Agent skill · Audited from source
client-comms-log
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: Log a client communication — call, email, text, letter, in-person, voicemail. Append-only per-case record with dated entries, direction, medium, summary, action items. Works alongside /client-letter and /status client.…
Cite
Cite this page
ModelsAtlas. “client-comms-log (anthropics/claude-for-legal)”. Retrieved 31 Oct 2026. https://modelsatlas.com/skills/anthropics/client-comms-log
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/legal-clinic/skills/client-comms-logThe 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 1 day ago
- Sandboxed runNot runSkills are read, not executed; layer L4 is skipped
What it tells the agent
Full source on GitHub ↗Its description: Log a client communication — call, email, text, letter, in-person, voicemail. Append-only per-case record with dated entries, direction, medium, summary, action items. Works alongside /client-letter and /status client.…
---
name: client-comms-log
description: >
Log a client communication — call, email, text, letter, in-person, voicemail.
Append-only per-case record with dated entries, direction, medium, summary,
action items. Works alongside /client-letter and /status client. Use when
logging a call or client email, reviewing a communication log, or asking
"what did we tell [client] last time".
argument-hint: "[case-id] [--add (default) | --read | --summary | --patterns]"
---
# /client-comms-log
1. Use the workflow below.
2. Require case-id (prompt if not provided).
3. Route by flag:
- `--add` (default): capture direction, medium, student, summary, action items, follow-up due. Confirm with user. Append (prepend most-recent-first) to `~/.claude/plugins/config/claude-for-legal/legal-clinic/client-comms/[case-id]/log.md`.
- `--read`: show the most recent N entries.
- `--summary`: one-paragraph condensed read.
- `--patterns`: scan for unanswered comms, missed follow-ups, language gaps, tone shifts, contact gaps. Supervision-oriented.
4. Integration: offer `/legal-clinic:deadlines --add` if the log establishes a deadline; route to `/legal-clinic:semester-handoff` via `--summary` when relevant.
---
# Client Communications Log
## Purpose
Four reasons to keep this log:
1. **Malpractice defense.** If a client claims "no one ever told me [X]," a dated entry showing otherwise is the answer. Clinical professors carry professional liability on student work; contemporaneous records protect them.
2. **Continuity at handoff.** The next semester's student takes over and reads the log; they don't re-ask the client questions already answered.
3. **Supervision visibility.** Five unreturned voicemails over six weeks is a pattern. The log makes patterns visible that individual students might not flag on their own.
4. **File retention.** Law school clinics have obligations to maintain complete client files. Communication history is part of that.
Light. Append-only. The student's job is to write a two-sentence entry after every contact; the skill formats it and appends.
## Load context
- `~/.claude/plugins/config/claude-for-legal/legal-clinic/client-comms/[case-id]/log.md` (if exists) — append target
- `~/.claude/plugins/config/claude-for-legal/legal-clinic/CLAUDE.md` → not heavily read; this skill is case-scoped
## Modes
Flag: `--add | --read | --summary | --patterns` (default: add)
### `--add` (default) — log a new entry
**Inputs:**
- Case ID (required — which case)
- Date + time (default: now)
- Direction: `in` (client → clinic) | `out` (clinic → client)
- Medium: `call | email | text | letter | in-person | video | voicemail-left | voicemail-received`
- Who (student): name
- Who (client side): client name, or "third-party: [description]" if from opposing counsel, family member, etc.
- Duration / length (e.g., "10 min call", "3-paragraph email", "45 min in-person meeting")
- Summary: 2-4 sentences. What happened, what was substantive.
- Action items:
- What the student owes the client (with deadline)
- What the client owes the student (with expected timing)
- Follow-up due: date if applicable
- Notes: anything that matters but doesn't fit above — language used, emotional tone, family dynamic observed
**Before writing:** show the user the formatted entry and ask for confirmation. Clinic records should be reviewed before they're written, not after.
**Append** to `~/.claude/plugins/config/claude-for-legal/legal-clinic/client-comms/[case-id]/log.md`. If the log doesn't exist, create it with a header:
```markdown
# Communications Log — [case name]
**Case ID:** [case-id]
**Client:** [name]
**Opened:** [YYYY-MM-DD]
Append-only. Most recent at top.
---
```
Then prepend new entries at the top (most recent first).
### `--read` — show recent entries
Print the most recent N entries (default 5). Useful when picking up a case mid-semester or before a client call.
### `--summary` — condensed read
Produce a one-paragraph summary of the log — most recent contact, total entries, common medium, any open action items from the student side, any unanswered communications. Feeds `/semester-handoff` and `/status`.
### `--patterns` — flag concerns across the log
Scan for:
- **Unanswered communications from client.** Client called or emailed N times without a response entry.
- **Missed follow-up.** Action item with follow-up due date, and no later entry resolving it.
- **Language / accommodation issues.** Client language noted as non-English; check whether outgoing communications have been in that language.
- **Escalation patterns.** Client tone shifting (frustrated / distressed) across entries.
- **Gaps.** Long stretches with no contact on an active case.
This is a supervision tool. Clinical professors running `--patterns` across their cases see which students might need support.
## Integration
- **`/client-letter`:** after generating and sending a letter, offer to log it as an outgoing comm.
- **`/status client`:** when producing a client-facing status summary, offer to log it (often these summaries go to clients).
- **`/client-intake`:** first entry in every new case's log is the intake contact.
- **`/semester-handoff`:** handoff memos read `--summary` for each case to populate the communications-history section.
- **`/deadlines`:** if a communication established a deadline ("client said they need to respond by Friday"), offer to `/deadlines --add`.
## What this skill does not do
- **Store substantive legal analysis.** That lives in intake, memo, and status files. The log is communication record — facts of contact, not legal strategy.
- **Auto-log from outside systems.** If the clinic uses a case management system (Clio), an integration could pull call logs and emails automatically. That's a future add; not v1.
- **Edit past entries.** Append-only. If an entry is wrong, write a new entry referencing and correcting it. The integrity of the log depends on not rewriting history.
- **Enforce lExcerpt, first 6,000 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/client-comms-log/)
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/client-comms-log/)
<a href="https://modelsatlas.com/skills/anthropics/client-comms-log/"><img src="https://modelsatlas.com/skills/anthropics/client-comms-log/badge.svg" alt="ModelsAtlas: SAFE B"></a>
Questions about client-comms-log
What does the client-comms-log skill do?
Is client-comms-log safe to install?
What can client-comms-log access on my machine?
How current is this page?
Sources
- github.com/anthropics/claude-for-legal/tree/main/legal-clinic/sk — 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 client-comms-log skill do?
- Is client-comms-log safe to install?
- What can client-comms-log access on my machine?