audit/skill/anthropics__brief.json · Report an issue / request a re-scan
04

Audit history

Every audit this skill has had.

DateSourceVerdictGradeScoreChange
2026-10-28fbc0c4cf804eSAFEB89first audit
05

Questions

What does the brief — anthropics/knowledge-work-plugins skill do?

Open source repository of plugins primarily intended for knowledge workers to use in Claude Cowork

Is brief — anthropics/knowledge-work-plugins 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 brief — anthropics/knowledge-work-plugins access on my machine?

The audit observed no filesystem, network or shell use at all in its source.

How current is this page?

The grade is for one exact copy of the source (fbc0c4cf804e), read on 2026-10-28. The repository is watched, and a new audit runs when it changes — this is the first audit.

Add this badge to your README

Shows this page's audit result and links back to it. It updates when the audit does.

ModelsAtlas audit badge

Markdown
[![ModelsAtlas audit: Brief](https://modelsatlas.com/skills/anthropics/brief/badge.svg)](https://modelsatlas.com/skills/anthropics/brief/)

Not your listing, or something out of date? Claim or update your listing.

Advertisement