trust-entry

A command for recording money paid into or taken out of a legal trust account. A trust account holds client or case funds separately from a law firm's own money.

In plain words
What is it for?
Use it to record deposits and withdrawals with a client name, direction, amount, and compliance checks.
Why use it?
It adds checks for missing details and required Google Sheets setup before recording the transaction.

Command

Install

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.

agentmods
npx agentmods add commands/protomated/protomated-plugins-official/trust-entry
Clone the repo
git clone --depth 1 https://github.com/protomated/protomated-plugins-official
Per session 10 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 617 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00010 $0.00617
Opus 5 $0.00005 $0.00309
Sonnet 5 $0.00002 $0.00123
Haiku 4.5 $0.00001 $0.00062

Measured 2d ago against content hash 9ec5c6730d61, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

trust-entry 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 2d 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.

legal-billing-tracker/commands/trust-entry.md · 50 lines

How it starts

The opening of the file, as written. The whole thing — 50 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/legal-billing:trust-entry — Trust Account Entry

Record a trust deposit or withdrawal with compliance checks built in.

Invocation

/legal-billing:trust-entry $ARGUMENTS

Parse client name, direction (deposit or withdrawal), and amount from $ARGUMENTS. Ask for anything missing.

Workflow

Step 0 — Confirm setup first: Call connect_google with check_only: true. If not connected, stop and tell the attorney to say "connect Google" — do not collect any fields yet. If connected, proceed; once you attempt add_trust_entry, if it returns "No Google Sheet configured yet", stop and ask whether to create a new sheet from the template (create_billing_sheet, only after they confirm) or connect an existing one (set_spreadsheet_url). Only continue once both are confirmed. If you call create_billing_sheet, always paste the full sheet URL from its result into your reply — do not just say "sheet created."

Step 1 — Identify the entry type from $ARGUMENTS or ask:

  • Deposit keywords: retainer, received, deposit, paid in, upfront, advance
  • Withdrawal keywords: filing fee, disbursement, paid out, refund, cost advance, settlement payout

If unclear: "Is this a deposit into trust (money coming in) or a withdrawal (money going out)?"

Step 2 — Collect required fields:

  1. Client name — confirm spelling
  2. Amount — never $0 or negative
  3. Description — brief (e.g., "Retainer received", "Filing fee — Circuit Court")
  4. Date — default to today
  5. Matter name — ask if the client has multiple matters

Step 3 — Safety checks:

  • If withdrawal > $10,000: "This is a $[X] withdrawal from trust. Please confirm you want to proceed."
  • Double-check: for a deposit, deposit = amount and withdrawal = 0. For a withdrawal, withdrawal = amount and deposit = 0. Never swap these.

Step 4 — Confirm before calling: "Recording a $[X] [deposit/withdrawal] for [client] — [description] on [date]. Confirm?"

Wait for explicit confirmation.

Read the full file on GitHub · 50 lines

Changes

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.

  1. 2d ago First seen · 50 lines · 10 tokens per session scan A 9ec5c6730d61

Subscribe to this mod's changes

trust-entry is a command published in the GitHub repository protomated/protomated-plugins-official (2 stars, last pushed 23d ago), licensed Apache-2.0. It adds 10 tokens to every session and 617 once invoked, about $0.0001 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 2026-08-31.