Agent skill · Audited from source
closing-checklist
skill · anthropics/claude-for-legalApache-2.0 licenceAudited 31 Oct 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: What's blocking close — maintain the closing checklist with status, critical path, and days to close. Self-updating: ingests new items from diligence findings and schedule builds, tracks status, surfaces what's…
Cite
Cite this page
ModelsAtlas. “closing-checklist (anthropics/claude-for-legal)”. Retrieved 31 Oct 2026. https://modelsatlas.com/skills/anthropics/closing-checklist
Trust audit
Audit 0.4.1 · source read 31 Oct 2026
SAFE means nothing in the source contradicts what the skill says it does. Grade B is shared by 16,667 of 17,602 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 · 31 Oct 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/corporate-legal/skills/closing-checklistThe 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 2 days ago
- Sandboxed runNot runSkills are read, not executed; layer L4 is skipped
What it tells the agent
Full source on GitHub ↗Its description: What's blocking close — maintain the closing checklist with status, critical path, and days to close. Self-updating: ingests new items from diligence findings and schedule builds, tracks status, surfaces what's…
---
name: closing-checklist
description: >
What's blocking close — maintain the closing checklist with status, critical
path, and days to close. Self-updating: ingests new items from diligence
findings and schedule builds, tracks status, surfaces what's blocking. Use
when user says "closing checklist", "what's left to close", "checklist
status", "add to the checklist", or on a scheduled status pull.
argument-hint: "[optional: item ID + status update]"
---
# /closing-checklist
1. Read `~/.claude/plugins/config/claude-for-legal/corporate-legal/deals/[code]/closing-checklist.yaml` and use the modes below.
2. If status update provided: Mode 3 (update item).
3. Otherwise Mode 4: blocking items, critical path, days to close.
---
## Matter context
**Matter context.** Check `## Matter workspaces` in the practice-level CLAUDE.md. If `Enabled` is `✗` (the default for in-house users), skip the rest of this paragraph — skills use practice-level context and the matter machinery is invisible. If enabled and there is no active matter, ask: "Which matter is this for? Run `/corporate-legal:matter-workspace switch <slug>` or say `practice-level`." Load the active matter's `matter.md` for matter-specific context and overrides. Write outputs to the matter folder at `~/.claude/plugins/config/claude-for-legal/corporate-legal/matters/<matter-slug>/`. Never read another matter's files unless `Cross-matter context` is `on`.
---
## Purpose
Deals close when the checklist is done. Everything on it, done. Nothing missing. This skill maintains the list, ingests new items as they surface from diligence, and tells the team what's blocking.
## The checklist
Lives at `~/.claude/plugins/config/claude-for-legal/corporate-legal/deals/[code]/closing-checklist.yaml`. Structure:
```yaml
deal_code: "Project Falcon"
target_close: [DATE]
signing_date: [DATE]
last_updated: [DATE]
conditions_precedent:
- id: CP-001
item: "HSR waiting period expiration"
category: "Regulatory"
responsible: "Buyer counsel"
due: 2026-04-15
status: "Filed 2026-03-01, waiting period runs"
blocking: true
source: "Purchase Agreement §7.1(a)"
- id: CP-002
item: "Acme Corp consent to assignment"
category: "Third-party consents"
responsible: "Target — Jane Doe"
due: 2026-04-20
status: "Request sent 2026-03-10, no response"
blocking: true
source: "Schedule 3.12(a)(4); Acme MSA §14.2"
closing_deliverables:
- id: CD-001
item: "Certificate of good standing — Target (DE)"
category: "Corporate"
responsible: "Target counsel"
due: 2026-04-28
status: "Not started"
blocking: true
source: "Purchase Agreement §2.3(b)(iv)"
# ... etc
```
## Modes
### Mode 1: Initialize from the purchase agreement
Read the signed (or near-final) purchase agreement. Extract:
- Every condition precedent (location varies by agreement — read the actual section headings)
- Every closing deliverable (closing deliverables schedule or corresponding section)
- Every covenant with a pre-closing deadline
Each becomes a checklist item with a source cite to the agreement section.
**Research obligations before populating regulatory/approval items.** Antitrust, foreign-investment, and sector-specific approvals (for example, HSR-style filings, CFIUS, industry regulators) have jurisdiction-specific mechanics, thresholds, and timing windows that change. Extract the name of each regulatory condition from the PA, then research the currently operative mechanics (who files, when, what triggers a second request, what the waiting period is). Cite primary sources and verify currency. Do not populate a timing assumption from memory.
**Material-adverse-effect / material-adverse-change closing conditions.** Pull the defined term from the PA — MAC/MAE framing is negotiated, not a standard. Research the governing-law interpretation of the specific language used (Delaware, New York, and other jurisdictions treat carve-outs and quantitative tests differently) before flagging an event as a potential MAC trigger.
**Consent-requirement extraction from material contracts** depends on governing-law default rules and the specific anti-assignment language in each contract. Research the applicable rule per contract rather than assuming a default.
### Mode 2: Ingest from diligence (the "self-updating" part)
Mode 2 is triggered when an upstream skill produces a finding with a pre-closing action. The upstream skills and output types this mode ingests:
- **`diligence-issue-extraction` findings** — any finding flagged for a closing action (consent, shareholder vote, board resolution, regulatory filing, release, escrow mechanic, pay-off letter). Not just "consents" — see the extraction skill's Handoffs section for the full list.
- **`material-contract-schedule` CoC / assignment items** — change-of-control provisions, anti-assignment clauses, MFN triggers surfaced during schedule build.
- **`deal-team-summary` output** — the exec-tier brief aggregates extraction findings and sometimes surfaces a closing-action item that a mechanical read of the individual extraction memos would miss (e.g., a §280G cleansing vote rolled up across multiple employment agreements, or a composite consent package). Mode 2 reads the latest deal-team-summary in the deal folder and reconciles its closing-action items against the checklist. Anything flagged by deal-team-summary as requiring pre-closing action that is not already on the checklist is appended.
The handoff schema covers the full range of pre-closing actions, not just consents:
```yaml
handoff:
# Required fields
item: "[Counterparty or action, one line]"
category: "[Third-party consents | Shareholder / board action | Regulatory filing | Release / termination | Escrow / holdback | Closing deliverable]"
source: "[Contract name / statutory section / VDR path + Bates]"
blocking: true # unless the agreement has a materiality qualifier
severity: "[🔴 / 🟠 / 🟡 / 🟢 — caExcerpt, first 6,004 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/closing-checklist/)
The badge shows our verdict and grade for this skill, and links back to this page. It changes when the audit does.
Similar skills
obra/superpowers
Use when creating new skills, editing existing skills, or verifying skills work before deployment
mattpocock/skills
A relentless interview to sharpen a plan or design, which also creates docs (ADR's and glossary) as we go.
mattpocock/skills
Grill the user relentlessly about a plan, decision, or idea. Use when the user wants to stress-test their thinking, or uses any 'grill' trigger phrases.
Add this badge to your README
[](https://modelsatlas.com/skills/anthropics/closing-checklist/)
<a href="https://modelsatlas.com/skills/anthropics/closing-checklist/"><img src="https://modelsatlas.com/skills/anthropics/closing-checklist/badge.svg" alt="ModelsAtlas: SAFE B"></a>
Questions about closing-checklist
What does the closing-checklist skill do?
Is closing-checklist safe to install?
What can closing-checklist access on my machine?
How current is this page?
Sources
- github.com/anthropics/claude-for-legal/tree/main/corporate-legal — the audited source at commit cb488a888d20 and every finding aboveObserved · 31 Oct 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 closing-checklist skill do?
- Is closing-checklist safe to install?
- What can closing-checklist access on my machine?