Live survey304 models · 14 providers · 23,592 auditsAudited implement · SAFE →What changedHow we verifyllms.txt

Agent skill · Audited from source

comments

skill · anthropics/claude-for-legalApache-2.0 licenceAudited 13 Nov 2026 · source cb488a888d20

★ 9,993pushed 4 days ago
✓SAFEGrade B · 89/100 · 13 Nov 2026 · cb488a8
9,993repo stars · whole anthropics/claude-for-legal

Is it safe? Yes — SAFE, grade B (89/100). We read this skill's source at commit cb488a888d20 and found no filesystem, network or shell access and no hard-coded secrets. What it does: Review open NPRM comment periods, log decisions, track deadlines. Use when an NPRM has a comment window open and you need to surface deadlines, decide whether to file, or record a filing / not-filing / waived decision…

Ask an AI about this pageGChatGPTCClaudePPerplexityGeGeminiXGrok
More
Cite

Cite this page

ModelsAtlas. “comments (anthropics/claude-for-legal)”. Retrieved 13 Nov 2026. https://modelsatlas.com/skills/anthropics/comments

Trust audit

Audit 0.4.1 · source read 13 Nov 2026

Trust score89/100✓SAFE B
0 critical0 high0 medium0 low0 info

SAFE means nothing in the source contradicts what the skill says it does. Grade B is shared by 17,406 of 18,389 audited skills.

What the source does

  • FilesystemNone observedNo reads or writes in the source
  • NetworkNone observedNo outbound calls in the source
  • 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 codeNA0
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 (0)

No findings at any severity. We re-audit when the source changes.

Audit 0.4.1 · source sha cb488a888d20 · 13 Nov 2026Report an issue or request a re-scan

Provenance

Who published it, and what the verdict is pinned to

  • Publisheranthropics GitHub organizationOwner of the repository this skill is read from
  • Source folderanthropics/claude-for-legal/regulatory-legal/skills/commentsThe exact folder we audited
  • LicenceApache-2.0As the repository states it
  • Commit pinned for this verdictcb488a888d20A new audit runs when the source changes
  • Repository statusNot archivedLast push 4 days ago
  • Sandboxed runNot runSkills are read, not executed; layer L4 is skipped

What it tells the agent

Full source on GitHub ↗

Its description: Review open NPRM comment periods, log decisions, track deadlines. Use when an NPRM has a comment window open and you need to surface deadlines, decide whether to file, or record a filing / not-filing / waived decision…

---
name: comments
description: Review open NPRM comment periods, log decisions, track deadlines. Use when an NPRM has a comment window open and you need to surface deadlines, decide whether to file, or record a filing / not-filing / waived decision (--decide CMT-ID).
argument-hint: "[optional: --decide CMT-ID]"
---

# /comments

## Purpose

NPRMs have deadlines. The decision to file a comment or not is an attorney
call — but the deadline disappearing without a logged decision is the risk.
This skill surfaces open comment periods and records decisions.

## Load context

`~/.claude/plugins/config/claude-for-legal/regulatory-legal/comment-tracker.yaml` → all tracked NPRMs and their status.
`~/.claude/plugins/config/claude-for-legal/regulatory-legal/CLAUDE.md` → default comment decision owner.

## Default view — open comment periods

```markdown
## Comment Period Tracker — [date]

### ⏰ Deadline in <14 days

| ID | Regulation | Deadline | Days left | Decision | Owner |
|---|---|---|---|---|---|
| CMT-001 | [name] | [date] | [N] | Undecided | [owner] |

### 🟡 Open (>14 days)

[same table]

### Recently decided

| ID | Regulation | Decision | Rationale |
|---|---|---|---|
| CMT-002 | [name] | Not filing | [reason] |

---

**Total open:** [N]  **Undecided with deadline <30 days:** [N]
```

## Log a decision

```
/regulatory-legal:comments --decide CMT-001
Decision: [filing / not-filing / waived]
Rationale: "[brief — e.g., 'Rule doesn't apply to our model' or 'Filing comment on Section 3']"
```

Updates tracker. If decision is "filing": prompt for filing deadline reminder
(comment deadline minus 5 business days for internal review).

## Notifications

On first detection of an NPRM (populated by reg-feed-watcher): Slack DM to
comment decision owner if Slack MCP is configured and `owner_slack` is set.

Reminder at 14 days before deadline if decision is still "undecided."
Reminder at 3 days before deadline if still undecided — elevated urgency.

## Consequential-action gate (submit a regulatory comment / respond to a regulator)

**Before logging a decision as "filing" — and always before producing a comment letter or regulator-response draft for submission:** Read `## Who's using this` in ~/.claude/plugins/config/claude-for-legal/regulatory-legal/CLAUDE.md. If the Role is **Non-lawyer**:

> Submitting a comment or response to a regulator has legal consequences. It's a public statement of the company's position, it's on the record in the rulemaking or enforcement matter, and positions taken here bind the company and can be used against it in subsequent proceedings. Have you reviewed this with an attorney? If yes, proceed. If no, here's a brief to bring to them:
>
> - The rulemaking or inquiry (regulator, docket, deadline)
> - What the proposed comment/response says and on what sections
> - Open questions and what's unresolved
> - What could go wrong (adverse admissions, inconsistent prior positions, coordination-of-comment concerns with trade associations)
> - What to ask the attorney (should we file at all; should we file jointly through a trade group; are there positions we should not take)
>
> If you need to find a lawyer: your professional regulator's referral service is the fastest starting point (state bar in the US; SRA/Bar Standards Board in England & Wales; Law Society in Scotland/NI/Ireland/Canada/Australia; or your jurisdiction's equivalent).

Do not log a "filing" decision or produce a submission-ready draft past this gate without an explicit yes. Tracking views, deadline reminders, and "not-filing / waived" decisions do not require the gate.

---

## What this skill does not do

- Draft the comment letter. That is a separate attorney task.
- Make the filing decision. It tracks the decision; the attorney makes it.
- Monitor post-comment activity. Once a decision is filed, this tracker's job
  is done — follow the rulemaking through `/regulatory-legal:reg-feed-watcher`.

> The `comment-decision` `gap_type` semantics, the per-send Slack confirmation rule, and the comment-tracker.yaml schema live in the **gap-surfacer** reference skill — load it before doing substantive work.

Excerpt, first 4,151 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 cb488a8

Download folder ↗
git clone https://github.com/anthropics/claude-for-legal
git -C claude-for-legal checkout cb488a888d20

The author documents no install command, so this uses the repository directly. Our verdict covers commit cb488a888d20 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 cb488a888d20

README badge

For maintainers · shows the latest audit

ModelsAtlas: SAFE BMODELSATLASSAFE · B
[![ModelsAtlas: SAFE B](https://modelsatlas.com/skills/anthropics/comments/badge.svg)](https://modelsatlas.com/skills/anthropics/comments/)

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/anthropics/comments/badge.svg)](https://modelsatlas.com/skills/anthropics/comments/)

Questions about comments

What does the comments skill do?
A suite of plugins for legal workflows
Is comments 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 comments 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 (cb488a888d20), read on 2026-11-13. 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.