Agent skill · Audited from source
comments
skill · anthropics/claude-for-legalApache-2.0 licenceAudited 13 Nov 2026 · source cb488a888d20
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…
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
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
| Layer | What we check | Result | Findings |
|---|---|---|---|
L0 Provenance | Repo owner, licence, archive status, activity | PASS | 0 |
L1 Static source | Secrets, path traversal, supply chain, hidden code | NA | 0 |
L2 Instructions | Prompt injection, authority framing, hidden directives | PASS | 0 |
L3 Inventory | The files and declarations match the source | PASS | 0 |
L4 Sandbox | Run in isolation and watch behaviour | SKIPPED why | 0 |
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
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
- ✓SAFE B 89 / 100
first audit · source
cb488a888d20
README badge
For maintainers · shows the latest audit
[](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
mattpocock/skills
Implement a piece of work based on a spec or set of tickets.
mattpocock/skills
Compact the current conversation into a handoff document for another agent to pick up.
mattpocock/skills
Pursue a long-running goal in a single session by co-ordinating subagents.
Add this badge to your README
[](https://modelsatlas.com/skills/anthropics/comments/)
<a href="https://modelsatlas.com/skills/anthropics/comments/"><img src="https://modelsatlas.com/skills/anthropics/comments/badge.svg" alt="ModelsAtlas: SAFE B"></a>
Questions about comments
What does the comments skill do?
Is comments safe to install?
What can comments access on my machine?
How current is this page?
Sources
- github.com/anthropics/claude-for-legal/tree/main/regulatory-lega — the audited source at commit cb488a888d20 and every finding aboveObserved · 13 Nov 2026
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.
- What does the comments skill do?
- Is comments safe to install?
- What can comments access on my machine?