Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add ZekaiSuni/claude-for-legal-turkish --skill client-comms-loggit clone --depth 1 https://github.com/ZekaiSuni/claude-for-legal-turkishWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/zekaisuni/claude-for-legal-turkish/client-comms-log)<a href="https://agentmods.dev/skills/zekaisuni/claude-for-legal-turkish/client-comms-log"><img src="https://agentmods.dev/badge/skills/zekaisuni/claude-for-legal-turkish/client-comms-log/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/zekaisuni/claude-for-legal-turkish/client-comms-log"><img src="https://agentmods.dev/badge/skills/zekaisuni/claude-for-legal-turkish/client-comms-log.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00078 | $0.01484 |
| Opus 5 | $0.00039 | $0.00742 |
| Sonnet 5 | $0.00016 | $0.00297 |
| Haiku 4.5 | $0.00008 | $0.00148 |
Grade A, and why
client-comms-log scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 9d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 117 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/client-comms-log
- Use the workflow below.
- Require case-id (prompt if not provided).
- 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.
- Integration: offer
/legal-clinic:deadlines --addif the log establishes a deadline; route to/legal-clinic:semester-handoffvia--summarywhen relevant.
Client Communications Log
Purpose
Four reasons to keep this log:
- 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.
- Continuity at handoff. The next semester's student takes over and reads the log; they don't re-ask the client questions already answered.
- 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.
- 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
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 9d ago First seen · 117 lines · 78 tokens per session scan A 6da1c6f9af1f
client-comms-log is a skill published in the GitHub repository ZekaiSuni/claude-for-legal-turkish (103 stars, last pushed 4mo ago), licensed Apache-2.0. It adds 78 tokens to every session and 1,484 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
Other skills, from other repositories
vendor-review
Evaluate a vendor — cost analysis, risk assessment, and recommendation. Use when reviewing a new vendor proposal, deciding whether to renew or replace a contract, comparing two vendors side-by-side, or building a TCO breakdown and negotiation points before procurement sign-off.
entity-compliance
Entity compliance tracker — initialize, report upcoming deadlines, update status, run health audit, export to CSV. Maintains a compliance-tracker.yaml built from the entity table, calculates filing deadlines by entity and jurisdiction, and surfaces what's due in the next 30/60/90 days. Use when user says "entity…
integration-management
Post-closing M&A integration tracker — phased workplan, consent tracking, contract assignment at scale, weekly status reports. Initializes from whatever deal artifacts are available (purchase agreement, deal summary, closing checklist) and connects to deal-context.md and closing-checklist.yaml from the M&A cold-start.…
matter-workspace
Manage matter workspaces — new, list, switch, close, or detach (practice-level). File-management logic for keeping one client or engagement's context separate from every other. Use when working across multiple clients or matters, when the user says "new matter", "switch matter", "list matters", "close matter", or when…
patent-docket
A workflow coordinator for patent case files, from an inventor's technical disclosure to patent application documents. A patent docket is the tracked record of a patent matter, including its stage, questions, drafts, and handoffs.
performance-management
Runs performance systems that change behavior — expectations, feedback, review cycles, calibration, and handling underperformance. Use this to design or fix a review process, run calibration, write or coach on feedback, address sustained underperformance, or work out why reviews consume weeks and change nothing.